Spark based Framework for Supervised Classification of Hyperspectral Images

The advancement of remote sensing sensors acquired large amount of image data easily. Primary aspects of big data, such as volume, velocity, and variety, are represented in the acquired images. Furthermore, standard data processing approaches have different limits when dealing with such large amounts of data. As a result, good machine learning-based algorithms are required to process the data with higher accuracy and lower computational efficiency. Therefore, we propose ANOVA F-test based spectral feature selection method with a distributed implementation of this machine learning algorithm on Spark. Experimental results are obtained using the bench mark datasets acquired using AVIRIS and ROSIS sensors. The performance of Spark MLlib based supervised machine learning techniques are evaluated using the criteria viz., accuracy, specificity, sensitivity, F1-score and execution time. Added to that, we compared the execution time between distributed processing and processing with single processor. The results reveal that the proposed strategy significantly cuts down on analytical time while maintaining classification accuracy.

@article{Aswini2022,
  title     = {Spark based Framework for Supervised Classification of Hyperspectral Images},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {13},
  number    = {2},
  year      = {2022},
  publisher = {The Science and Information Organization},
  author    = {N. Aswini and R. Ragupathy},
  doi       = {10.14569/IJACSA.2022.0130253},
  url       = {https://doi.org/10.14569/IJACSA.2022.0130253}
}