Entropy based determination of optimal principal components of Airborne Prism Experiment (APEX) imaging spectrometer data for improved land cover classification

Other literature type English OPEN
Kallepalli, A. ; Kumar, A. ; Khoshelham, K. (2014)

Hyperspectral data finds applications in the domain of remote sensing. However, with the increase in amounts of information and advantages associated, come the "curse" of dimensionality and additional computational load. The question most often remains as to which subset of the data best represents the information in the imagery. The present work is an attempt to establish entropy, a statistical measure for quantifying uncertainty, as a formidable measure for determining the optimal number of principal components (PCs) for improved identification of land cover classes. Feature extraction from the Airborne Prism EXperiment (APEX) data was achieved utilizing Principal Component Analysis (PCA). However, determination of optimal number of PCs is vital as addition of computational load to the classification algorithm with no significant improvement in accuracy can be avoided. Considering the soft classification approach applied in this work, entropy results are to be analyzed. Comparison of these entropy measures with traditional accuracy assessment of the corresponding „hardened‟ outputs showed results in the affirmative of the objective. The present work concentrates on entropy being utilized for optimal feature extraction for pre-processing before further analysis, rather than the analysis of accuracy obtained from principal component analysis and possibilistic <i>c</i>-means classification. Results show that 7 PCs of the APEX dataset would be the optimal choice, as they show lower entropy and higher accuracy, along with better identification compared to other combinations while utilizing the APEX dataset.
  • References (25)
    25 references, page 1 of 3

    Hughes, G. 1968. “On the Mean Accuracy of Statistical Pattern Recognizers.” IEEE Transactions on Information Theory 14 (1): 55-63.

    Itten, Klaus I., Francesco Dell‟Endice, Andreas Hueni, Mathias Kneubühler, Daniel Schläpfer, Daniel Odermatt, Felix Seidel, et al. 2008. “APEX - the Hyperspectral ESA Airborne Prism Experiment.” Sensors 8 (10): 6235-59. doi:10.3390/s8106235.

    Jain, Anil, and Douglas Zongker. 1997. “Feature Selection: Evaluation, Application, and Small Sample Performance.” IEEE Transactions on Pattern Analysis and Machine Intelligence 19 (2): 153-58.

    Janecek, Andreas GK, and Wilfried N. Gansterer. 2008. “A Comparison of Classiffication Accuracy Achieved with Wrappers, Filters and PCA.” In Workshop on New Challenges for Feature Selection in Data Mining and Knowledge Discovery.

    http://www.ecmlpkdd2008.org/sites/ecmlpkdd2008.org/files/pdf /workshops/fsdm/7.pdf.

    Jehle, Michael, Andreas Hueni, Alexander Damm, Petra D‟Odorico, Jörg Weyermann, M. Kneubiihler, D. Schlapfer, Michael E. Schaepman, and Koen Meuleman. 2010. “APEXCurrent Status, Performance and Validation Concept.” In Sensors, 533-37.

    http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5690122.

    Jolliffe, I. T. 2002. Principal Component Analysis. New York: Springer. http://site.ebrary.com/id/10047693.

    Krishnapuram, Raghuram, and James M. Keller. 1996. “The Possibilistic c-Means Algorithm: Insights and Recommendations.” IEEE Transactions on Fuzzy Systems 4 (3): 385-93.

    Krishnapuram, R., and J.M. Keller. 1993. “A Possibilistic Approach to Clustering.” IEEE Transactions on Fuzzy Systems 1 (2): 98-110. doi:10.1109/91.227387.

  • Metrics
    No metrics available
Share - Bookmark