K
K. P. Soman
Researcher at Amrita Vishwa Vidyapeetham
Publications - 504
Citations - 8779
K. P. Soman is an academic researcher from Amrita Vishwa Vidyapeetham. The author has contributed to research in topics: Deep learning & Support vector machine. The author has an hindex of 32, co-authored 489 publications receiving 5773 citations. Previous affiliations of K. P. Soman include Indian Institute of Technology Kharagpur & Indian Institutes of Technology.
Papers
More filters
Journal ArticleDOI
A Low Cost Implementation of Multi-label Classification Algorithm Using Mathematica on Raspberry Pi
TL;DR: With the facilities available in Mathematica software for Raspberry Pi, the line of code required for implementing data mining algorithms can be reduced sufficiently and Random Kitchen Sink algorithm improves the accuracy of Multi-label classification and brings improvement in terms of memory usage for large dataset.
Proceedings ArticleDOI
Dimensionality Reduction of Hyperspectral Images for Classification using Randomized Independent Component Analysis
TL;DR: The proposed nonlinear component analysis for the dimensionality reduction of HSI based on Random Fourier feature maps outperforms the conventional and kernel methods, in terms of classification accuracy.
Proceedings ArticleDOI
A Deep Learning Approach for Part-of-Speech Tagging in Nepali Language
TL;DR: A deep learning based POS tagger for Nepali text is proposed which is built using Recurrent Neural Network, Long Short-Term Memory Networks, Gated Recurrent Unit and their bidirectional variants and shows significant improvement and outperforms the state-of-art POS taggers with more than 99% accuracy.
Journal Article
Spatial Preprocessing for Improved Sparsity based Hyperspectral Image Classification
TL;DR: It is presented that hyperspectral image classification based on sparse representation can be significantly improved by using an image enhancement step and this step lead to 97.53% of classification accuracy which is high when compared with the classification accuracy obtained without applying the spatial preprocessing technique.
Book ChapterDOI
Deep Belief Network Based Part-of-Speech Tagger for Telugu Language
TL;DR: The main aim of this research is to do sequential tagging for Indian languages based on the unsupervised features and distributional information of a word with its neighboring words.