dimensionality reduction on hyperspectral data for solids analysis
DESCRIPTION
Dimensionality Reduction on Hyperspectral Data for Solids Analysis. Annalisse Booth Utah State University Electrical and Computer Engineering Department Research Experience for Undergraduates 2009. Hyperspectral Imaging: An Overview. Records information across electromagnetic spectrum - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Dimensionality Reduction on Hyperspectral Data for Solids Analysis](https://reader036.vdocument.in/reader036/viewer/2022062812/56816280550346895dd2ece1/html5/thumbnails/1.jpg)
Dimensionality Reduction on Hyperspectral Data for
Solids Analysis
Annalisse BoothUtah State University
Electrical and Computer Engineering DepartmentResearch Experience for Undergraduates 2009
![Page 2: Dimensionality Reduction on Hyperspectral Data for Solids Analysis](https://reader036.vdocument.in/reader036/viewer/2022062812/56816280550346895dd2ece1/html5/thumbnails/2.jpg)
Hyperspectral Imaging: An Overview
Source: http://www.yellowstoneresearch.org
• Records information across electromagnetic spectrum
• Spectral band correlates to certain range of wavelength
• Bands combined to form cube
• Hundreds to thousands of bands per cube
• 258 bands in current data
![Page 3: Dimensionality Reduction on Hyperspectral Data for Solids Analysis](https://reader036.vdocument.in/reader036/viewer/2022062812/56816280550346895dd2ece1/html5/thumbnails/3.jpg)
January 11, 2008 17:41:25, wavelength 46
Solids Hyperspectral Data
• 3 months data
• Camera on tripod, but shaken
• Cleaned up by Mckay
• Turned into video, RGB approximations
• Wrote other applicable codes
![Page 4: Dimensionality Reduction on Hyperspectral Data for Solids Analysis](https://reader036.vdocument.in/reader036/viewer/2022062812/56816280550346895dd2ece1/html5/thumbnails/4.jpg)
Gathering Tools for Analysis
An example of a Locally Linear Embedding (LLE)
• Multidimensional Scaling (MDS)• Principle Component Analysis (PCA)• Locally Linear Embedding (LLE)• Isomap (weighted geodesic distances)• Maximum Variance Unfolding (MVU)
![Page 5: Dimensionality Reduction on Hyperspectral Data for Solids Analysis](https://reader036.vdocument.in/reader036/viewer/2022062812/56816280550346895dd2ece1/html5/thumbnails/5.jpg)
Comparing Techniques
Source: Boundary Constrained Manifold Unfolding. Bo, Hongbin, Wenan. 2008.
![Page 6: Dimensionality Reduction on Hyperspectral Data for Solids Analysis](https://reader036.vdocument.in/reader036/viewer/2022062812/56816280550346895dd2ece1/html5/thumbnails/6.jpg)
Comparing Techniques
Source: Boundary Constrained Manifold Unfolding. Bo, Hongbin, Wenan. 2008.
![Page 7: Dimensionality Reduction on Hyperspectral Data for Solids Analysis](https://reader036.vdocument.in/reader036/viewer/2022062812/56816280550346895dd2ece1/html5/thumbnails/7.jpg)
Comparing Techniques
Source: Boundary Constrained Manifold Unfolding. Bo, Hongbin, Wenan. 2008.
![Page 8: Dimensionality Reduction on Hyperspectral Data for Solids Analysis](https://reader036.vdocument.in/reader036/viewer/2022062812/56816280550346895dd2ece1/html5/thumbnails/8.jpg)
Work Still Uncompleted
• Write program to choose pixels from each substance through time
• Compare pixels of each substance to self and other substances
• Analysis in Isomap for preliminary results
• Write code for Riemmanian Manifold Learning (RML)
• Execute code on data
• Write code for Boundary Constrained Manifold Unfolding
• Execute new code, compare