D
Dibyendu Bikash Seal
Researcher at University of Engineering & Management
Publications - 15
Citations - 74
Dibyendu Bikash Seal is an academic researcher from University of Engineering & Management. The author has contributed to research in topics: Computer science & Biology. The author has an hindex of 4, co-authored 8 publications receiving 40 citations. Previous affiliations of Dibyendu Bikash Seal include University of Calcutta & Information Technology University.
Papers
More filters
Journal ArticleDOI
Estimating gene expression from DNA methylation and copy number variation: A deep learning regression model for multi-omics integration.
TL;DR: A deep learning-based predictive model is developed using Deep Denoising Auto-encoder and Multi-layer Perceptron that can quantitatively capture how genetic and epigenetic alterations correlate with directionality of gene expression for liver hepatocellular carcinoma (LIHC).
Journal ArticleDOI
A novel gene ranking method using Wilcoxon rank sum test and genetic algorithm
TL;DR: A novel gene ranking method based on Wilcoxon Rank Sum Test and genetic algorithm is proposed that can reach up to 100% classification accuracy with very few dominant genes, which indirectly validates the biological and statistical significance of the proposed method.
Proceedings ArticleDOI
Human Activity Recognition using Deep Neural Network
TL;DR: This paper has attempted to apply machine learning and deep learning techniques on a publicly available dataset and an accuracy of 97.32% is achieved, which indicates suitability ofDeep learning techniques over traditional machine learning techniques for the task of human activity recognition using mobile sensor data.
Proceedings ArticleDOI
Gene — Gene Interaction: A clustering, correlation & entropy based approach
Dibyendu Bikash Seal,Sujay Saha,Mayukh Chatterjee,Prokriti Mukherjee,Aradhita Mukherjee,Bipasha Mukhopadhyay,Sohini Mukherjee +6 more
TL;DR: This paper has used two metrics, like correlation & entropy to find the level of interaction between the genes applied on Gene Interaction networks, and applied this algorithm on three benchmark cancer datasets Colorectal, Leukaemia and CML.