S
Sushovan Chaudhury
Publications - 17
Citations - 103
Sushovan Chaudhury is an academic researcher. The author has contributed to research in topics: Computer science & Pattern recognition (psychology). The author has an hindex of 5, co-authored 17 publications receiving 103 citations.
Papers
More filters
Journal ArticleDOI
An efficient way of text-based emotion analysis from social media using LRA-DNN
Nilesh Shelke,Sushovan Chaudhury,Sudakshina Chakrabarti,Sunil L. Bangare,G. Yogapriya,Pratibha Pandey +5 more
TL;DR: In this article , a Leaky Relu activated Deep Neural Network (LRA-DNN) was proposed for emotion extraction from text, which comes under four categories, such as pre-processing, feature extraction, ranking and classification.
Journal ArticleDOI
Effective Image Processing and Segmentation-Based Machine Learning Techniques for Diagnosis of Breast Cancer
Sushovan Chaudhury,Alla Naveen Krishna,Suneet K. Gupta,K. Sakthidasan Sankaran,Samiullah Khan,Kartik Sau,Abhishek Raghuvanshi,F. Sammy +7 more
TL;DR: A breast cancer image processing and machine learning framework that was developed and an improvement on the original histogram equalization technique is discussed, which aids in the removal of noise from photographs while simultaneously improving picture quality.
Journal ArticleDOI
Classification and Detection of Mesothelioma Cancer Using Feature Selection-Enabled Machine Learning Technique
M. Shobana,V. R. Balasraswathi,R Radhika,Ahmed Kareem Oleiwi,Sushovan Chaudhury,Ajay S. Ladkat,Mohd Naved,Abdul Wahab Rahmani +7 more
TL;DR: A classification and detection method for mesothelioma cancer is proposed using the CFS correlation-based feature selection approach, and the choice of features has a substantial influence on the accuracy of the categorization.
Journal ArticleDOI
A BERT encoding with Recurrent Neural Network and Long-Short Term Memory for breast cancer image classification
Sushovan Chaudhury,Kartik Sau +1 more
TL;DR: In this paper , the authors explored two modalities of breast images, ultrasound, and histology, for their classification into cancerous and non-cancerous categories using BERT pre-training of Image Transformers (BEiT) as a feature encoding technique.
Journal ArticleDOI
A Lightweight Hybrid Dilated Ghost Model-Based Approach for the Prognosis of Breast Cancer
Edwin Ramirez-Asis,Romel Percy Melgarejo Bolivar,Leonid Alemán Gonzales,Sushovan Chaudhury,Ramgopal Kashyap,Walaa F. Alsanie,G. Viju +6 more
TL;DR: A novel malignant detection and family categorisation model based on the improved stochastic channel attention of convolutional neural networks (CNNs) and DenseNet models is presented, which can detect and classify malignancy.