sensingkit: a multi-platform mobile sensing framework · poster: sensingkit: a multi-platform...
TRANSCRIPT
Cognitive Science Research Grouphttp://cogsci.eecs.qmul.ac.uk
SensingKit: A Multi-Platform Mobile Sensing FrameworkKleomenis Katevas, Hamed Haddadi, Laurissa Tokarchuk
http://www.sensingkit.org
IntroductionMotivated by the lack of a universal, multi-platform library, we present SensingKit, an efficient, open-source, client-server system
that supports both iOS and Android mobile devices. SensingKit
is capable of continuous sensing the device’s motion,
orientation, location and proximity to other smartphones
and transmit the data to a server for further analysis over any Internet connection. We believe that this platform will be beneficial to all researchers and developers who need to perform mobile sensing in their applications and experiments.
ReferencesKleomenis Katevas, Hamed Haddadi, Laurissa Tokarchuk, and Richard G. Clegg. 2015. Walking in Sync: Two is Company, Three's a Crowd. In Proceedings of the 2nd workshop on Workshop on Physical Analytics (WPA '15). ACM, New York, NY, USA, 25-29.
Kleomenis Katevas, Hamed Haddadi, and Laurissa Tokarchuk. 2014. Poster: SensingKit: a multi-platform mobile sensing framework for large-scale experiments. In Proceedings of the 20th annual international conference on Mobile computing and networking (MobiCom '14). ACM, New York, NY, USA, 375-378.
Narasimhan, K. P., & White, G. (2014). Agent Clusters: The Usual vs. The Unusual. In Advances in Practical Applications of Heterogeneous Multi-Agent Systems. The PAAMS Collection (pp. 244-255). Springer International Publishing.
AcknowledgementsThis work is supported by funding from the UK Defence Science and Technology Laboratory.
Platform Characteristics• Works in Android and iOS mobile systems.
• Supports most of the available smartphone sensors: Accelerometer, Gyroscope, Magnetometer, Device Motion, Motion Activity, Pedometer, Altimeter, Battery, Location, Microphone, Ambient Temperature, Light.
• Power efficient proximity sensing using iBeacon™ /
Eddystone™ technology over Bluetooth Smart (BLE).
• Easily extensible using a modular design.
• Automated time sync and data processing on the server.
• Available in open-source under the GNU LGPL v3.0.
Future Work
Multi-sensory modelling of different qualities of social interactions.(Narasimhan, 2014)
CrowdSense for iOS / AndroidA free continuous sensing tool, based on SensingKit open
source library. It provides an easy way for researchers to capture sensor data using any iOS or Android device.
Walking in Sync
0 50 100 150 200
0.00.4
0.8
(a) Scenario 1 (2 People)
Window of 1 sec with 50% overlapping
Corre
lation P1 and P2
0 50 100 150 200
0.00.4
0.8
(b) Scenario 2 (3 People)
Window of 1 sec with 50% overlapping
Corre
lation P1 and P2
P2 and P3P1 and P3
Pearson Correlation applied to windows of 1 sec (with 50% overlap)
We used smartphones to capture the motion of two groups of people during a 12 minute walk in a park using high frequency accelerometers.
SensingKit Server
Web
Ser
vice
s
Com
mun
icat
ion
Mod
ule
Plug-inSystemModel
Manager
SensorModules Data
Data DataExtraction
Internet
SensingKit System Architecture
Platform Architecture
Power Consumption
Power consumption of SensingKit running on an iPhone 5S smartphone.
00 03 06 09 12 15 18 21 24 27 30 33 36 39 42 45 48 51 54 57Time (hours)
0
10
20
30
40
50
60
70
80
90
100
Pow
er (%
)
iPhone 5SIdleAccelerometer (100Hz)Gyroscope (100Hz)Mangetometer (100Hz)Device Motion (100Hz)Location (Best Accuracy)iBeacon Broadcast (1Hz)iBeacon Scan (1Hz)iBeacon Scan + Broadcast (1Hz)Microphone (44100.0 Hz)