ijream-applications of iot technology and computer visionijream.org/papers/ijreamv05i0452005.pdf ·...

International Journal for Research in Engineering Application & Management (IJREAM)

ISSN : 2454-9150 Vol-05, Issue-04, July 2019

6 | IJREAMV05I0452005 DOI : 10.35291/2454-9150.2019.0287 © 2019, IJREAM All Rights Reserved.

Applications of IoT Technology and Computer Vision

in Higher Education – A Literature Review *M. Lakshaga Jyothi,

#Dr. R.S.Shanmugasundaram

*Research Scholar,

#Professor, Department of Computer Science and Engineering, Vinayaka Mission’s

Kirupananda Variyar Engineering College, Vinayaka Mission’s Research Foundation (Deemed to be

University), Salem, TN, India. *[email protected],

#[email protected]

Abstract Nowadays, Higher Educational Institutions (HEIs) are adopting new technologies even before they are

recognized educationally making them compulsory technological parts of the educational system. To sustain with the

rapid educational changes and technological advancements, IoT seems to be the possible solution. IoT system senses,

collects and manipulates the data over Internet using its Unique Identifiers (UID). After few years, sum of devices

worldwide with IoT connections, ten years ahead will be approximately 75 billion worldwide. Its future lies with its

implementation. Raspberry Pi, a typical learning platform to study IoT technology has been explored. The Human

brain performs complex image processing functions, whereas the eye functions similar to a digital camera. Computer

Vision (CV) applications in Higher Education will date back to the 1980s. So, Computer Vision when coupled with IoT

technology in a Higher Education can give rise to smart, intelligent campuses improving student experiences and

positively enhancing educational perceptions. In this review paper, the literature works related to what/how different

styles, principles, and technologies that are not only related to IoT and Computer Vision technology but also any new

technological research works that can be possibly adopted into Higher Educational Environment will be discussed,

thus exploring its future with building automated intelligence in HEIs.

Keywords — Internet of Things, Computer Vision, IoT Applications, Raspberry Pi, Higher Education, Automated

Intelligence

I. INTRODUCTION

Higher Educational Institutions are integrating various

educational technologies into their educational space.

Educational transformation is becoming a trending jargon

through Computer and Telecommunication. Even though,

technologies are getting adopted; microcomputers have yet

to be effectively integrated into educational sector. From the

past two decades, Works from Researches of various fields

shows that, they have not yet succeeded in developing

complete solution for integrating educational technologies

into the educational environment. Various challenging

factors such as Space, Cost, Availability, Reliability,

Support or knowledge matters while considering their

adoption. Thus, collectively to fill these heterogeneous gaps

it is necessary to go for a better and promising solution,

here comes the technology called IoT- Internet of Things.

Nowadays, Automation has become a trending context to

refer to smartness in our everyday life. With the help of IoT,

which can act as a medium to interface physical and the

virtual worlds through the computation of the embedded

objects present in them through automation. But bringing

intelligence along with automation will stream a great start

for the future generations to work with.

With IoT concept integrated with connectivity, sensors,

analysis of data and making decisions based on the results

can simplify many real time problems in the classroom

where huge number of students will be gathered more often.

IoT will increase our everyday routines through intelligent

and strong systems making our life fast and easy in terms of

our priorities and preferences. An IoT based Higher

Educational Environment can not only provide smartness

through automation but can also provide efficient operation,

monitoring and maintaining of the routine activities inside

the classes. When we look into the difference between the

context ―smart‖ and intelligence, former is one where the

delivery of the content is quick and automatic but in the

latter one the delivery of the content cannot be quick but

will be very efficient and operational i.e., it can provide

users with the results what they are trying to do by means of

some computational works.

―A picture is worth a thousand words‖, like our vision, a

digital vision called Computer Vision came into existence

that captures and stores an image or image sets then




transforming them into meaningful information to make

interesting decisions. Our eye sight is one of the important

and brilliant creations of God among our sensory systems.

In general, it is a fact that our surrounding environment is

composed of various visual signals or signs (cues). In the

context of Higher Education, Physical cues may be Student

Classroom Activities, Teaching Activities, Student

Engagement, Academic Performance Activities,

Administrative activities, Monitoring and Maintenance

Activities etc.

Computer Vision Engineering is a composition of

interdisciplinary fields such as Artificial Intelligence (AI),

Machine Learning (ML), Image Processing, Sensor

Technologies, Augmented Reality, Robotics etc. In recent

past, application of CV technologies where done on some

closed source platforms. As in combination with IP based

technologies, a new set of implementations, environments

or systems were created that were not made possible before

resulting in a revolution on IoT innovations. Once we are

ready connecting devices with the concept of IoT, then

there arises the next step towards making things more

intelligent by generating actionable data for a better

valuable insights. Apart from the theoretical knowledge,

the future and the full potential of any technology lies in its

implementation. Considering this, various IoT prototyping

platforms have been introduced such as Arduino, Beagle

board, Intel, Raspberry Pi etc. In this review work,

Raspberry Pi platform has been taken into consideration for

its state of the art related works and technologies.

This review paper has been set to investigate how

effectively IoT along with Computer Vision can be used to

create an intelligent educational environment promoting

automation and intelligence, thus its impact in higher

education. Towards the realization of this objective, the

goals of the proposal are to survey the literature works

related to the different methodologies and styles of IoT and

CV principles or technologies adopted into Higher

Educational Environment in essence with constructing

automated intelligence based IoT systems. Thus, enabling a

quick start in providing automation in educational

institutions especially in classrooms where the students will

be gathered more often than other areas. IoT based

automation has become a developing research area to

emphasize students in knowing the importance about the

technologies that will rule the future gatherings.

This paper has been organized as follows: Section I.

which gives an overview and implementation background of

IoT technology in HEIs and the possible applications of IoT

and CV technology in the HEIs. Section II. purely focuses

on the overview of Raspberry Pi consisting of its history,

core components and models. Section III. investigates on

the major area of interest considered for the literature study.

Section IV. describes the primary research methods used for

the study and Classification of data for further analysis

Section V. investigates the existing literature works that

were taken into account for further analysis of data in the

detailed manner. Sections VI. gives the literature review

results, Section VII. limitations of this study paper, Section

VIII. reveals the discussions and findings from the papers

that were selected for the survey, Section IX. finally forms

the conclusions.

A. Technological Evolution of IoT:

Educational technology has its main purpose as serving

the entities of the educational infrastructure. Its usages in

the Higher Educational Institutions (HEIs) have become a

trend in this digital era. When a technologist named Kevin

Ashton from Britain, coined the term ―Internet of Things‖ in

1999 would have known that IoT will become so popular

forming a remarkable age called ―IoT Age‖ making

ourselves as the IoT Generations. Educational History of

IoT dates back to the 1980s with the brief history of IoT use

cases in Higher Education is discussed as follows. As said

by Mark Weiser [1], The deepest technologies are the ones

that fade away‖, i.e., computational processing will be

invisible whereas the information processing will

overwhelm surrounding us. In this context, we try to focus

on IoT in Higher Education where ―Things‖ include objects

that are not only the electronic devices or the products of

any higher level technological developments (i.e., vehicles,

appliances, equipment) but also things that we ordinarily

use around us such as chair, table etc. inside the educational

environment. The supreme goal of IoT is to make things

connected at any time, or in any place, with anything and

also with anyone using any path or any services [2].

Automatic machines can reduce man power work along

with perfection [3]. An overview of various IoT contexts

applicable to Higher Education is discussed below (Table

1.).

Table Shows Core components of Raspberry Pi

Names Term Coined By Year

Ubi.Comp

AmI

Pervas.Comp

Cont.

Affec.Comp

IoT

CPS

WoT

IoE

IıoT

IoS

IoWT

Ubiquitous Computing

Ambient Computing

Pervasive Computing

Context-Aware Computing

Affective Computing

Internet of Things

Cyber-Physical Systems

Web of Things

Internet of Everything

Industrial Internet of

Things

Internet of Signs

Internet of Wearable Things

1988

1990’s

1993

1994

1997

1999

2006

2008

2012

Late 2012

Late 2012

Recent




Table 1. In above table mentioned outlines the various

IoT contexts that are widely used in Higher Education

B. Exploring IoT Systems in Higher Educational

Environment:

Teaching. Teaching where teachers are the primary focus

with students considered to be secondary. When inducing

teaching through IoT, to concentrate on new pedagogical

techniques and approaches [4] Smart teaching methods

useful for IoT implementation such as [5-8], and how to

make a smart classroom[9], promotion of ubiquitous

learning using mobile personal device can also be made

possible, positive effects on ICT by enhancing education

process and learning effective and motivate [10].

Learning. A smart learning concept [11] based on

context-aware ubiquitous learning methods for a good

learning experience, learner-centric and service-oriented

educational paradigm without just focusing on the learning

devices [12]. Learner engagement and independent learning

can be made possible through richer contexts and

augmented techniques, in contrast, smart learning can be

supported by smart devices and intelligent technologies

[13], record lecture data and share it with e-learning

platform [14], Student-centered learning methods through

projects, problems of discovery etc were discussed [15],

better learning through connected devices [16], more

collaborative e-learning becomes vital with IoT [17].

Educational Administration. With IoT, admin can

maintain the student’s attendance record [18], students as

well as teachers, can identify their presence with

smartphones [19] to perform learning analytics on the

educational data of student’s learning activities [20],

various contexts arise for smart education. By sensing eye

gazed, emotional stress, motion detectors for gestures and

various neurological parameters to monitor them effectively

[21], through multimodal learning analytics, sensors can be

placed inside the classroom to potentially record the

activities such as temperature, capture audio feeds, wearable

wristband to sense their biological factors effects, motion

capture sensors to sense hand, eye, head, face gestures[20].

College premises. Various studies are made through IoT

to create smart environments in [22-24],There were studies

on how e-learning data be captured and analyzed to improve

teaching and learning through personalized learning [25],

Electronic equipments such as printers, scanners be

integrated with bar codes, and QR tags for better

identification, integrating embedded devices or UID to

interact with intelligent network structure to monitor objects

[26], monitoring of parking slots and number of vacancies,

message alerts can be given to reduce security violations,

Air monitors can be used to reduce noise pollution, garbage

collection systems, auto water flows in gardens, e-books

with 3D modeling of the image using QR codes can be used

in libraries.

Classroom. A teacher can maintain his/her control over

the classroom with IoT by identifying student engagement

or interest by identifying the concentration levels [27]. After

lectures are given, real-time feedback on the quality of the

lectures be arrived [28], intelligent classroom with tele-

education methods [29], automatic adjustment of lights in

the classroom, RFID tags with student ID cards [30]/ in

entrance of campus [31] or student-teacher classroom

relationship enhancement [32], transform the dumb

classroom-technology that just require human control to

smart space as ―intelligent classroom‖ with ubiquitous

computing and ambient intelligence [33].

C. Possible Applications of IoT and Computer Vision in

Higher Education:

This below mentioned diagram can give a brief

skeleton of ideas with the amalgam of Computer Vision

Technology and IoT that can be implemented in Higher

Educational Institutions.

Figure 1. Applications of IoT and Computer Vision

II. RASPBERRY PI-AN INTRODUCTION

A. An Overview of Raspberry Pi:

In the previous sections, we saw various impacts of

IoT in different educational infrastructures. However, IoT is

an integration of the various numbers of heterogeneous

technologies such as Embedded Devices, Cloud Computing,

Artificial Intelligence, Big Data and Machine Learning etc.

To make its implementation easier an alternative hands-on

platform is chosen, which is Raspberry Pi. Raspberry Pi is a

very tiny credit card sized single board computer with

affordable cost and size [34]. It can function as a multi-task

performing desktop computer. Raspberry Pi was formed by

UK registered charity in 2008 and later launched in 2012.




Drastically, more IoT Raspberry Pi models were developed

such as Pi1, Pi2, Pi3, and Pi3 is the most recent. This

platform can be used as a brilliant solution to explore IoT

technological uses in education and this paper aims at

reviewing the applications of Raspberry Pi and Computer

Vision technology in Higher Education. Below is a typical

Raspberry Pi Model.

Educational implementation of Raspberry Pi started in

2012, and once after its initial release to nurture the basic

computational education in the UK. It is basically used to

learn coding skills, build DIY (Do-It-Yourself) or hardware

projects, automation etc. It has a set of GPIO (General

Purpose Input Output) pins to control physical computing

and IoT. It is not open source but it operates in an open

source environment, with its primary OS as Raspbian.

Raspberry Pi is used to make people learn programming

languages such as Python and it is manufactured consisting

of a three boards configured through licensed manufacturers

dealt by Newark element14 (Premier Farnell), RS

Components and Egoman. Thus, they started to sell

Raspberry Pi kits online.

B. History of Raspberry Pi:

Raspberry Pi Foundation was started in 2006, with

researchers named Eben Upton, Rob Mullins, Alan Mycroft

and Jack Lang from Computer Laboratory of Cambridge

University. The team developed various models of

prototypes from 2006 to 2008 and then finally released the

first version titled ―Raspberry Pi‖. By 2008, mobile device

processors became powerful against cheap cost. Thus the

team founded the Raspberry Pi Foundation. Raspberry Pi

has become a trending jargon for researchers in IoT

technology. Within few years, various generations of

Raspberry Pi models such as Model A to Model B has been

sold for various projects on supercomputer development,

drones, games, robotics, consoles etc.

C. Core Components of Raspberry Pi:

Raspberry Pi consists of the following core components.

Figure 2. Pictorial representation of Raspberry pi and

its components. (Courtesy: Anand Nayyar (2015),

[145])


Computing

Parameters

Functionality

1. Micro USB

Supply

It requires 5volts (V) per USB2.0

standard with Micro-USB type B-

interface, connecting A connector on

one side and B connector on the other.

2. SD Card Slot Required to run Operating System. It

supports Secure Digital High Capacity

and Secure Digital eXtended Capacity.

Best suited is Class 10 with 10MB/sec

speed.

3. USB Ports Each model has USB ports depending

on the models such as B with 2 and B+

with 4 ports.

4. Ethernet jack To install or update software with

Ethernet connection consisting of RJ45

Ethernet Jack supporting CAT5/6

cables for Wireless Router Connection

or any Internet connectivity sharing

device.

5. HDMI (High

Definition

Multimedia

Interface)

To connect Raspberry Pi top TV via

HDMI cable with maximum resolution

1920X1200. Evan it can stream MPEG-

4 videos.

6. Video out (RCA

Cable)

Connection to standard monitor or TV

using RCA cable and 3.5mm stereo

cable for audio facility. Less expensive

than HDMI.

7. Status Led’s 5LED to perform functions such as

ACT: (Color-Green); Show card status

when an activity done by end user.

PWR: (Color-Red): Power which is

continuously ON when Pi is ON.

FDX: (Color-Orange): If the Ethernet

connection is of full Duplex mode.

LNK: (Color-Orange): Powered ON

with Ethernet connection establishment

and Packet transfer is started.

100: (Color-Orange): LED gets ON,

when 100 Mbps connection speed is

available and is switched OFF when it

is at 10Mbps speed.

8. GPIO Pins (General Purpose Input Output): used

to connect peripheral devices to Pi kit.

It has 40 pins, 26 for digital

inputs/outputs. 9-14 for inputs/outputs.

Also supports onboard UART, SPI,

I2C.

9. CSI Camera

Connector

Raspberry Pi has (MIPI) Camera serial

interface-2 to connect small camera

modules to Broadcom BCM 2835

processor. Version 1.01 supports 4 data

lanes, each lane carrying 1Gbps

bandwidth. PHY specification is

defined to indicate the physical and

hardware layer interface between

camera and processor id fast data

exchange is needed.

10. DSI Display

Connector

To connect Pi to LCD panel through

15-pin ribbon cable. It helps to feed

graphics data to the display through the

DSI connector.

11. System on Chip ARM based processor. To support

videocore 4 GPU, fast 3D core,

openGL, Blueray, H.264 video

playback etc.




Table 2. In above table mentioned outlines the various

core components of a typical Raspberry pi Model.

D. Raspberry Pi Model:

There are many different models released from 2012

till now. Each model has its unique features and

characteristics to perform and support the system.

Following are the Raspberry Pi Models available in the

market.

i. Raspberry Pi A+,

ii. Raspberry Pi 2 Model B,

iii. Raspberry Pi Model B+,

iv. Raspberry Pi 3 Model B+,

v. Computer Module,

vi. Compute Module 3 and

vii. Computer Module 3 Lite.

To look out for a Pi model to suit our requirements,

first and foremost is to gather important resources needed

for the Pi project.

Table Shows Computing Parameters of a Raspberry Pi

model

Computing

Parameters

Functionality

i. Speed Faster the system, more tasks in short

span of time.

ii. RAM/ROM For large programs, more RAM

needed.

iii. Physical Size and

Weight

It depends on the project-specific

requirements.

iv. Cost Budget needed for the project

implementation.

v. I/O facility Based on GPIO pins available.

vi. Networking If project demands internet, then

Ethernet or Wi-Fi modules be

required.

Table 3. In above table mentioned outlines the Shortlist

the model based on the computing parameters needed

for the project


Selection Criteria based on Computing

Parameters

Model

Low cost, Small programs, Less memory Pi Model A

Most powerful kit for DIY projects Pi Model B

Industrial Application, Strong CPU processing Pi Model

Compute

Low constrained environment, without

wireless capacity

Pi Model Zero

Low constrained environment with Wireless

networking capacity

Pi Model Zero

W

Powerful kit to suit higher level projects Pi 3 Model B+

Table 4. In above table mentioned outlines the Selection

criteria based on which the Raspberry Pi model can be

selected that suits the project.

III. MAJOR AREA OF INTEREST

A. Major topics considered for the study:

The major topics based on which the following study

has been done, are listed below:

Computer Vision Technology:

Image Processing

Augmented Reality/Virtual Reality

Robotics

3D (3Dimensional) Technology

IoT Technology:

Raspberry Pi

There are many papers available in the above

mentioned fields. However, for the purpose of this review

work and also due to constrained time limit, only around

104 papers related to the above mentioned technologies

were explored which were collected from Google Scholar,

IEEE Xplore, Academic papers, Journals, Conference

proceedings etc.

Automated Intelligence:

Automation: Creating methods/system through which

manually operated systems can be then transformed into a

machine-driven system.

Intelligence: Can be Artificial Intelligent system that

basically uses computers to find a solution to a problem that

usually needs human level understanding.

Automated intelligence is a special stream in which a

special software or hardware can be used to do the task or

the things automatically without any human intervention.

But automation alone cannot make a task very easy to be

completed. It makes it more efficient, decision making has

to be done by the system on its own without a human

instruction. There comes into the picture the ―Intelligence‖.

So, Automation can or cannot be necessarily an artificially

intelligent system i.e., Automatic system can be artificially

intelligent or it can be a system with program fix

instructions. It depends on the system specific requirements.

Artificial Intelligence is a branch of science which deals

with the computer program development using several

algorithms such as problem-solving, logical reasoning,

tackling perceptions, learning, and understanding of the

language etc. In simple words, Through Automated

intelligence, Smart systems can be transformed into

intelligent decision-based processing systems.

Papers related to IoT based Automated Intelligence are

very few and yet in the developing stage. Current research

papers are primarily on how IoT devices/ objects can be

identified, connected and managed. In this study paper, an

attempt has been made to enhance the perspective on how

IoT devices can be worked with intelligence also. Primarily,

Literature works related to IoT/Raspberry Pi use cases in

Higher Educational Sector has been explored in

combination with Computer Vision Technologies. Finally,

how Recent trends are getting evolved with Pi devices

working with Intelligence in Higher Educational Sector.

Thus, its usage in Higher Educational Institutions on




promoting Automation Intelligence with Raspberry Pi

technology has been explored.

B. Exploring the IoT/Raspberry Pi Applications in Higher

Education:

Combining Bluetooth and kinetics for designing smart

conference rooms [35], Bio sensors can be used to identify

students and stored in database using Raspberry Pi like

Moodle through Wi-Fi for attendance recording [36], smart

projectors to upload and download any PowerPoint

presentations without use of laptop in each classes, even

they can store their PPT is separate servers logging into

their unique credentials [35], PPT navigation with gesture

recognition [37], Google voice assistant using Raspberry Pi

can be used for effective classroom [38], It can also be used

for lecture projection systems using NETIO application,

controlled using Wired or Wireless connections [39],

controlled through mobile applications [40], controlled and

sharing of displays with remote desktops [41], controls to

android phones in intranet structures [42], using Virtual

Network Computing protocol for remote access in

projections [43], Real-time attendance tracker and recorder

systems using RFID tags and Knowledge Base System

(KBS) and Twilio cloud platform [44], Smart dustbin can

be used inside college premises as in [45], ELAB IoT

platform with Xively for smart learning environment [46],

Concept called ―Magic Mirror: to function as an interactive

display to give updates or information through voice

commands [47], Smart security in hostels of colleges can be

made though RFID and MATLAB with Face and thumb

recognition [48], Online exam assessments using Wi-Fi with

PHP [49], voice command based controls can be used

inside the college or classroom for effective management

[50], security system using PIR sensor also with night vision

capturing facility [51], Classroom temperature monitoring,

occupancy etc [52], automated blood bank services inside

college and direct link between donor and recipient using

GSM and Raspberry Pi and message alerts at emergency

situations [53], Digital Notice board using Mobile phones

alerts through Wi-Fi for sending notices in the form of text

[54], monitoring weather inside the college environment

using temperature, air, moisture sensors etc using

ThingSpeak on Zigbee communications and send results on

mobile apps [55], Garbage monitoring using Zigbee and

GSM on GUI platform [56], Control electrical appliances

using Flask and SQLite3 on GUI platform [57], Recycling

college drinking water treatment and monitoring using

Raspberry Pi and ultrasonic sensors [58], lecture delivery

system based on IoT using Raspberry Pi to record class

lectures in audio and video formats and through FTP

protocol and Python using VNC application [59], Learning

Management System can be implemented using Raspberry

Pi [60], Smart Blackboard/Whiteboard Cleaning using

Raspberry Pi as the control module to track the eraser

position [61], Classroom timetables can be managed

effectively using RFID, GSM and Raspberry pi [62], based

on Real-Time Clock, automated college bells can be used

without any demand from human control [63], To

demonstrate an experiment using robots inside classrooms

or labs based on human computer interaction giving voice

commands to robots [65], and also RFID based Intelligent

vehicle safety surveillances be used for precautions inside

the colleges [66]. Affective computation of student

activities- where emotions are analyzed from the behavior

or emotions of the students using Face Recognition Systems

and Open CV concepts [67].

IV. DATA COLLECTION AND

CLASSIFICATION

A. Data Collection:

This study reviews literature selected with the prime

focus on IoT technology and also Raspberry Pi and its

related technologies and its inferences to higher education,

instructional design and educational technology.

Google Scholar, IEEE Xplore were the websites used

to explore and find academic papers, journals, conference

proceedings based on the keywords ―IoT and Computer

Vision Technology in Higher Education‖ and ―Raspberry Pi

and Computer Vision Technology in Higher Education‖.

The papers analyzed include mutually quantitative and

qualitative data on the educational applications of these

technologies worldwide. For the intention of this study, the

data collected resulted in identifying around 100 papers

related to possible applications of Raspberry Pi in Higher

Education. Based on the results, it has been clearly seen that

all the articles were cited by the researchers. Since these

papers were citied they can be considered as a typical

quality representation of the literature works in this area of

study.

B. Data Classification:

Thus, this paper can give the readers with the

glimpse of the recent advancements in IoT/Raspberry Pi

technology on coupling with Computer Vision principles, so

that it can form a smart or intelligent higher educational

environment promoting automated intelligence in the

Higher Educational Sector.

Articles were separately classified in terms of

quantitative and qualitative methods. Quantitative analysis

was performed to organize the papers with the categories

such as Image Processing, Robotics, Artificial Intelligence,

3Dimensions, Augmented Reality and Virtual Reality

according to their publication years, Qualitative analysis

was done by identifyting the key concept/ key terms in each

of the literature work chosen as specified in the table below

as well as described in the following paragraphs.

To provide the readers, researchers an overview of




all the literature works, related to this paper are listed from

Table 5. to Table 9. Table 5 represents the list of possible

applications of IoT technology in Higher Education. Table

6 represents the possible applications of Raspberry Pi and

Augmented Reality, Virtual Reality and 3D. Table 7

represents the possible applications of Raspberry Pi and

Image Processing technology, Table 8 represents the

possible applications of Raspberry Pi and Robotics

technology, Table 9 represents the possible applications of

Raspberry Pi and its Recent developments.

V. REVIEW ANALYSIS

A. Internet of Things:

IoT technologies that were implemented in Higher

Educational Institutions (HEIs) were listed from the year

1989 to 2018. In 1989, Arthur Leuhrmann made Intellectual

Amplifier. Similarly, Janette et. al (2000), Tried using

Ubiquitous computing devices for teaching, learning,

communications along with portable technologies, With the

same context, Bryan Alexander (2004), have Ubiquitous e-

learning environment using mobile devices in higher

educational environment with wireless technologies. Later,

A Student Educational Device (SED) was prepared on

interaction with smart classroom using Wi-Fi devices

offering assignments, classes, textbooks and videos by

KevinMcREynold (2008).

In (2009) Smart e-learning system along with HCI

based on polka dots and color band pattern recognition

along with Augmented Reality using Speeded up robust

features for feature extraction techniques. Swati Vitkar

(2012), to make e-learning over cloud environment,

ubiquitous devices were tried communicating through cloud

networks. Ubiquitous Scientific Device Transfer (USDT)

using RFID tags and Context-aware ubiquitous learning

with sensing technology to analyze real world student’s

behavior in Gwo-Jen Hwang (2012), Further, in 2013,

Usage of ubiquitous computing devices such as Pad-type

appliances, interactive whiteboards, telepresentations using

cellular, NFC, Wi-Fi or Bluetooth inside the Classroom. In

the same year (2013), holography (3DHT) is used as a

learner’s stimulus agent in the smart learning environment

was introduced. Educational framework, where everything

in the educational domain is automated and also pervasive

computing related to cognitive domain. Similarly, (2013),

Gopinath et. al used PyBlueZ a python library module to

connect Raspberry Pi via HDMI to a touchscreen interface

using Bluetooth 2.1 dongle along with a calibrator program

of Xinput-calibrator using Radio Frequency Communication

Protocol. Uganda et. al in 2013, to teach science tried to

study the development of Epi- prototype as an educational

tool for using Raspberry Pi in educational sector especially

in Uganda in order to teach science, computing and

engineering. With a scenario of setting temperature sensor

and ADC convertor through GPIO pins in Epi to implement

a digital advertising board.

Valeriu Manuel IONESCU et. al (2014), based on GPIO

sensors with Oracle JDK 1.8 based on Multiple Client

Single server communication over TCP/IP and user

interface was added to support usability to secure data

transfer AES algorithm was also implemented. Folakemi et.

al(2014), tried using pervasive computing devices like

PDA’s, wearables, display boards, etc with 3D printing,

Games, Virtual Assistants, Daily Self-trackers. AR-based

games can be created which was made possible by (Boris

Pokric et.al) using Environment monitoring using ARGenie

and ekoNET platform integrating IoT solutions with AR

based games on a CoAP network. In 2015, 3Dholographic

Technology (3DHT) is used for teaching and learning

environment. Similar to Valeriu’s work, A Remote

controlled digital advertising board with Raspberry pi 3

model B dividing the system into multiple levels and

regions and multiple screens are also used for LCD display

via HDMI with backend as PHP and frontend as HTML5

bootstrap. E-learning environment with ubiquitous devices

and systems by (Matthew Montebello et. al, 2017), Majid

Bayani Abbasy et. al worked on Descriptive theoretical

research on IoT with Education forming a novel Internet of

Educational Things model (IoET) Various features of IoET

were statistically analyzed such as classroom engagement,

Creativity, e-Learning, self-learning, research opportunity,

collaboration etc. Mirjana Maksimoviƈ et. al (2017),

developed his work on Collaborative based IoT supported

education in classroom environment with IoT enabled

devices such as Interactive whiteboards, Smart document

camera. Jay R.Porter (2017), Building automation with

IoT Building Monitoring Device (IBMD) along with 3D

printers is introduced to teachers and students with various

STEM concepts using Edukas Model, Ant Colony

Optimization, Random Forest and Principal Component

Analysis. In 2017, Luka Petroviƈ et. al, Web based

application using PHP and Laravel 5.3 framework, MYSQL

along with RFID tags and QR codes on Moodle LMS

interconnection with plant watering scenario and Vuforia

task to recognize Raspberry pi system and complete IoT

schemas to test knowledge on the subject by assigning tasks

of different difficulty levels. Works related to combining AI

and AR for teaching and learning practices by Stefan A. D.

Popenici et al, Fernando Moreira et. al also worked on

Conceptual approach to enhance the learning process of

TLP in the higher education by deploying IoT, Big Data,

and Cloud Computing technologies. A Smart advertising

board by Togo Similar to Valeriu’s work, implemented

using Raspberry Pi on Wi-Fi connection via HDMI display

and GUI based webpage is created using PHP language and

MYSQL for database communication. To evaluate student’s

attention inside classroom by integrating RFID system with

indoor positioning system from teacher’s perspective by




Rawia Bdiwi et. al (2018). Ana-Maria SUDUC and

Shahbaz et. al investigated on enhancing teaching and

learning using various IoT technologies in education. Using

EDM(Educational Data Mining) techniques with respect to

Student’s profile, Learning content customization,

Performance predictors, concept maps, courseware

construction, classify characteristics, Undesirable behavior,

Group students, Social Network Analysis, Intelligent

Systems for instructor feedback etc. to help educators in

making decisions related to students academic performances

based on the data generated with Binary Edge Detection

Method, Adaptive thresholding, Ellipse fitting method,

Pixel sampling, Running video Average. Sensor technology

to track 3D objects by Diego Lǒpez de Ipiña and QR codes

to implement in higher education as QR codes based

textbooks, geolocation based information display, using

camera name and ratings of place be displayed by Ashmit

Kohli(2018). The above analysis is based on the references

[64-95]

B. Augmented Reality:

To possibly see the applications of Raspberry Pi and

Augmented Reality, Virtual Reality and 3D, it is visible that

in the recent years various works have been done such as in

2015 and 2017, Augmented Reality has been used with

wearable devices to create teaching and learning

environments by Suvarna et.al, Dharmateja et.al, Nikhil

et.al, and Sűleyman et.al. A Model to combine

Computational Experiment along with Computational

Thinking with physical computing environments connecting

Ejs or Scratch in Raspberry Pi for an inquiry based learning

activities with STEM epistemology practices by Sarantos

(2017), Energy Monitoring system by Jannish as interfaced

with Computer Vision and AR using Node-Red tool and

Influx DB, TP-Link HS110, MQTT. A Novel Mobile

learning with Augmented Reality using 3D models with

Motion Estimation, Page Determination, Text Recognition,

Model Rendering modules with OCR to explain theoretical

concepts by Xunyu (2018). Iain (2004) tried his work on

Blind WA in combination with Cisco Systems deploying 3D

sound models, Haptic systems and Braille concepts along

with visuo-spatial concepts for vision impaired students

with easy access to learning materials. Low cost tablets for

rural students by Putjorn (2015), Video streaming with

holograms (2017). The above analysis is performed from

the references [96-103]

C. Image Processing:

While focusing on Image Processing algorithms, An

Android based educational tool (Mobi4Ed) is used to study

the Image/Image Processing algorithms with client as

Google Nexus and Server with Intel Xeon CPU and

Windows Server 2008 R2 running OpenCV with Visual

C++ by Romy Ferzli et.al (2011). Detecting laser spot with

OpenCV Library by capturing an image through webcam

installed and connected to USB port on Raspberry Pi. It can

be used against a computer based image processor system

(Aryuanto et. al (2014)), A real time, finger gesture

recognition by Geraldine (2015), Similarly in 2015, Novel

technique to control wheelchair remotely based on eye

movement for the disabled persons based on image

processing techniques at different stages such as Eye

detection and Face detection, Edge detection, color

conversion, Hough Transformed, motion detection and

object tracking on OpenCV library installed on Raspberry

Pi (Shyam et. al) , In the same year, Varsha tired to detect

the vigilance of drivers using real time image processing

and computer vision techniques with automatic alarm

systems. Qifan proposed a novel method to detect fall alarm

and abnormal inactivity of the elderly people using

Computer Vision and Image processing techniques and alert

is sent through SMS or mail through TCP/IP protocol.

Hassna in 2015, Embedded agent for Cardiac MRI images

along with Java Agent Development (JADE) platform for

multi-agent system construction. Implementing Parallel

algorithm with C-means method executed on Raspberry Pi 2

devices. Marko in 2015, proposed, a multi-camera based

remote surveillance system supporting images with 1080

pixels consisting of a 10-second refresh rate. Raw image is

taken using tool called raspiyuv. Image is compressed with

Kvazaar HEVC encoder to output HEVC image in BPG

format. These images were broadcasted over camera nodes

to terminals over Internet with WebSocket Protocol and a

client server model with image broadcasted to client

through node.js and the client receiving images in full-

duplex communication without polling. QR codes on

integration with Raspberry Pi with image processing

techniques and UVC Camera driver and Open CV library

on TFT_LCD display by P.V.Vinod et.al (2015). Digital

image processing for road sign recognition system with

embedded computing platforms such as Raspberry Pi,

Capture images with OpenCV library and Image processing

algorithms such as OpenCV Contour and Edge detection,

Optical Character Recognition run on Ubuntu MATE with

GPIO pins interaction with Camera module. k-NN for

feature classification and geometric space by Enis et. al

(2016), (Jyoti) in 2016, proposed a Wi-Fi based

photography using hand gestures, In 2016, Shaik et. al

proposed A 2- dimensional game using Raspberry Pi using

Python Tkinter, Accelerometer and Hand Gesture

controlled camera using SimpleCV library and image

processing techniques, LM358 converts analog value to

digital, thus pi uses those values to control game through

display. Pi connection to laptop with SSH protocol. The

same way Nestor(2016), Integrating Augmented Reality

with Image processing techniques such as Color Markers,

Ad-hoc Marker selection, Single/Double Marker, Fiducial

Markers Transformations on Raspberry Pi 3 Model 2B to

detect the user and display a garmet cloths and accessories




on the person. Fire pattern recognition, face recognition

systems were developed by Dhanujalakshmi et.al, Kiran

et.al and Lubasi et.al in 2017 and 2018. Pi Book Reader by

Aditi et. al (2018). The above analysis is performed from

the references [104]-[121].

D. Robotics:

In the area of Robotics, few papers were surveyed as

mentioned below, Keerthi et. al (2015), Robotic arm is used

with Raspberry Pi with 15 GPIO pins interfaced by

controlling the joints of the robotic arm and its movements

though Android application with the Wi-Fi connection.

Morgane et. al in 2017, proposed an educational robots

such as Thymio robot has been studied to determine how its

usage been perceived by the teachers in education. A

Collaborative Robotic Educational Tool with a main

module FGPA communicates with Smart devices via

Bluetooth, with secondary module integration with Arduino

shields. External elements included such as Servo

management, motor control, memory., etc. They have also

provided scenarios to implement in educational activities

such as 4-wheeled robot arm, Educational drones,

Educational Environment, Smart Devices, Internet remote

playground, Pedro et. al in (2016). A Controlling robotic

arm SCORBOT-ER III to do several industrial tasks

automatically using Raspberry Pi model B and Image

Processing techniques along with TP-LINK TL-SC3230

type IP camera connected via D-Link DGS-1024D Ethernet

switch to the Ethernet port. With this setup, after execution

the robotic arm will hook up the given marked object using

its green bottle stopper and placing it in the exact recipient,

irrespective of its position. Real-time acquisitioned image

with overlays of lines and circles for calculating for target

position of the robotic arm to move the object by Roland et.

al (2016). But in 2015, Miller et.al proposed SCmesh

allows camera for object tracking, event detection, file

transmission to monitor environment, habitat, surveillance

etc. with SlugCam and Wi-Fi. The above analysis is

performed from the references [122]-[126].

E. IoT in Teaching and Learning:

While in the recent advancements, Nikolas et. al

(2014), proposed a model integrating Raspberry Pi and its

software to teach Physics concepts through lessons, e-

books, experiments, code examples etc. along with

PHP/MYSQL on Linux with better user interfaces possible

by JS/jQuery, AJAX, JSON etc. emphasizing on its

importance to use Pi in educating schools as well as college

students at various distributed subjects with scientific

proofs. Again, in the same year, A Clustering of 8

Raspberry Pi Boards in the form of parallel supercomputers

along with Ethernet, USB with slave nodes for power

supply and master nodes for keyboard, mouse, display

connections forming the PiBrain to educate students in

concepts of Introduction to Programming supercomputers at

a very little cost running on ARM processor. It utilizes MPI

(message passing protocols) for communication in parallel

programming models by P.Turton et.al. Rebecca et. al

(2016), examined the classroom applications of Rpi in

teaching Database management course, computer

architecture course, Computer organization course as a

prerequisite for teaching IoT technology based on active

learning projects with a computer lab setup for Rpi in a

testbed environment. Diyana et. al (2015), For a virtual

laboratory, Raspberry Pi acting like a console server for

remotely accessing communication devices following steps

such as serial port selection, Serial port configuration based

on Speed/Band rate, Number of Bits, Parity, Number of

Stop Bits and Flow control etc. thus enhancing the

education in the computer science fields and its

correspondingly related subjects. Investigation of teacher’s

reaction towards CPD (Continuing Professional

Development) programme with Raspberry Pi to enhance the

skills in circuitry, python programming, hardware

configuration etc by doing workshops with Bridge21 model

to learn Raspberry Pi. With several stages such as set up

phase, warm up, investigation stage, planning stage, create

stage, present, reflect stage to do projects and learn with

Raspberry Pi by J. R. Byrne et. al (2016). Peter Jamieson et.

al (2016), Integrating Raspberry Pi into education thus

enhancing the student’s skills in Project based learning for

ECE students by introducing Pi related courses into

curriculum against several challenges such as Open Source

project accessibility, student progress etc. Marina et. al

(2015), installing Remote Experimental Labs (RExLab) for

teaching various physics concepts in the schools using

Raspberry Pi B model and PiFace interface. User

interaction module is developed by PHP with a web server

application such as Apache or Lightpd. Heat Propagation

Experiment was conducted with main server processing

PHP pages and Pi process commands of experiments.

Communication between each controller and main server.

Microcontroller will do control commands. Online

experimentation with a setup to run Python on Raspberry Pi

and receive the results for the experiments using a camera

module with the help of IEEE 802.15.4 WSN

communication solution to locally collect sensor data. LMS

Moodle platform to experience interaction with lab and

hence calculations are done and analyzed. Finally forming

management system with first-come, first served approach

to access remote lab by Hélia et. al (2015). Using Net IO,

A projector is remote controlled from a mobile phone via

Ethernet /Wi-Fi and Raspberry Pi 2 Model B+ providing an

unified server facility by Siddharth et. al (2016). Wi-Fi

Based Projector to display content of the screen on laptop

as well as mobile and Raspberry Pi through Virtual

Network Computing by Manaswi et. al (2016) . Kazuaki et.

al (2016), To study the networking concepts, real

networking systems are to be developed. Physical




Visualization and Physical manipulations with two

equipments for Terminal and Router, Dials and buttons and

LED lumps for physical direct manipulation collectively

connected to Raspberry Pi with wheezy OS. Low-cost

laboratory using Raspberry Pi Model B+ to promote

electrical engineering education has been developed for

courses such as Digital Signal Processing and

Instrumentation with Ethernet, Wi-Fi network connection

for real time remote measurement with mySQL for data

storage by Ciira et.al (2016).

F. Recent trends in IoT and Raspberry Pi technology:

Real time emotion based facial recognition system using

Image processing techniques to detect facial emotions such

as anger, digust, happiness, surprise and neutral with

Raspberry Pi with CMU MultiPIE database with image

collections. With remote desktop connections, and Virtual

Network Connections (VNC) and putty software by

Suchitra et. al(2016). AI based smart mirror like interface

device equipped with Raspberry Pi, microphone , speakers

to display weather updates , news etc. with speech

recognition by Vaibhav et.al (2017). Speech based robot

connected to a Raspberry Pi board through Bluetooth or

Wi-Fi and further it is operated based on the commands

with APP AMR Voice by Renuka (2017). Drones and

raspberry pi technology used to educate students on robotics

course by making them build their own drones on the

Robotics OS using any web and SSH environment like a

base station. Equipped with a single piece plastic frame,

ESC driven DC motors along with reinforced shafts and

bearers via JavaScript interfacing to SkyLine3, camera and

IR distance sensors by Isaiah et. al (2018). A wireless

notice board to display text, image or pdf files on Projector

and mobile application to convert any voice message into

text format and sent back to the board using cloud storage

by Ganesh E.N. et. al (2018). 360-degree video processing

with raspberry pi to improve teaching and learning

experiences with AR/VR technology based on scenarios

such as Teacher training video analysis, Mobile lecture

recording and Group discussions by Micheal et. al (2018).

Investigation on the applicability of Raspberry Pi as an IoT

technology in the field of education considerably in a

teaching process along with Learning Management System

(LMS), Machine Learning, To examine student social

behaviour based on the facial expression with Face

detection technology, Feature Extraction, Classification

based on facial expression. Teachers feedback on lecture

quality by Salman et. al (2019). On some specific topics

trending nowadays, few literatures have been proposed such

as: Micheal Derntl et. al(2013), proposed a dynamic topic

mining model so as to address various challenges in

Learning Analytics and Knowledge (LAK) data sets and to

explore and visually analyse D-VITA a web based browsing

tools was developed for dynamic topic models. Some other

papers were related to IoT based smart education system as

in 2018, N.Indira et. al developed a voice controlled robot

arm with Raspberry Pi using Google Alexa and Artificial

Neural Network. Alberto Pacheco et. al (2018), tried

creating a Osmotic computing architecture model for a IoT

based smart classroom is used to test deep learning models

for person detection by comparative study with cloud, fog

microserver and mobile edge computing device against

some limitations with real time responses with IoT

applications. Similarly, Katalin Ferencz et. al have deployed

a self designed Raspberry Pi based extension board to

collect sensor data with Apache Cassandra, a database

cluster to store senor data in low cost servers on web based

Glassfish application server with Pi Java based platform.

For Real time analytics, Wajdi Hajji et. al (2016) for

constructing Pi based Cloud so as to study the feasibility of

big data analytics in real-time environment both in virtual

and native real world environments with Apache Spark,

HDFA and Docker platform on MAGEEC ARM Cortex

M4-based STM32F4DISCOVERY board for measuring the

energy consumed by a Raspberry Pi model. Nicholas

Constant et. al(2018), A prototype for smart fog gateway

along with Pi and Intel Edison for Wearable Internet of

Things(w-IoT) devices in achieving smart analytics and

selective transfer to cloud for long term storage and

temporal variability monitoring. Tested over e-textile

gloves. In the same years for Deep learning, works were

done by (Ajay Kushwaha et. al). Automatic theft alert

system to alarm the owner using camera based theft

detection with machine learning using Convolution Neural

Network on Raspberry Pi, Ashwani Kumar et. al, Raspberry

Pi with Artificial Intelligence using Artificial Neural

Network (ANN) of CIFAR-10 model along with

Tensorflow to help the visually impaired people based on

image and video processing techniques, Marcelo Worsley

et.al, Multimodal Learning Analytics based literature review

works that deeply emphasize on deep learning to develop

data collection tools to find a way to use MMLA through

Raspberry Pi also.

The above analysis for subsection E. and F. is based on

the references [127]-[168]. The above accomplished data

analysis has been given in the form of table format below

for user reference.




Table Shows Relative Survey on possible applications of IoT technologies in Higher Educational Institutions.

Authors Year Concept CV Technology IoT Technology Application

Arthur

Leuhrmann

1989 Intellectual Amplifier - IoT Education

Janette et. al 2000 Ubiquitous computing using theoretical

framework for teaching, learning and

communications along with portable

technologies.

- Ubiquitous

teaching and

learning

Education

Bryan Alexander 2004 Mobile based ubiquitous learning in higher

education with wireless technologies.

Sensor Technology Mobile based

learning

Higher

Education

Kevin McReynold

2008 Student Educational Device (SED)

interact with smart classroom using WI-

FI.

Human Computer

Interaction

Mobile based

learning

Smart

Classroom

Sang Hwa Lee 2009 E-learning system with interactive HCI

based on polka dot and color band

pattern recognition and AR

Human Computer

Interaction, Augmented

Reality, Feature

Extraction

E-learning Smart Learning

systems

Swati Vitkar

2012 Cloud based e-learning for ubiquitous

computing environments.

- Ubiquitous

Computing

Higher

Education

Gwo-Jen Hwang

2012 Analyse real world student’s behaviour. Sensor technology Context-aware

Ubiquitous

learning, RFID

Higher

Education

Catherine et. al 2013 Usage of ubiquitous computing devices

such as Pad-type appliances, interactive

whiteboards, telepresentations using

cellular, NFC, Wi-Fi or Bluetooth inside

the Classroom.

- Ubiquitous

learning

Higher

Education,

Classroom

Robin A.Waliker 2013 Use holography (3DHT) as a learners

stimulus agent in the smart learning

environment

3D Holography Ubiquitous

computing

Education

Jasmine Norman 2013 Educational framework where everything

in the educational domain is automated

and cognitive

- Pervasive

computing

Education

Gopinath

Shanmugasundara

m et. al

2013 PyBlueZ is python library module used to

connect Raspberry Pi using Bluetooth 2.1

along with a calibrator program of

Xinput-calibrator using Radio Frequency

Communication Protocol

Human Computer

Interaction

IoT based

teaching

-

Murat Ali et.

al[2013]

2013 Epi- prototype as an educational tool

with Raspberry Pi to teach science,

computing and engineering.

- IoT based

teaching

Education

Valeriu Manuel

IONESCU et. al

2014 Implementing custom digital advertising

board based on GPIO sensors with Oracle

JDK 1.8 over TCP/IP and AES algorithm

for security.

- Internet of

Educational

Things

-

Folakemi et. al 2014 3D printing, Games, Virtual Assistants,

Daily Self-tracker can be used with

pervasive computing devices such as

PDA’s, Wearable devices, display

boards.

3D printing, Games,

Augmented Reality,

Human Computer

Interaction

Pervasive

computing ,

Wearable

Technology

Classroom

environment

Upadhye sudeep 2015 3Dholographic Technology (3DHT) is

used for teaching and learning

environment.

3D technology for

teaching and learning

- Higher

Education

Boris Pokric et.al 2015 Environment monitoring using ARGenie

and ekoNET platform

Augmented Reality

based games

IoT, CoAP

protocol

Smart

Environment

Umakant B.

Gohatre et. al

2015 Remote controlled digital advertising

board dividing the system into multiple

levels and regions and multiple with

backend as PHP and frontend as HTML5

bootstrap

- Raspberry pi 3

Model B, Internet

of Educational

Things

Education

Matthew

Montebello

2017 Smart Learning environments with

ubiquitous computing in e-learning.

- Ubiquitous

learning

E-Learning

Majid Bayani

Abbasy et. al

2017 Descriptive theoretical research on

forming Internet of Educational Things

model (IoET) to analyze classroom

engagement, Creativity, e-Learning, self-

learning, research opportunity,

collaboration etc.

- Internet of

Educational

Things

Education

Mirjana

Maksimoviƈ

2017 Collaborative based IoT supported

education in classroom environment with

IoT enabled devices such as Interactive

Human Computer

Interaction

Internet of

Educational

Things

Higher

Education




whiteboards, Smart document camera

Jay R.Porter et. al 2017 Building Monitoring Device (IBMD)

along with 3D printers for teachers and

students with various STEM concepts

using Edukas Model, Ant Colony

Optimization, Random Forest, Principal

Component Analysis

3D printers IoT based

automation

Hıgher

Education

Luka Petroviƈ et.

al

2017 Web based application using PHP

and Laravel 5.3 framework, MYSQL on

Moodle LMS interconnection with

plant watering scenario and Vuforia

task to identify pi model,complete IoT

schemas to test knowledge on the

subject.

Human Computer

Interaction

IoT, Raspberry Pi

RFID, QR for

learning

Hıgher

Education

Stefan A. D.

Popenici et al

2017 Integration of AI and Augmented Reality

to teaching and student learning practice.

Artificial intelligence,

AR

- Education

Fernando Moreira

et. al

2017 Conceptual approach to uplift the learning

process of TLP in the higher education by

deploying Big Data, IoT, Cloud

Computing technologies

- IoT based

learning, Big

Data, Cloud

Education

Toge Swatee

Pralhad et. al

2017 Smart advertising board using Raspberry

Pi on Wi-Fi and GUI based webpage is

created using PHP language and MYSQL

for database communication.

- Internet of

Educational

Things

Education

Rawia Bdiwi et. al 2018 Indoor positioning system to evaluate the

attention of students from teacher’s

perspective.

- Internet of

Educational

Things

Smart Learning

Environment

Ana-Maria

SUDUC

2018 Survey work on educating students to

enhance their learning experiences

through IoT technologies.

- IoT based learning Higher

Education

Shahbaz et. al

2018 IoT enabled classroom environment to

promote teaching and learning process

with IoT tools and technologies based on

the data generated by IoT devices.

- IoT based

teaching and

learning

Hıgher

Education

Everton Gomede

et. al

2018 Educational Data Mining with respect to

Student’s profile, Learning content

customization, Performance predictors,

etc. to help educators in making decisions

related to students academic

performances based on the generated

data.

- Educational Data

Mining, IoT

Hıgher

Education

Diego Lǒpez de

Ipiña

2018 Sensor system that can track the target

using virtual 3D environment

3D, sensor technology - Education

Ashmit Kolli 2018 QR codes based textbooks, geolocation

based information display, using camera

name and ratings of place be displayed.

Augmented Reality, QR

codes

- Smart Learning

Table 5. In above table mentioned outlines the possible applications of IoT technologies in Higher Educational

Institutions based on the work done in the past 20 years.

Table Shows Relative Survey of possible applications of Raspberry Pi and Augmented Reality, Virtual Reality and 3D.

Authors Year Concept Algorithm Application

Suvarna kumar

Gokula et. al

2015 Augmented reality in OpenSpace 3D - Augmented

Reality.

Dharmateja et. al 2015 Wifi enabled touchscreen tablet

- Virtual

Reality

Nikhil

Paonikar at.

al

2017 AR and wearable voice-controlled interface with head mounted

display.

-

Augmented

Reality, Image

recognition.

Sűleyman Nıhat

Sad et. al

2017 Ubiquituous based mobile learning with augmentation in the

classroom environment

AICHE Model,

KOLB’s Four Stage

Learning Cycle

Augmented

Reality

Martin

Gonzalez

2017 AR with Kinetics for physics and maths education. Amazon’s Voice

Service.

Kinetics,

Augmented

Reality.




Sarantos

Psycharis et. al

2017 Computational Experiment and Computational Thinking with physical

computing with Pi for inquiry based learning activities with STEM

epistemology practices.

Simulation,

augmentation

methods

Augmented

Reality

Nishant Shani et.

al

2018 Pygame development using Simple DirectMedia Layer(SDL) PyODE Python

Open Dynamics

Engine

Augmented

Reality

Jannish

A.Purmaissur et.

al

2018 Energy monitoring interfaced with Computer Vision and AR using

Node-Red tool and Influx DB, TP-Link HS110, MQTT.

Open CV

Augmented

Reality, Image

Processing

Xunyu Pan et. al

2018 Mobile learning with AR and 3D models Motion Estimation, Page

Determination, Text Recognition, Model Rendering modules with

OCR to explain theoretical concepts

Open CV

Augmented

Reality,3D

models

Iain

Murray

2004

Blind WA in combination with Cisco Systems to deploy 3D sound

models, Haptic systems and Braille concepts along with visuo-spatial

concepts for vision impaired students

Multimodal learning

3D models,

haptic models

Putjorn et. al 2015 Educational learning tool for rural students with low cost tablet

computers.

OBSY sensing

device

3D modeling,

3D printing.

Prajakta et. al 2017 Video streaming using holograms Pepper Ghost

Effect

3D technology

Table 6. In above table mentioned outlines the possible applications of Raspberry Pi and Augmented Reality, Virtual

Reality and 3D based on the work done in the past 5 years.

Table Shows Relative Survey of possible applications of Raspberry Pi and Image Processing Technology.


Romy Ferzli et. al 2011

Android based educational tool (Mobi4Ed) is to study the Image/Image

Processing algorithms with Google Nexus and Intel Xeon CPU and

Windows Server 2008 R2 running OpenCV with Visual C++.

Haar face-detection

algorithm

Image

Recognition,Mo

bile Cloud

Computing

Ajantha Devi et.

al

2014 Camera-based assistive device Marker-based image

recognition

Image

Processing,

Aryuanto

Soetedjo et. al

2014 Detecting laser spot with OpenCV Library through webcam on

Raspberry Pi

Laser spot detection

algorithm, Color

threshold

Image

Processing

Geraldine et. al 2015 Real-time finger gesture recognition Color markers

OCR with image

capturing techniques

Image

Processing

Shyam Narayan

Patel et al

2015 Remote controlled wheel chair with eye movement for the disabled

persons based on image processing techniques and motion detection

and object tracking on OpenCV library installed on Raspberry Pi.

Haar Cascade

Algorithm, Hough

transform method,

Gaussian Blur filter

Image

Processing

Varsha E.

Dahiphale et. al

2015 Real time driver vigilance system with CV and automatic alarm

systems

Haar Cascade

classifiers, Frontal

face detection

system, Viola-Jones

Face detection

Image

Processing

Qifan Dong et. al 2015 Detect fall alarm and abnormal inactivity of the elderly people using

CV and Image processing techniques and SMS alert or mail through

TCP/IP protocol

Gaussian Mixture

Model, TCP/IP

Image

Processing

Hassna BENSAG

et. al

2015 Embedded agent for Cardiac MRI images with Java Agent

Development (JADE) platform for multi-agent system construction.

C-means method of

Classification

Image

Processing

Marko Viitanen

et. al

2015 A multi-camera based remote surveillance sytem using raspiyuv.

Image is compressed and broadcasted over Internet with WebSocket

Protocol through node.js with client receiving images in full-duplex

communication without polling.

WebSocket, High

Effciency Kvazaar

HEVC encoder

(HEVC), Better

Portable Graphics

(BPG)

Image

Processing

P.V.Vinod Kumar

et . al

2015 QR codes Pi with image processing techniques and UVC Camera

driver and Open CV library on TFT_LCD display.

Halftone mask Image

Processing

Enis Bilgin et. al 2016 Road sign recognition system with Pi and capture images processing

algorithms on Ubuntu MATE with GPIO pins interaction with Camera

module. k-NN.

k-Nearest Neighbor,

OpenCV Contour

and Edge detection,

Optical Character

Recognition, feature

classification and

geometric space.

Image

Processing

Jyoti Yadav et. al 2016 Wifi based photography using hand gestures with Open CV. Color markers Wearable

technology

Image




Processing.

Shaik Riyaz

Hussain et. al

2016 2D game using Python Tkinter, Accelerometer and Hand Gesture

controlled camera using SimpleCV library and image processing

techniques, LM358 converts analog value to digital, thus pi uses those

values to control game through display.

Secure Shell (SSH)

protocol

Image

Processing

Nestor Lobo et.al 2016 AR and Image processing techniques on Raspberry Pi 3 Model 2B to

detect the user and display a garmet cloths and accessories on the

person.

Color Markers, Ad-

hoc Marker

selection,

Single/Double

Markers, Fiducial

Markers

Transformations

Image

Processing

Dhanujalakshmi

et. al

2017 Fire pattern recognition with heat signature and alter message is send

through MMS

RGB filter

cieLAB filter

Image

Processing,

Pattern

recognition.

Aditi.S. et.al 2018 Pi Book reader with image to text and text to speech conversion with

Open CV

Optical Character

Recognition

Gesture Speech

Recognition,

Feature

Extraction.

Kiran kumar et. al 2018

Face recognition system with OpenCV for attendance recording using

Java, MYSQL.

Principal

Component

Analysis, Haar

Cascade Algorithm

Image

Processing,

Feature

Extraction.

Lubasi Kakwete

Musambo et. al

2018

Facial authentication using Object detection method, Open CV and QR

codes.

Frontal face

biometric algorithm,

Haar Classifier

Object

detection,

Image

recognition.

Table 7. In above table mentioned outlines the possible applications of Raspberry Pi and Image Processing Technology

based on the work done in the past 7 years

Table Shows Relative Survey of possible applications of Raspberry Pi and Robotics Technology.


Keerthi

Premkumar et. al 2015

Robotic arm is used with Pi with 15 GPIO pins interfaced by

controlling the joints of the robotic arm and its movements though

Android application via Wi-Fi.

- Robotics

Morgane

Chevalier et. al 2016 Thymio robot to determine its by teachers in education - Robotics

Pedro Plaza et. al 2016

A Collaborative Robotic Educational Tool with a FGPA main module

and secondary integrates with Arduino shields. A 4-wheeled robot arm

for Education based drones, Smart Devices Educational Environment,

Internet remote playground.

- Robotics

Roland Szabó et.

al 2016

Robotic arm SCORBOT-ER III to do industrial tasks with Pi and

Image Processing techniques connected over Ethernet. Robotic arm

will hook up the given marked object using its green bottle stopper and

thus placing it in the exact recipient, irrespective of the position.

HSV filtering,

OpenCV libraries Robotics

Miller et. al

2015

SCmesh allows camera for object tracking, event detection, file

transmission to monitor environment, habitat, surveillance etc. With

SlugCam and Wi-fi.

SC mesh’s

Multipath routing,

DSR protocol

Eyes of Things,

Image

Processing.

Table 8. In above table mentioned outlines the possible applications of Raspberry Pi and Robotics Technology based

on the work done in the past 4 years

Table Shows Relative Survey of possible applications of Raspberry Pi and its Recent developments that can enhance

automated intelligence.

Authors Year Concept Algorithm Applicable

Area

Micheal Derntl et.

al

2013 A dynamic topic mining model in addressing the challenges with

Learning Analytics and Knowledge(LAK) based data sets. To explore

and visually analyse D-VITA a web based browsing tools was

developed for dynamic topic models.

D-VITA Learning

Analytics

Nikolaos

K.Ioannou et.

al[2014]

2014 Raspberry Pi and its software to teach Physics concepts through

PHP/MYSQL on Linux with better user interfaces possible by

JS/jQuery, AJAX, JSON etc.

- IoT based

Smart

Classroom




P.Turton et.

al[2014]

2014 Clustering of 8 Pi Boards for parallel supercomputers along with

Ethernet, USB with slave nodes for power supply and master nodes for

keyboard, mouse, display connections forming the PiBrain to educate

students in concepts of Introduction to Programming supercomputers

using MPI message passing protocols

MPI (Message Passing

Protocol)

IoT based

Smart

Classroom

Rebecca F. Bruce

et. al[2015]

2015 Rpi in teaching Database management course, computer architecture

course, and Computer organization course as a prerequisite for

teaching IoT technology based on active learning projects with a

computer lab setup for Rpi in a testbed environment.

SSH IoT based

Smart

Classroom

Diyana

Kyuchukova et.

al[2015]

2015 Pi virtual lab to control communication devices following steps such as

serial port selection and configuration based on Speed/Band rate,

Parity, Number of Bits, Number of Stop Bits and Flow control etc. thus

enhancing CS education.

SSH IoT based

Virtual Labs

J. R. Byrne et.

al[2015]

2015 Teacher’s reaction towards CPD (Continuing Professional

Development) programme with Pi to enhance the skills in circuitry,

python programming, hardware configuration etc doing workshops

with Bridge21 model.

Bridge21 model IoT based

Smart

Classroom

Peter Jamieson et.

al[2015]

2015 Pi to promote skills using Project based learning for ECE students by

introducing Pi related courses into curriculum against several

challenges such as Open Source project accessibility, student progress

etc.

Project Based

Learning (PBL), Open

Source Software

(OSS)

IoT based

Smart

Classroom

Marina Rocha

Daros et. al[2015]

2015 Remote Experimental Labs (RExLab) to teach physics concepts in

schools using PiFace interface. UI with PHP and a web server

application such as Apache or Lightpd. Heat Propagation Experiment

was conducted with main server processing PHP pages and Pi process

commands of experiments.

- IoT based e-

Lab

Hélia Guerra et.

al[2015]

2015 Pi based remotely controlled lab with online experiments running

Python on Pi and results are collected locally .LMS Moodle platform

interact with lab and hence calculations are done and analyzed. Finally

forming management system with first-come, first served approach to

access remote lab.

IEEE 802.15.4 IoT based e-

Lab with

Learning

Management

System

O.Dürr et. al 2015 Real time detection of face recognition using Convolution neural

network on Raspberry Pi using Fisherface classifier.

Fisherface classifier Real time

face

recognition

Siddharth Arun et.

al[2016]

2016 Using Net IO, projector is remote controlled from a mobile phone via

Ethernet /Wi-Fi and Raspberry Pi 2 Model B+ providing an unified

server facility.

- Augmented

Reality

Manaswi

R.Ganbavale[201

6]

2016 Wi-Fi Based Projector to display content on laptop as well as mobile

and Raspberry Pi through Virtual Network Computing

Remote Frame Buffer,

remote Desktop

Protocol

Augmented

Reality

Kazuaki

Yoshihara [2016]

2016 Real networking systems are developed with two equipments for

Terminal and Router, Dials and buttons, LED lump .,etc. for physical

direct manipulation collectively connected to Raspberry Pi with

wheezy OS.

- Simulation

environments

Ciira wa MAINA

et. al[2016]

2016 Pi Laboratory to promote electrical engineering education for courses

such as Digital Signal Processing and Instrumentation with Ethernet,

Wi-Fi network connection for real time remote measurement with

mySQL for data storage.

- Real time

analytics

Suchitra et.

al[2016]

2016 Real time emotion based facial recognition system using Image

processing techniques to detect facial emotions with Raspberry Pi with

CMU MultiPIE database with image collections. With VNC

Haar cascade, (26

facial points

extracted), features

extraction using

Active shape

Model(ASM), Viola-

jones face detection

and Adaboost

classifier

Real time

face

recognition

M.Karthikeyan et.

al[2016]

2016 To identify the real time object in the surveillance, army, traffic

monitoring, human machine interaction with Pi and Camera module

with robot motors

Foundation

subtraction,

Movement templates

Real time

object

detection

Wajdi Hajji et. al 2016 Constructing Pi based Cloud for feasibility study of the real time big

data analytics in virtual and native real world environments with

Apache Spark, HDFA and Docker platform on MAGEEC ARM Cortex

M4-based STM32F4DISCOVERY board to measure the consumed

energy of a Raspberry Pi technology.

- Real time Big

Data

Analytics

C.Balasubramaniy

an et. al

2016 IoT enabled Air Quality monitoring system with Raspberry Pi using

Grove sensors with ThingSpeak Cloud database with MATLAB code

to generate alert message and sent to TWITTER for real time

monitoring and analysis.

- Real time

Analytics

Vaibhav Kanna

et. al[2017]

2017 AI based smart mirror like interface device equipped with Raspberry

Pi, microphone, speakers to display weather updates, news etc. with

speech recognition

- Ambient

Intelligence

Renuka

P.Kondekar et. al

[2017]

2017 Speech based robot connected to Raspberry Pi through Bluetooth or

Wi-Fi and further it is operated based on the commands with APP

AMR Voice.

Mel Frequency

Spectral Coefficient

algorithm, ANN

Artificial

Intelligence,

Robotics




Nicholas Constant

et. al

2017 A prototype for smart fog gateway along with Raspberry Pi and Intel

Edison for Wearable Internet of Things(w-IoT) devices for selective

transfer to cloud for long term storage and temporal variability

monitoring resulting in achieving smart analytics with Tested over e-

textile gloves.

- Fog

Computing,

Edge

Computing

Badraddin Alturki

et. al

2017 Distributed data analytics to collect and analyze data in edge or fog

devices with a hybrid approach to collect data locally and apply data

fusion techniques on resource constrained devices and send to cloud

for processing.

- Distributed

data

analytics, Fog

Computing

Katalin Ferencz

et. al

2018 Self designed Raspberry Pi based extension board to collect sensor data

with Apache Cassandra a database cluster to store senor data in low

cost servers on web based Glassfish application server with PiJava

based platform

Sensor data

acquisition and

visualization

Sensor data

analytics

Rabindra K. Barik

et. al

2018 Fog computing based framework called FogLearn to apply K-means

cluster in Ganga River Basin Management , also in detecting disease

such as diabetes mellitus in patients by using swart watches worn by

patients

DNN Fog

Computing

Isaiah Brand et.

al[2018]

2018 Pi and Drones to educate students on robotics course by making them

build their own drones on the Robotics OS using any web and SSH

environment like a base station along with reinforced shafts and

bearers via JavaScript interfacing to SkyLine3, camera and IR distance

sensors.

MultiWii Serial

Protocol

Robotics

Alberto Pacheco

et. al

2018 Osmotic computing architecture model for a IoT based smart

classroom is used to test deep learning models for person detection by

comparative study with cloud, fog microserver and mobile edge

computing device against some limitations with real time responses

with IoT applications.

DNN inference model Osmotic

Computing

Ganesh E.N. et.

al[2018]

2018 A wireless notice board to display on Projector and mobile application,

convert any voice message into text, sent back to the board using

cloud.

- IoT based

Smart

Classroom

Micheal S.

Feurstein [2018]

2018 360-degree video processing with pi to improve teaching and learning

experiences with AR/VR technology based on Teacher training video

analysis, Mobile lecture recording and Group discussions

- IoT based

Smart

Classroom ,

Augmented

Reality

Ajay Kushwaha

et. al

2018 Automatic theft alert system to alarm the owner using camera based

theft detection with machine learning using Convolution Neural

Network on Raspberry Pi

CNN Deep

Learning,

Smart

Security

Mahmut Taha

Yazici et. al

2018 Edge computation based machine learning both training and inference

on Raspberry Pi with a comparative study on their algorithms

Random Forest,

Support Vector

Machines, Multi-

Layer Perception

Machine

Learning

N.Indira et. al 2018 A voice controlled robot arm with Raspberry Pi using Google Alexa

and Artificial Neural Network.

Deep Learning IoT based

Smart

Classroom

Ashwani Kumar

et. al

2018 Raspberry Pi with Artificial Intelligence using Artificial Neural

Network (ANN) of CIFAR-10 model along with Tensorflow to help the

visually impaired people based on image and video processing

techniques

CNN Image

Processing,

Artificial

Intelligence

Delia Velasco-

Montero et.al

2018 Through shallow learning, Real time Deep Neural Networks inference

have been comparatively studied based on power consumption,

throughput, precision etc. on Raspberry Pi

- Deep

Learning

Marcelo Worsley 2018 Multimodal Learning Analytics based literature review works that

deeply emphasize on deep learning to develop data collection tools to

find a way to use MMLA through Raspberry Pi also.

Deep Learning Multimodal

Learning

Analytics

Salman Mahmood

et. al[2019]

2019 Raspberry Pi as an IoT technology in teaching process along with

Learning Management System (LMS), Machine Learning, Examine

student social behaviour, lecture quality with Feature Extraction, Face

detection technology, Classification on facial expression.

Teacher Student

framework (TSI).

IoT based

Smart

Education

Table 9. In above table mentioned outlines the possible applications of Raspberry Pi and its Recent trends for

automated intelligence based on the work done in the past 7 years

VI. REVIEW RESULTS

A. Quantitative Results:

From the 34 articles selected on ―IoT in Higher

Educational Applications‖, 7 papers are related to

Teaching, 8 papers are related to Learning, 6 are related to

College Administration, 6 are related to College Premises

and 7 papers are related to Classroom implementation in

general keyword search on ―IoT in Higher Education‖.

Following figure (Fig 3.) defines more papers were related

to Learning outcomes of the students. (Fig 4.) depicts that

Out of 31 articles, papers were from 1989 to 2018, with

highest paper works collected from the publication year

2017. Out of 33 Articles, papers were ranging from the

publication year 2011-2018, with the higher number of




papers from 2015 related to possible IoT applications in

higher education as in (Fig 5.), Fig 6. shows the recent

advancements in this field, with more number of papers

from Real time analytics, second highest with Artificial

intelligence, Machine Learning and IoT based Classroom

setup and less number of papers in Fog/Edge Computing,

Simulation Environments, Robotics, Osmotic Computing,

Sensor data analytics, etc.

IoT in Higher Educational Applications

0

1

2

3

4

5

6

7

8

9

Tea

chin

g

Lear

ning

Col

lege

Adm

inis

trat

ion

Pre

mis

es

Cla

ssro

om

IoT in Higher Educational

Applications

Figure 3. Articles on “IoT Technology in Higher

Educational Applications” classified by Implemented

Region.

IoT possible applications in Higher Educational Institutions

0

1

2

3

4

5

6

7

8

9

1989

2000

2004

2008

2009

2012

2013

2014

2015

2017

2018

No. of Years [1989-2018]

No

of

Art

icle

s =

31

IoT possible applications in

Higher Educational

Institutions

Figure 4. Articles on “Possible Applications of IoT

Technology in Higher Education” classified by

Publication Year.

0

1

2

3

4

5

6

7

8

2011 2014 2015 2016 2017 2018

Years [2011-2019]

No

. o

f A

rtic

les =

33

Augmented Reality

Image Processing

3D technology

Robotics

Figure 5. Articles on “Raspberry Pi and Computer

Vision Technology in Higher Education” classified by

Publication Year.

0

1

2

3

4

5

6

2013 2014 2015 2016 2017 2018 2019

No. of Years [2013-2019]

No

. o

f A

rti

cle

s =

35

Artificial Intelligence Robotics Sensor data analytics

Fog/Edge Computing Real time analytics IoT based classroom education

IoT based Labs Learning Analytics Augmented Reality

Simulation Environments Ambient Intelligence Osmotic Computing

Figure 6. Articles on “Recent trends in Raspberry Pi

and Computer Vision Technology in Higher

Education” classified by Publication Year and

Trending technologies.

B. Qualitative Results:

The articles reviews are under wide range of

topics and categories which are related to IoT, Raspberry

Pi and Computer Vision in Higher Educational Institutions.

The keywords from the articles are as follows:

Deep Learning, Convolution Neural Network(CNN),

Random Forest, Support Vector Machines, Multi-Layer

Perception, DNN inference model, MultiWii Serial

Protocol, Sensor data acquisition and visualization, Mel

Frequency Spectral Coefficient algorithm, Artificial

Neural Network (ANN), Foundation subtraction,

Movement templates, Haar cascade, Viola-jones face

detection, Adaboost classifier, features extraction using

Active shape Model(ASM), (26 facial points extracted ),

Remote Frame Buffer, remote Desktop Protocol, Project

Based Learning (PBL), Open Source Software (OSS),

Fisherface classifier, MPI (Message Passing Protocol),

SSH, D-VITA, HSV filtering, OpenCV libraries, Bridge21

model, Frontal face biometric algorithm, Principal

Component Analysis, RGB filter cieLAB filter, Color

Markers, Ad-hoc Marker selection, Single/Double

Markers, Fiducial Markers Transformations, k-Nearest

Neighbor, OpenCV Contour and Edge detection, Optical

Character Recognition, Halftone mask, WebSocket, High

Efficiency Kvazaar HEVC encoder (HEVC), Better

Portable Graphics (BPG), C-means method of

Classification, Gaussian Mixture Model, Viola-Jones Face

detection, Laser spot detection algorithm, Color threshold,

Marker-based image recognition, Haar face-detection

algorithm, Pepper Ghost effect, OBSY sensing device,

Multimodal learning, PyODE Python Open Dynamics

Engine, Amazon’s Voice Service, AICHE Model, KOLB’s

Four Stage Learning Cycle, Internet of Educational

Things, IoT based learning, Ubiquitous computing,




Pervasive Computing, Context-aware Ubiquitous learning,

RFID, Drones, Real time gesture recognition, Learning

Analytics, Educational Data Mining, Osmotic Computing,

Fog Computing, Edge Computing, Ambient Intelligence,

PHP, MYSQL, Wearables, QR codes, Java Agent

Development Environment (JADE), Cloud, Holography,

3D printing, Games, Virtual Assistants, Daily Self-tracker

can be used with pervasive computing devices such as

PDA’s, Wearable devices, display boards.

VII. LIMITATIONS

Due to unnatural time limit, merely 150 articles were

considered for the review work. Articles available in Non-

English languages have not been considered for this study.

As the investigation was conducted only on Google

Scholar, IEEE Xplore, International Conferences, and

Journals, Few of the Academic databases were not

included for the study.

VIII. DISCUSSION AND FINDINGS

Looking into the review results, the rise of Raspberry Pi

and Computer Vision in Higher Education Sector can be

visible from the past 20 years until present. In the IoT

impacts on Higher Education is huge driving education

into a smart and intelligent educational environment. As

we have seen various works related to IoT based higher

educational development. Different literature works were

collected and reviewed separately for Raspberry Pi

applications in higher education and also its application in

higher education specific to Computer Vision Technology

such as Augmented Reality, Virtual Reality and 3D, Image

Processing technology and Robotics.

From this study, it reveals that a huge set of examples

are available in each corner of the higher educational

sector. Take these scenarios and choosing from the recent

trending technologies, these systems have a greater scope

of making new educational transformation in the real time

future. Keeping this as the first step, we can explore and

build more projects, products and systems by integrating

two or more technologies to form a highly potential

education system. It is just a start in deriving new

invaluable sights through deeper analysis of the huge

number of educational data using Data Mining and

Analytics, Artificial Intelligence and Machine Learning

Algorithms, Deep Learning Algorithms, Educational Data

Mining (EDM) and Learning Analytics and

Knowledge(LAK), Fog/Edge Computing, Osmotic

Computing, Sensor Data Analytics, Predictive Analytics.

Thus formed IoT generated big data can be helpful in

forming a more efficient, better operational and automated

intelligent educational infrastructure can be deployed. The

study reveals that only less number of papers are available

on Real time analytics, second highest with Artificial

intelligence, Machine Learning and IoT based Classroom

setup and less number of papers in Fog/Edge Computing,

Simulation Environments, Robotics, Osmotic Computing,

Sensor data analytics. Thus, it results in enhancing the

performances of the educational workflows in the coming

future.‖

IX. CONCLUSION

With the huge technological demand in the Higher

Education Sectors, the need to grow along with the

technological advancements have given rise to look for a

solution i.e., IoT Technology. It is familiar that IoT usage

in the educational history dates back to nineteenth Century.

But its potential reformation in the past few decades has

proven it to promote a promising future in the

technological upliftment of the Higher Education Sectors.

Narrowing down IoT technology in combination with

Computer Vision techniques will create a broader view on

how the surrounding environment is managed to evolve

with the visual signs resulting in innovative use cases for

the Higher Educational field.

In this review, we have gone through plenty of use cases

for the major domains under Computer Vision technology

such as Augmented Reality, Image Processing, Robotics,

3D technology. Thus, the results reveal that not only more

works were related to Image Processing techniques in the

past ten years, but also on possible applications of IoT

technology in the Higher Educational Framework. These

above mentioned articles were highest during the past 3

years. Since these papers were taken from academic

journals and research databases, this forms it to be a good

and valuable proof on usage of IoT and Computer Vision

in the Higher Education Sector, making it to form a huge

educational transformation.

In this review paper, further we have discussed various

applications of Raspberry Pi and Computer Vision

technology in the Higher Educational Institutions

especially of Pattern Recognition principles such as Face

Recognition, Object detection, Gesture recognition and for

Robotics. There were examples with Robotics arm

implementation for teaching and learning, and for 3D

technology use cases on deploying 3D models for teaching,

learning, holography, models for visually impaired., etc. In

the recent years, few publications were available on IoT

based classrooms, labs, teaching and learning. Thus, from

the above mentioned results, it can be concluded that future

classrooms will become an IoT connected environment for

both the staffs and the students.

We surprisingly came across various new 10 domains

such as Learning Analytics and Knowledge(LAK),

Educational Data Mining(EDM), Fog and Edge

Computing, Osmotic Computing, Sensor Data Analytics,

Predictive Analytics, Artificial Intelligence, Machine




Learning, Deep Learning models and Simulation

environments with the trend set of forming the concept of

invoking automation and intelligence in the HEI

environments emphasizing on the importance on the field

of analytics, mining techniques related to education, node

level computations, sensor level analytics .,etc. This review

reveals that these with state-of-the art technologies, and

new trending technologies related to IoT and CV can help

the researchers, developers, and scientists based on this

area of interest to promote automated intelligence in the

HEI environment.

These summarized applications of Raspberry Pi in

forming a smart and intelligent educational infrastructure

can be considered as a starting guide to come up with new

ideas. This review paper limited to Computer Vision

technology will help those who are interested with IoT

based CV system deployment. The future of IoT concept

with CV seems to be more amusing as more connecting

things will start to communicate with less human

interaction bringing a shift in the way the higher education

and its environment will thrive to survive.

REFERENCES

[1] Shahla Gul, Muhammad Asif, Shahbaz Ahmad, Mahammad Yasir,

Muhammad Majid, M.Sheraz Arshad: A Survey on Role of

Internet of Things in Education. International Journal of

Computer Science and Network Security, vol. 17, no. 5, 2017.

[2] Keyur K Patel, Sunil M Patel, T.: Internet of Things- IoT,

Definition, Characteristics, Architecture, Enabling Technologies,

Application and Future Challenges. IJESC International Journal of

Engineering and Computing, vol. 6, Issue no. 5, ISSN: 2321

3361,2016.

[3] Nidhi Shukla, Sandhya Mishra.: Internet of Things(IoT): A Future

Vision On MODERN SOCIETY. International Journal of

Engineering and Techniques. Vol. 4, issue. 3, pp. 12-15, 2018.

[4] Tikhomirov V., Dneprovskaya, N., Yankovskaya E.: Three

Dimensions of Smart Education, 2015.

[5] Fitzgerald, R., A Smart Teaching System, 2013.

[6] Moazeni, S., Pourmohammadi, H. Smart teaching quantitative

topics through VARK learning styles model. IEEE Integrated

STEM Education Conference, 2013.

[7] Tilton., W., Adult professional development: can brain-based

Teaching strategies increase learning Effectiveness? Fielding

Graduate University, ProQuest, 2011.

[8] Tredowski, TN., Woods, AM.: Seven Student-Centered Principles

for Smart Teaching in Physical Education, Journal of Physical

Education, Recreation & Dance. vol. 86, no. 8, pp. 41-47, 2015.

[9] Zhu, ZT, Yu, MH, Riezebos, P.: A research framework of smart

education. Springer Open Online Published, Smart Learning

Environment (2016).

[10] T.Priestley.,: Everything is hyper connected in the internet of

things, 2014.

[11] Gwak.D.: The meaning and predict of Smart Learning. Smart

learning Korea Proceeding, Korean e-Learning Industry

Association, 2010.

[12] Kim T., Cho J.Y., Lee B.G.: Evolution to Smart Learning in Public

Education: A Case Study of Technologies for Networked Learning.

IFIP Advances in Information and Communication Technology,

Springer, Berlin, 2013.

[13] Kim, S., Song, S.M., & Yoon, Y.I.: Smart learning services based

on smart cloud computing- Sensors, vol. 11, no. 8, pp. 7835-

7850, 2011.

[14] Shivaraj Kumar T.H, Sriraksha T.A, Noor U Saba.: An IOT Based

Secured Smart e-Campus, International Journal of Humanities and

Social Science Invention, vol. 6, no. 3, pp. 88-93, 2017.

[15] Evigeny Osipov, Laurynas Riliskis: Educating Innovators of

Future Internet of Things.

[16] Shrinath, Vıkhyath, Shivani, Sanket, Shruti: IOT Application in

Education, International Journal of Advanced Research and

Development, vol. 2, no. 6, 2017. 17. Mercatus, 2015.

[17] Chang. C.H.: Smart Classroom roll caller system with IOT

architecture, Proceedings of 2nd International Conference, IBICA,

pp. 356-360, 2011.

[18] A.Alghamdi, S.Shetty: Survey toward a smart campus using

internet of things. Proceedings 2016 in IEEE 4th International

Conference, Future Internet of Things and Cloud, FiCloud, 2016.

[19] Kusmin, M., Laanpare, M., Saar, M, Rodriguez-Triana, M.J.: Smart

Schoolhouse as a Data-Driven Inquiry Learning Space for the Next

Generation of Engineering. IEEE EDUCON – Global Engineering

Education, 2017.

[20] Bajaj V., & Pachori, R. B.: Detection of human emotions using

features based on the multiwavelet transform of EEG signals.

Intelligent Systems Reference Library, 2015.

[21] Cornel. C, & Ph.D.: The Role of Internet of Things for a

Continuous Improvement in Education, vol. 2, no. 2, pp. 24-31,

2015.

[22] Mȁkitalo-Siegi, K. Zottmann, J. Kaplan, F & Eds, F.F.: The

Classroom in the Future: Orchestrating Collaborative Learning

Spaces, 2012.

[23] Selinger, M., Sepulveda, A., Buchan J.: Education and the internet

of everything: How ubiquitous connectedness can help transform

pedagogy. Education IoE Whitepaper, Cisco, 2013.

[24] Piccianio, A.G.: The evolution of big data and learning analytics in

American Higher Education, Journal of Asynchronous Learning

Networks, vol. 16, no. 3, pp. 9-20, 2012.

[25] Debasis Bandyopadhyay, Jaydip Sen.: Internet of Things –

Applications and Challenges in Technology and Standardization,

2011.

[26] A.Rythivaara.: Collaborative classroom management in a co-taught

primary school classroom. vol. 53, pp. 182-184, 2012.

[27] Chew. C.B.: Sensors enables Smart Attendance System using Nfc

and Rfid technologies. International Journal for New Computer

Architecture and their Applications. vol. 5, no. 1, pp. 19-28, 2015.

[28] Uskov V.L., Bakken J.P., Pandey A.: The Ontology of Next

Generation Smart Classrooms. İn: L.Uskov V., Howlett R., Jain

L. (eds) Smart Education and Smart e-Learning, Smart

Innovation, Systems and Technologies, vol. 41, Springer, 2015.

[29] Mary Catherine, O’Connor.: RFID Takes Attendance – and Heat

Retrieved (2005).

[30] Hung-Wei Chen: The Study of RFID Based Roll-Call and

Entrance Control System. Master thesis, Asia University,

National Chung Cheng University (2011).

[31] Andrew W. Wright.: RFID Classroom Management System.

Master thesis, Industrial and Manufacturing Engineering,

California Polytechnic State University (2011)




[32] R.Josѐ, H.Rodriguez, N.Otero: Ambient Intelligence: Beyond the

Inspiring Vision. Journal of Universal Computer Science(J.UCS),

pp-1480-1499 (2010).

[33] https://www.raspberrypi.org/help/what-%20is-a-raspberry-pi/

[34] Dhaval Chheda et al.,: Smart Projectors using Remote Controlled

Raspberry Pi, International Journal of Computer Applications,

(2013).

[35] Arunkumar.L., Arun raja.: Biometrics Authentication Using

Raspberry Pi. International Journal For Trends In Engineering

Technology (2015).

[36] Ansari Imran, Bhatkar Firoz, Chaudhary Faisal, Khan Shahrukh,

Prof. Mubashir Khan.: Smart Lecture Delivery Using Raspberry Pi.

International Journal of Advanced Research in Computer

Engineering Technology (2015).

[37] Ch Sai Sudeep Reddy et al.: Smart Classroom using Raspberry Pi.

International Journal of Pure and Applied Mathematics, vol. 120,

no. 6, pp- 1871-1884(2018).

[38] Praneeth MSSR, Nikhilesh M., Tahrun Reddy.P., Priya B.K.:

Upgradataion of Wired to Wireless Projector using WLAN.

Recent Researches in Electrical Engineering, Dept of ECE,

Amrita College of Engineering

[39] Jaya Bharatho chintalapathi, Srinivasa Rao T.Y.S.: Remote

Computer Access through Android mobiles. IJCSI International

Journal of Computer Science Issues, vol. 9, no. 3 (2012).

[40] Suhashini Chaurasia.: Implementation of Remote Desktop Utility

Teamviewer. IOSR Journal of Computer Engineering, ISSN:2278-

0061,p-ISSN: 2278-8727

[41] Priyadharshini Raskarl, Seja Patel.: Virtual Network Computing- A

Technique to Control Android phones Remotely: International

Journal of Engineering and Computer Science ISSN:2319-7242,

vol. 3, issue. 2 (2014).

[42] Ajit Kotkar, Alok Nalawade.: Android Based Remote Desktop

Client. International Journal of Innovative Research in Computer

and Communication Engineering, vol. 1, issue. 2 (2013).

[43] Rashmi A Kalje, Prof. S.P.Kosbatwar.: Android Based Remote

control of Mobile Devices Using VNC System. IJCSIT

International Journal of Computer Science and Information

Technologies, vol. 5, no. 4 (2014).

[44] ChinjuPaul, Amal Ganesh, Sunitha C.: An IoT Based Smart

Environment for Classrooms, International Journal of Pure and

Applied Mathematics, vol. 119, no. 16, pp-239-245 (2018).

[45] Amrutha P.V., Chaithar B.N., Kavyashree D.R., Pooja S Kumar.:

IoT Based Waste Management Using Smart Dustbin.

[46] Konstantin Simić, marijana Despotovićr- Zrakić, Zivko Bojović.,

Branislav Jovanić, Đorde Knežević.,A Platform for a Smart

Learning Environment. Facta Universitatis, vol. 29, no. 3, pp-407-

417 (2016).

[47] Suryansh Chandel, Ashay Mandwarya, S.Ushasukhanya.:

Implementation of Magic Mirror using Raspberry Pi 3.

International Journal of Pure and Applied Mathematics.

[48] Sneha Sonar, Rajendra Patil.,: Hostel In Out Management and

Monitoring System Using RFID, Face and Thumb Recognition.

İnternational Journal of Innovation Research in Science,

Engineering and Technology, vol. 5, issue. 7, pp-12659- 12668

(2016).

[49] Karishma Sudharshan kalike, Vargantwar M.R.: Raspberry Pi

Based Online Examination System. Vol. 5, issue. 9, pp- 16547-

16552.

[50] Surinder kaur, Sanchit Sharma, Utkarsh Jain, Arpit Raj.: Voice

Command System Using Raspberry Pi. Advanced Computational

Intelligence: An International Journal (ACII), vol. 3, no. 3 (2016).

[51] Anabham bhavani, Tulasi Jami, Gajjala Ashok.: Low Cost Smart

Security with Night Vision Capability Using Raspberry Pi and

PIR Sensor. International Journal of Advanced Technology and

Innovative Research, vol. 8, issue. 21, pp-4053-4056 (2016).

[52] Kristian Hentschel, Dejice jab, Jeremy Singer, Matthew

Chalmers.,:Supersensors: Raspberry Pi Devices for Smart

Campus Infrastructure.

[53] Ashlesha C. Adsul., V.K.Bhosale.,: Automated Blood Bank System

using Raspberry Pi. International Journal for Scientific Research &

Development, vol. 5, issue 9, pp-1045-1047 (2017).

[54] Vinod B.Jadhav, Tejas S.Nagwanshi, Yogesh P.Patil, Deepak R

Patil.,: Digital Notice Board Using Raspberry Pi. International

Research Journal of Engineering and Technology, vol. 3, issue. 5,

pp. 2076-2079 (2016).

[55] Gaurav Jadhav, Kumal Jadhav, Kavita Nadlamani.: Environment

Monitoring System using Raspberry Pi. International Research

Journal of Engineering and Technology, vol. 3, issue. 4, pp. 1168-

1172 (2016).

[56] Harshita A.GawadurajKadam, Dona Jain, Nirav Patel.: An IOT

based Dynamic Garbage Level Monitoring System using Raspberry

Pi. International Journal of Engineering Research and Application,

vol. 7, issue. 7, pp-30-34 (2017).

[57] V.Hemanthraj, N.Dhamodharan, V.Mohankumar.: IoT Based

College Automation with Smart Classroom Integration Using

Raspberry Pi. Vol. 5, issue. 6, pp. 2120-2125 (2017).

[58] Prof.Amruta Nikam, Madhuri Urgunde, Priyanka Shinde.: IoT

Based Automatic Water Recycling Using Raspberry Pi.

International Journal of Innovations & Advancement in Computer

Science. Vol. 7, issue. 3, pp. 386-388 (2018).

[59] Shaik Yusuf Bahi Saheb, Gharade Abdul Mueed, Haider

Choudhary, Ziauddin Ansari.: IoT Based Lecture Delivery System

Using Raspberry Pi. International Journal of Advanced Research in

Computer Engineering & Technology, vol. 6, issue. 3, pp. 245-247

(2017).

[60] Khaleel Mershad, Pilar Wakim.,; A Learning Management System

Enhanced with Internet of Things Application. Journal of Education

and Learning, vol. 7, no. 3, pp. 23-40 (2018).

[61] Gu Yichen, Li Lan.: Smart Black/Whiteboard, Final Report (2016).

[62] Kanvitha.P., Sirisha., M.Kalpana Chowdary.,: Timetable

Management System Using Raspberry Pi and RFID. International

Research Journal of Engineering and Technology, vol. 4, issue. 9,

pp. 99-102.

[63] Devakate Atul Balaso, Londhe Sarita Dhanaji, Patil Dipali Netaji.:

Automatic College Bell Using Raspberry Pi. International Journal

of Emerging Trends in Science and Technology, vol. 3, issue. 6, pp.

4086-4089 (2016).

[64] N.Indira.: Human Interaction Artificial Intelligence by Using

Raspberry Pi. International Journal of Advanced Engineering and

Research Development, vol. 5, issue. 3, pp. 410-417 (2018).

[65] Arhikeyan.V.K., Kirubhasudha.N., Kiruthika.S., Monisha.T.,

Dr.Sivasankari.B.: Raspberry Pi Based Intelligent Autonomous

Campus Mobility Services, International Journal of Scientific

Research in Computer Science, Engineering and Information

Technology, vol. 3, issue. 1, pp. 1457-1461 (2018).

[66] Kalyani.A., Premalatha.B., Ravi Kiran.: Real-Time Emotion

Recognition from Facial Images using Raspberry Pi. International

Journal of Advanced Technology and Innovative Research, vol. 10.

İssue. 1, pp. 0013-0016 (2018).

[67] Arthur Luehrmann.: Technological innovations in higher

education: Are they possible?.Journal of Computing in Higher

Education. Vol.1, Issue. 1, pp. 82-92 (1989).

[68] Janette R. Hill, Thomas C. Reeves, Heike Heidemeier.:

Ubiquitous Computing for Teaching, Learning and




Communicating: Trends, Issues & Recommendations. Copyright

2000.

[69] Bryan Alexander. Going Nomadic: Mobile learning in Higher

Educarion. EDUCAUSE Review (2004).

[70] 71.Kevin McReynolds.: Pervasive Computing in Higher Education:

A Smart Classroom Model. The technology Interface Journal/ Fall

(2008).

[71] Sang Hwa Lee, Junyeong Choi, and Jong-Il Park.: Interactive E-

Learning System Using Pattern Recognition and Augmented

Reality, IEEE Transactions on Consumer Electronics, Vol. 55,

No. 2, (2009).

[72] Catherine Marinagi.: Employing Ubiquitous Computing Devices

and Technologies in the Higher Education Classroom of the

Future. Vol. 73, pp. 487-494 (2013).

[73] Robin A.Walker.: Holograms as Teaching Agents. 9th

International Conference on Display Holography, IOP

Publishing, Journal of Physics: Conference Series (2013).

[74] Jasmine Norman.: Impact of Pevasive Computing in Education.

International Journal of Education and Learning, vol. 2, no. 2, pp.

39-48 (2013).

[75] Gopinath Shanmuga Sundaram, Bhanuprasad Patibandal, Harish

Santhanam, Sindura Gaddam, Vamsi Krishna Alla, Gautham Ravi

Prakash, Shiva Chaitanya Vıshwakarma Chandracha, Sindhu

Boppana and James M. Conrad, ―Bluetooth Communication using

a Touchscreen Interface with a Raspberry Pi‖, IEEE, 2013.

[76] Murat Ali, Jozef Hubertus Alfonsus Vlaskamp, Nof Nasser Eddin,

Ben Falconer and Colin Oram, ―Technical Development and

Socioeconomic Implications of the Raspberry Pi as an

educational tool in Developing Countries‖, 5th Computer Sicnec

and Electronic Engineering Conference (CEEC), 2013.

[77] Valeriu Manuel IONESCU, Florin SMARANDA, Adrain- Viorel

DIACONU, ―Control System For Video Advertising Based on

Raspberry Pi‖, RoEduNet Internationational Conference 12th

Edition: Networking in Education and Research, (2013).

[78] Folakemi Oluwagbemi, Sanjay Misra, Nicholas Omoregbe.:

Pervasive Computing in Classroom Environments and

Applications. International Conference on Education & eLearning

Innovations, (2014)

[79] Upadhye sudeep.: Use of 3D Hologram Technology in

Engineering Education, IOSR Journal of Mechanical and Civil

Engineering (IOSR-JMCE), pp. 62-67, (2015).

[80] Boris Pokric, Srdjan Krco, Dejan Drajic, M.Pokric,: Augmented

Reality renabled IoT services for environmental monitoring

utilising serious gaming concept, (2015).

[81] Umakant B.Gohatre, V.D.Chaudhari, ―Digital Advertising of Still

and Moving Images Using Raspberry Pi ‖ International Journal of

Engineering Research and Technology, Vol. 4, Issue. 2, (2015).

[82] Matthew Montebello.: Smart Ubiquitous Learning

Environments. International Journal of Education. Vol. 5,

no.3/4,pp. 17-24 (2017).

[83] Mirjana Maksimoviƈ.: IOT Concept Application in Educational

Sector using Collaboration. Teaching, Learning and Teacher

Education, vol. 1, No. 2, pp. 137-150, (2017).

[84] Dr. Jay. R. Porter, Dr.Josepgh A. Morgan, Dr.Micheal Johnson.,:

Building Automation and IoT as a Platform for Introducing STEM

Education in K-12. American Society for Engineering Education,

(2017).

[85] Luka Petroviƈ, Ivan Jezdoviƈ, Danijela Stojanoviƈ, Zorica

Bogdanoviƈ, Marijana Despotoviƈ-Zrakiƈ.: Development of an

educational game based on IoT. International Journal of

Electrical Engineering and Computing, vol. 1, no. 1, pp. 36- 45,

(2017).

[86] Stefan A.D. Popenici, Sharon Ken.: Exploring the impact of

artificial intelligence on teaching and learning in higher

education. Research and Practice in Technology Enhanced

Learning, (2017).

[87] Fernando Moreira, Maria João Ferreira, Abilio Cardoso.: Higher

Education Disruption Through IoT and Big Data: A Conceptual

Approach, Springer International Publishing, pp. 3009-405,

(2017).

[88] Toge Swatee Pralhad, Bhope Vishal, ―Smart Interactive

Advertising Board Using Raspberry Pi‖, International Journal

of Advance Research, Ideas And Innovations In Technology,

Vol. 3, Issue. 6, (2017)

[89] Rawia Bdiwi, Cyril de Runz, Sami Faiz, Arab Ali Cherlif,: Smart

Learning Environment: Teacher’s Role in assessing classroom

attention, Research in Learning Technology, Vol. 27, (2019).

[90] Ana-Maria SUDUC, Mihai Bizoi, Gabriel Gorghiu.,: A Survey on

IoT in Education. Revista Românească pentru Educaţie

Multidimensională, vol. 10, issue. 3, pp. 104-111, (2018).

[91] Dr.Shahbaz Pervez, Shafiq ur Rehman, Dr. Gasim Alandjani.:

Role of Internet of Things (IOT) in Higher Education. 4th

International Conference on Advances in Education and Social

Sciences, pp. 792-800 (2018)

[92] Everton Gomede, Fernando Henrique Gaffo, Gabriel Ulian

Briganó, Rodolfo Miranda de Barros, Leonardo de Souza

Mendes.: Applications of Computational Intelligence to

Imrpove Education in Smart Cities, MDPI,Sensors, (2018).

[93] Diego Lǒpez de Ipiña, Paulo R.S. Mendonça, Andy Hopper.:

TRIP: a Low-Cost Vision Based Location System for

Ubiquitous Computing.

[94] Ashmit Kolli.: Augmented Reality and Ubiquitous Computing

using HCI.

[95] Suvarna Kumar Gogula.,Sandhya Devi Gogula, Chanakya

Puranam.: Augmented Reality in Enhancing Qualitative

Education. International Journal of Computer Applications, vol.

132, no. 14, pp.41-45, (2015).

[96] Dharmateja.R., Dr.A.Ruhan Bevi.: Raspberry Pi Touchscreen

Tablet (Pi-Pad). International Journal of Recent and Innovation

Trends in Computing and Communication, vol. 3, issue. 2, pp.

600-605, (2015).

[97] Nikhil Paonikar, Samuel Kumar, Manoj Bramhe.,: Raspberry

Pi Augmentation: A cost effective solution to Google Glass.

International Research Journal of Engineering and Technology,

vol. 4, issue. 3, pp. 1439-1442, (2017).

[98] Sarantos Psycharis, Konstantinos Kalovrektis, Eva Sakellaridi,

Konstantinos Korres, and Dimitrios Mastorodimos, : Unfolding

the Curriculum: Physical Computing, Computational Thinking and

Computational Experiment in STEM’s Transdisciplinary

Approach, European Journal of Engineering Research and

Science Special Issue : CIE, 2017.

[99] Xunyu Pan, Joseph Shipway, Weijuan Xu.: Learning Enhancement

with Mobile Augmented Reality. International Symposium of

Electronic Imaging, Society for Image Science and Technology,

(2018).

[100] Iain Murray, Helen Armstrong.: A Computing Education Vision

For the Sight Impaired. ACE ’04 Proceedings of the Sixth

Australian Conference on Computing Education, vo. 30, pp. 201-

206, (2004).

[101] PuTjorn Pruet, Deravi Farzin, Chee Siang Ang, Naong Chaiwut.:

Exploring the Internet of Educational Things(IoET) in rural

unprivileged areas, IEEE (2015)

[102] 103.Prajakta Chavan, Gauri Bhatt, Neha Ture, Prof. K.K.Mathew.:

Real-Time Video Streaming using Holograms. International




Journal of Advanced Research, vol. 5, issue. 8, pp. 1006-1010,

(2017).

[103] Romy Ferzli, Ibrahim Khalife.: Mobile Cloud Computing

Educational Tool for Image/Video Processing Algorithms, IEEE

(2011)

[104] V.Ajantha Devi., Dr.S.Santhosh baboo.: Embedded Optical

Character Recognition On Tamil Text Image Using Raspberry

Pi, International Journal of Computer Science Trends and

Technology (IJCST), vol. 2, issue. 4, pp. 127- 131, (2014).

[105] Aryuanto Soetedjo, Ali Mahmudi, M. Ibrahim Ashari, Yusuf

Ismail Nakhoda, ―Raspberry Pi Based Laser Spot Detection‖,

IEEE International Conference on Electrical Engineering

Computer Science, 2014.

[106] Geraldine Shirley.N., Jayanthy.S.: Virtual Control hand Gesture

Recognition System using Raspberry Pi, ARPN Journal of

Engineering and Applied Sciences, vol. 10, no. 7, pp. 2989-2993,

(2015)

[107] Shyam Narayan Patel, V.Prakash, ―Autonomous Camera based

Eye Controlled Wheelchair system using Raspberry- Pi‖, 2nd

International Conference on Innovations in Information Embedded

and Communication Systems, (2015).

[108] Varsha E. Dahiphale, Sathyanarayana Ramachandra Rao, A

Review Paper on Portable Driver Monitoring System for Real

Time Fatigue‖, IEEE Computer Society, 2015

[109] Qifan Dong, Yang Yang, Wang Hongjun, Xu Jian-Hua, ―Fall

Alarm and Inactivity Detection System Design and

Implementation on Raspberry Pi‖, ISBN 978-89-968650-5-6,

ICACT, (2015).

[110] Hassna BENSAG, Mohamed YOUSSFI, Omar BOUATTANE,

―Embedded Agent for medical image segmentation‖, 27th

International Conference on Microelectronics (ICM) ,2015.

[111] Marko Viitanen, Ari Koivula, Jarno Vanne, Timo D.

Hämäläinen, ―Kvazaar HEVC Still Image Coding on Raspberry

Pi 2 for Low-Cost Remote Surveillance‖, IEEE ,(2015).

[112] P.V.Vinod Kumar, K.Dhanunjaya, ―Kindling and Perception of

Qr-Images Using Raspberry-PI‖, International Journal of

Engineering and Computer Science, vol. 4, issue. 7, pp. 13082-

13085, (2015).

[113] Enis Bilgin, Dr. Stefan Robila, ―Road Sign Recognition System

on Raspberry Pi‖, IEEE Long Island Systems, Applications and

Technology Conference LISAT, (2016).

[114] Jyoti Yadav, Mohammaed Firash Khan, Muhammed Shahan

K.K., Sreedevi.P., Sumayya K., Manju V.M.: Raspberry Pi Based

Gesture Photography. International Journal of Advanced

Research in Computer and Communication Engineering+, vol. 5,

issue. 3, pp. 412-416 ,(2016).

[115] Shaik Riyaz Hussain, K. Rama Naidu, Chintala R.S.Lokesh,

Patchava Vamsikrishna, Goli Rohan, ―2D-Game Development

Using Raspberry Pi‖, International Conference On Information

Communication And Embedded System ICICES, (2016).

[116] Nestor Lobo, ―Intellie-Mirror:An Augmented Reality based IoT

System for Clothing and Accessory Display‖, 2016 International

Conference on Internet of Things and Applications (IOTA), (2016).

[117] Dhanujalakshmi.R., Divya.B., Divya.C., Robersingh.A.: Image

Processing Based Fire Detection System using Raspberry Pi

System, SSRG International Journal of Computer Science and

Engineering, vol. 4, issue. 4, pp. 18- 20, (2017).

[118] Aditi.S,Annapoorani.S.P.,Kanchana.P.:Book ReaderUsing

Raspberry Pi for Vısually Impaired. International Research

Journal of Engineering and Technology, vol. 5, issue. 1, pp. 555-

557, (2018).

[119] Kiran Kumar.R, Mekala.S.: Face Recognition Attendance System

Using Raspberry Pi. International Journal of Pure and Applied

Mathematics, vol. 118, no. 20, pp. 3061-3065, (2018).

[120] Lubasi kakwete Musambo, Jackson Phiri.: Student Facial

Authentication Model based on OpenCV’s Object Detection

Method and QR code for Zambian Higher Institutions of

Learning. International Journal of Advanced Computer Science

and Application, vol. 9, no. 5, pp. 88-94, (2018).

[121] Keerthi Premkumar, K Gerard Joe Nigel, ―Smart Phone Based

Robotic Arm Control Using Raspberry Pi, Android and Wi-Fi‖,

2nd International Conference on Innovations in Information

Embedded and Communication Systems, (2015).

[122] Morgane Chevalier, Fanny Riedo, Francesco Mondada.: How do

teachers perceive educational robots in formal education? A study

based on the Thymio robot (2016)

[123] Pedro Plaza, Elio Sancristobal, German Fernandez, Manuel

Castro,Clara Pérez, Collaborative Robotic Educational Tool

based on Programmable Logic and Arduino, IEEE (2016)

[124] Roland Szabó, Aurel Gontean, ―Industrial Robotic Automation

with Raspberry PI using Image Processing‖, ISBN 978-80-

261-0602-9, © University of West Bohemia, (2016).

[125] Leland Miller, Kevin Abas, Katia Obraczka.: SCmesh: Solar-

Powered Wireless Smart Camera Mesh Network. IEEE 24th

International Conference on Computer Communication and

Networks, (2015).

[126] Nikolaos Ioannou, George S. Ioannidis, George D.

Papadopoulos, Athanasios E.Tapeinos, ―A novel Educational

Platform, based on Raspberry Pi‖, Optimised to assist the

teaching and learning of young students, International

Conference on Interactive Collaborative Learning, IEEE ,(2014).

[127] 128.P.Turton,T.F.Turton, ―PiBrain – A Cost Effective

Supercomputer for Educational Use‖, 5th Brunei Internatinoal

Conference on Engineering and Technology BICET (2014) pp-

1-4.

[128] Rebecca F. Bruce, J.Dean Brock, Susan L.Reiser, ―Make Space

for the Pi‖, Proceedings of the IEEE SoutheaseCon, (2015).

[129] Diyana Kyuchukova, Georgi Hristov, Plamen Zahariev and

Svilen Borisov, ―A study on the possibility to use Raspberry Pi as

a console server for remote access to devices in virtual learning

environments‖, European Union (2015).

[130] .J. R. Byrne, L. Fisher, B. Tangney, ―Computer Science Teacher

reactions towards Raspberry Pi Continuing Professional

Development (CPD) workshops using the Bridge21 Model‖, 10th

International Conference on Computer Science & Education

(ICCSE 2015).

[131] Peter Jamieson, Jeff Herdtner, ―More Missing the Boat -

Arduino, Raspberry Pi, and Small Prototyping Boards and

Engineering Education Needs Them‖, IEEE (2015).

[132] Marina Rocha Daros, João Paulo Cardoso de Lima, Willian

Rochadel , Juarez Bento Silva, José Schardosim Simão, ―Remote

Experimentation in Basic Education using an Architecture with

Raspberry Pi‖ IEEE (2015).

[133] Hélia Guerra, Alberto Cardoso, Vitor Sousa, Joaquim Leitão,

Vitor Graveto, Luís Mendes Gomes ―Demonstration of

Programming in Python using a remote lab with Raspberry Pi‖,

IEEE (2015)

[134] Siddharth Arun, C. Aakash, V.Ajay, ―Design and

Implementation: Remote Control for Projectors Using Raspberry

Pi‖, Middle-East Journal of Scientific Research, Vol. 24, No. 11,

ISSN: 1990-9233, (2016).

[135] . Manaswi R.Ganbavale, Shubhangi C. Deshmukh, ―Raspberry Pi

Based Intelligent Projector‖, International Journal of Innovative




Research in Computer and Communication Engineering, vol. 4,

issue. 8, pp. 14704- 14709.

[136] Kazuaki Yoshihara* and Kenzi Watanabe, Nobukazu Iguchi,

―New Educational Equipments for Networking Study by

Physical Visualizations and Physical Direct Manipulations‖, 30th

International Conference on Advanced Information Networking

and Applications, IEEE Computer Society, (2016).

[137] Ciira wa MAINA, Asaph MUHIA, James OPONDO, ―A Low

Cost Laboratory for Enhanced Electrical Engineering

Education‖, IST-Africa 2016 Conference ProceedingsPaul

Cunningham and Miriam Cunningham (Eds) IIMC International

Information Management Corporation, (2016).

[138] Suchitra, Suja P., Shikha Tripathi, ―Real-Time Emotion

Recognition from Facial Images using Raspberry Pi II‖ 2016 3rd

International Conference on Signal Processing and Integrated

Networks (SPIN) (2016).

[139] Vaibhav kanna, Yash Vardhan, Dhruv Nair, Preeti Panu,

―Design and Development of a Smart Mirror Using Raspberry

Pi‖, International Journal of Electrical and Data

Communication,ISSN2320-2084.

[140] Renuka P.Kondekar, A.O. Mulani, ―Raspberry Pi based voice

operated Robot‖, International Journal of Recent Engineering

Research and Development (IJRERD),vol. 02, Issue. 12, pp. 69-76,

(2017).

[141] Isaiah Brand, Josh Roy, Aaron Roy, John Oberlin, Stefanie

Tellex, ―‖PiDrone: An Autonomous Educational Drone using

Raspberry Pi and Python‖, RSJ International Conference on

Intelligent Robots and Systems, 2018.

[142] Micheal S.Feurstein, ―Towards an Integration of 360- degree

Video in Higher Education‖, proceedings of DeLFI Worksops

2018.

[143] Salman Mahmood, Sellapan Palaniappan, Raza Hasan, Kamal

Uddin Sarker, Ali Abass, Puttasamy Malali Rajegowda, ―

Raspberry PI and role of IoT in Education‖, IEEE (2019).

[144] Anand Nayyar, Vikram Puri, ―Raspberry Pi- A Small, Powerful,

Cost Effective and Efficient Form Factor Computer: A Review,

International Journal of Advanced Research in Computer Science

and Software Engineering, Vol. 5, Issue 12, (2015).

[145] Rabia M.Yilmaz.: Augmented Reality Trends in Education

between 2016 and 2017 Years. State of the Art Virtual Reality

and Augmented Reality Knowhow, (2018).

[146] Kim, S., Song, S.M., & Yoon, Y.I.: Smart learning services

based on smart cloud computing- Sensors, vol. 11, no. 8, pp.

7835-7850, (2011).

[147] Noufal Ibrahim KV.: Creating Physics Aware Games using

PyGame and PyODE. Proceedings of PYCon Asia-Pacific, (2010).

[148] Prof. Swati Vitkar.: Cloud Based Model for E-Learning in

Higher Education. IJAIR, ISSN: 2278-7844, (2012).

[149] Gwo-Jen Hwang, Chin-ChungTsai, Hui—Chun Chu, Kinshuk,

Chieh-Yuan Chen. A Context aware ubiquitous learning

approach to conducting scientificninquiry activities in a science

park, Australasian Journal of Educational Technology, vol. 28,

no. 5, pp. 931-947, (2012).

[150] Majid Bayani Abbasy, Enrique Vlíchez Quesada.: Predictable

Influence of IoT (Internet of Things) in the Higher Education.

International Journal of Information and Education Technology.

Vol. 7, no. 12, pp. 914-919, (2017).

[151] Sejal V. Gawande, Prashant R. Deshmukh, ―Raspberry Pi

Technology‖, International Journal of Advanced Research in

Computer Science and Software Engineering, Vol 5, Issue 4,

(2015).

[152] Ching-Hsang, Chang and Wei-Lin Wang.,: RFID System, Tsang

Hai Book, Taiwan, (2008).

[153] M.Karthikeyan, M.Kudalingam, P.Natrajan, K.Palaniappan,

A.Madhan Prabhu, ―Object Tracing Robot by Using Raspberry PI

with open Computer Vision (CV), International Journal of Trend

in Research and Development, Vol. 3, Issue. 3, ISSN: 2394-

9333, (2016).

[154] Dürr, Y.Pauchard, D.Browarnik, R.Axthelm, M.Loeser, ―Deep

Learning on a Raspberry Pi for Real time Face Recognition

(2015)

[155] Delia Velasco-Montero, Jorge Fernández-Berni, Ricardo

Carmona-Galan, Angel Rodríguez-Vázquez,‖Performance

Analysis of Real-Time DNN Inferencfe on Raspberry Pi‖,2018.

[156] Ajay Kushwaha, Ankita Mishra, Komal Kamble, Rutuja

Janbhare, ―Theft Detection using Machine Learning‖, IOSR

Journal of Engineering, Vol. 8, pp-67-71, (2018)

[157] Mahmut Taha Yazici, Shadi Basurra, Mohamed Medhat Gaber,

―Edge Machine Learning: Enabling Smart Internet of things

Applications‖, Big Data and Cognitive Computing, 2(26),

(2018).

[158] N.Indira, H.Sanofar Nisha, P.Vidhyabanu, M.Suganya,

―Human Interaction Artificial Intelligence By Using Raspberry

Pi‖, International Journal of Advance Engineering and Research

Development, Vol. 5, Issue. 3, 2018.

[159] Ashwani Kumar, Anlush Chourasia, ―Blind Navigation System

Using Artificial Intelligence‖, International Research Journal of

Engineering and Technology, Vol. 5, Issue. 3, 2018.

[160] Marcelo Worsley, ―Multimodal Learning Analytics’ Past, Present

and Potential Futures‖, Companion Proceedings 8th

International Conference on Learning Analytics and

Knowledge, 2018.

[161] Nicholas Constant, Debanjan Borthakur, Mohammedreza Abtahi,

Harishchandra Dubey, Kunal Mankodiya, ―Fog – Assisted wIoT: A

Smart Fog Gateway for End-to-End Analytics in Wearable

Internet of Things‖, 23rd IEEE Symposium on High Performance

Computer Architecture HPCA 2017.

[162] Katalin Ferencz, József Domokos, ―IoT Sensor Data Acquistion

and Storage System Using Raspberry Pi and Apache

Cassandra‖,2018.

[163] Wajdi Hajji, Fung Po Tso, ―Understanding the Performance of

Low Power Raspberry Pi Cloud for Big Data‖, MDPI

Electronics Journal, 5(29), 2016.

[164] C.Balasubramaniyan, D.Manivannan, ―IoT Enabled Air Quality

Monitoring System (AQMS) using Raspberry Pi‖, Indian

Journal of Science and Technology, Vol. 9(39), 2016.

[165] R.K.Barik, R.Priyadharshini, H.Dubey, V.Kumar and

K.Mankodiya, ―FogLearn: Leveraging Fog-based Machine

Learning for Smart System Big Data Analytics‖, International

Journal of Fog Computing, Vol. 1, Issue. 1, 2018.

[166] Micheal Derntl, Nikou Günnemann, Ralf Klamma, ―A Dynamic

Topic Model of Learning Analytics Research‖, 2013.

[167] Badradiin Alturki, Stephan Reiff-Margainee, Charith Perera, ―A

Hybrid Approach for Data Analytics for Internet of Things‖,

ACM, 2017.

ijream-applications of iot technology and computer visionijream.org/papers/ijreamv05i0452005.pdf ·...

Documents