Sainik Kumar Mahata

Scopus Publications

Dynamics of Character Embeddings in Indian Mythology: A Physics-Informed Neural Networks Approach
Apurba Paul, Anish Goswami, Sainik Kumar Mahata, Dipankar Das
Fire 2025 Proceedings of the 17th Annual Meeting of the Forum for Information Retrieval Evaluation, 2026
Transformer-based language models like BERT have transformed NLP through their deep contextualized embeddings. However, the layer-wise evolution of these embeddings remains underexplored, especially in narrative rich domains like Indian mythology, where prominent personalities or characters undergo semantic progression over time. In this paper, we present a continuous-time framework to model the dynamics of character embeddings from the Indian epic Mahabharata. We treat BERT’s embedding transitions as trajectories in a latent dynamical system governed by ordinary differential equations, and propose a Physics-Informed Neural Network (PINN) that incorporates narrative metadata to regularize this evolution. Experiments on six major characters, each playing a pivotal role in the narrative, reveal that contextual embeddings evolve smoothly and predictably across layers. Our PINN model aligns closely with true embeddings while maintaining interpretability through constraints like smoothness, norm conservation, and narrative consistency. This framework bridges neural model interpretability with cultural narrative analysis, opening new directions for temporally-aware NLP and domain-specific embedding modeling.
A Cascaded Speech-to-Speech Translation System for Bengali to English
Aveepsa Sarkar, Anoushka Sen, Sainik Kumar Mahata
Lecture Notes in Networks and Systems, 2026
Sentiment Analysis Using Machine Learning: A Comprehensive Study
Anwesha Das, Abhijeet Kumar Singh, Sainik Kumar Mahata
2026 9th International Conference on Electronics Materials Engineering and Nano Technology Iementech 2026, 2026
In today's digital landscape, understanding consumer emotions is vital for businesses aiming to improve their products, services, and marketing strategies. Sentiment analysis, also known as Opinion Mining, is a powerful tool that enables companies to analyze customer opinions and emotions through text, social media, reviews, and surveys. This data-driven approach provides valuable insights into consumer preferences and behaviors, allowing brands to tailor their strategies effectively. This article explores the importance of sentiment analysis in market research, its methodologies, applications, and how businesses can leverage it to enhance customer engagement and brand perception. In this increasingly digitalized world, e-commerce is gaining ground by putting goods at the customers' fingertips so they don't even need to leave their homes. The relevance of a review is increasing because more and more individuals these days rely on online products. To make an informed decision, a customer must go through thousands of product reviews. But sifting through hundreds of reviews would be considerably simpler in today's thriving machine learning world if a model was used to polarize those evaluations and learn from them. Using a large-scale Amazon dataset, it polarized, it using supervised learning technique and obtained good accuracy.
Dense Semantic Compression: A Low-Dimensional Siamese Architecture for Efficient Paraphrase Detection
Sagnik Raha, Adarsh Kumar, Sainik Kumar Mahata
2026 9th International Conference on Electronics Materials Engineering and Nano Technology Iementech 2026, 2026
Multi-Modal Forensic Retrieval Framework Combining Semantic Clip Embeddings with Biometric Attribute Analysis for Suspect Identification
Adrija Ghosh, Roushan Paul, Sainik Kumar Mahata
2026 9th International Conference on Electronics Materials Engineering and Nano Technology Iementech 2026, 2026
Today's criminal identification systems encounter major obstacles while matching textual descriptions to visual databases since they use manual processes that show poor scalability and human-dependent decision making. The research introduces an automatic multi-modal framework which combines CLIP for text-image semantic linking with FaceNet for biometric feature extraction and EfficientNet for visual attribute detection. The pipeline system receives natural language request input, then extracts meaningful weighted attributes (semantics at 70% and attributes at 20% with face information at 10%) before finding top-k matches through a combination scoring method. The system achieves an 94% hit rate appearing in the top 10 results against the database of suspects. The paper presents technical specifications about face detection using MTCNN alongside confidence threshold values (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\geq 0.9$</tex>) and attribute matching through Jaccard approach which are examined together with operational ethics related to real-world application.
Neural Machine Translation Using LSTM and Attention
Soumi Datta, Deena Joseph Wilson, Sainik Kumar Mahata
Lecture Notes in Networks and Systems, 2026
Prediction and Analysis of High Power pcLED’s Useful Life Using Machine Learning Model: A ML Predictions with Physical Degradation Result
Arindam Chakraborty, Sainik Kumar Mahata, Rajiv Ganguly, Monojit Mitra
Iranian Journal of Science and Technology Transactions of Electrical Engineering, 2026
Multimodal Approaches to Speech Emotion Recognition
Dipanjan Saha, Sayan Das, Prasun Maity, Sainik Kumar Mahata, Dipankar Das
Communications in Computer and Information Science, 2026
Emotion Detection in Text Using BERT
Sagar Suman, Ahana Sen, Sainik Kumar Mahata, Darothi Sarkar, Monalisa Dey, Koushik Chatterjee
Lecture Notes in Networks and Systems, 2026
A Hybrid AI Framework Integrating Machine Learning and Large Language Models for Intelligent Crop Recommendation
Tirthanka Saha, Rajdeep Ghosh, Tirtha Dutta, Pretam Sarkar, Rounak Saha, Sainik Kumar Mahata
2026 9th International Conference on Electronics Materials Engineering and Nano Technology Iementech 2026, 2026
Food is an essential component in living beings and for that we need agriculture and soil type detection is an essential part of agriculture. To help with that we have created a model where the model gives a hybrid decision support system accurately modeled to reduce the increasing risk of crop failure caused by unstable climatic conditions and soil nutrient differences. When the global agricultural environment drops the dependency in traditional farming, this study shows a strong computational methodology that combines mainly three particular layers to provide highly precise guidance. The starting layer in our model uses Random Forest machine learning model that focuses on soil classification based on soil type. The model then checks essential soil parameters that include Nitrogen (N), Phosphorus (P), and Potassium (K) levels along with the pH. The second layer brings the use of a Geospatial API needed for a 10 year longitudinal climate check in the second layer. The data of historical temperature, rainfall with local soil chemistry helps to calculate the environmental problems. The third layer is the Mistral 7B Large Language Model LLM, which is used in practical farming advice. Machine learning handles quantitative data while the LLM gives a practical context so that it offers agricultural related advice to support data results with real farming experience. The output lists the top five probable crops according to climate changes and difficulty risk scores. This dual focus on soil health and climate gives assurance on productive advice and continuity under volatile situations. Validation results indicate that the model performs almost flawlessly with benchmark data. By connecting the fixed set of probabilistic distribution of the Random Forest with the adaptive intelligence of a Large Language Model, the model provides a comprehensive decision-support tool with fewer limitations from the single-model machine learning applications.
Mood Capture Music Recommendation System
Ushneesh Chattopadhyay, Arpan Basu, Sainik Kumar Mahata
Lecture Notes in Networks and Systems, 2025
Enhancing Educational Feedback—A Paradigm Shift Through AI-Driven Chatbots
Sreeja Ghosh, Sakshi Sharma, Sainik Kumar Mahata
Lecture Notes in Networks and Systems, 2025
A Comparative Study of Cascade and End-to-End Speech Translation for Linguistic Diversity in India
Anoushka Sen, Aveepsa Sarkar, Sainik Kumar Mahata
Lecture Notes in Networks and Systems, 2025
A Survey on Recent Advancements in Neural Machine Translation
Soumi Datta, Deena Joseph Wilson, Sainik Kumar Mahata
Smart Innovation Systems and Technologies, 2025
Sentiment Analysis Using LSTM Model for Emotion Detection
Mehuli Dam, Sumanta Roy, Darothi Sarkar, Sainik Kumar Mahata
2025 8th International Conference on Electronics Materials Engineering and Nano Technology Iementech 2025, 2025
A Hybrid Approach to Sarcasm Detection in Dravidian Code-Mixed Texts
Ceur Workshop Proceedings, 2025
Enhancing Accuracy in Indian Language Summarization
Ceur Workshop Proceedings, 2025
Gen AI lens: Precision Diagnostics Through Interactive Segmentation and User centric Innovation in Medical Imaging
Ayan Chattopadhyay, Ayuska Saha, Amreta Dey, Gayatri Ghosh, Sainik Kumar Mahata
2025 8th International Conference on Electronics Materials Engineering and Nano Technology Iementech 2025, 2025
Detecting Disfluencies—Overcoming Barriers to Effective Communication
Dipanjan Saha, Amit Mondal, Sainik Kumar Mahata, Dipankar Das, Sivaji Bandyopadhyay
Lecture Notes in Networks and Systems, 2025
Consensus-Based Machine Translation for Code-Mixed Texts
Sainik Kumar Mahata, Dipankar Das, Sivaji Bandyopadhyay
ACM Transactions on Asian and Low Resource Language Information Processing, 2024
Comparative Analysis of Financial Datasets Predictive Modeling Using Feature Extraction Methods
Anupam Mondal, Sainik Kumar Mahata, Monalisa Dey, Darothi Sarkar
Lecture Notes in Electrical Engineering, 2024
SETA- Extractive to Abstractive Summarization with a Similarity-Based Attentional Encoder-Decoder Model
Monalisa Dey, Sainik Kumar Mahata, Anupam Mondal, Dipankar Das
Ecti Transactions on Computer and Information Technology, 2024
Parallel Corpus Development Using Machine Translation
Sainik Kumar Mahata, Jyoti Gupta, Khusboo Kumari, Monalisa Dey, Anupam Mondal, Darothi Sarkar
Lecture Notes in Electrical Engineering, 2024
Text summarization implementing abstractive and extractive methods
Debjyoti Ghosh, Abhirup Mazumder, Sainik Kumar Mahata
2023 7th International Conference on Electronics Materials Engineering and Nano Technology Iementech 2023, 2023
Exploring Summarization of Scientific Tables: Analysing Data Preparation and Extractive to Abstractive Summary Generation
International Journal of Computers and their Applications, 2023
Design Evaluation and Uses of Paraphraser Content Generation
Soumyajit Chowdhury, Pawan Shaw, Sainik Kumar Mahata
2023 7th International Conference on Electronics Materials Engineering and Nano Technology Iementech 2023, 2023
Exploring the Role of Automated Video Inspection and Recognition in Security Enhancement
Darothi Sarkar, Monalisa Dey, Sahini Das, Soham Bangal, Aniket Kar, Sainik Kumar Mahata, Anupam Mondal
2023 7th International Conference on Electronics Materials Engineering and Nano Technology Iementech 2023, 2023
Simplification of English and Bengali Sentences for Improving Quality of Machine Translation
Sainik Kumar Mahata, Avishek Garain, Dipankar Das, Sivaji Bandyopadhyay
Neural Processing Letters, 2022
Investigating the roles of sentiment in machine translation
Sainik Kumar Mahata, Dipankar Das, Sivaji Bandyopadhyay
Machine Translation, 2021
Sentiment Classification of Code-Mixed Tweets using Bi-Directional RNN and Language Tags
Proceedings of the 1st Workshop on Speech and Language Technologies for Dravidian Languages Dravidianlangtech 2021 at 16th Conference of the European Chapter of the Association for Computational Linguistics Eacl 2021, 2021
Preparation of Sentiment tagged Parallel Corpus and Testing Its Effect on Machine Translation
Sainik Kumar Mahata, Amrita Chandra, Dipankar Das, Sivaji Bandyopadhyay
Lecture Notes in Networks and Systems, 2021
Classification of COVID19 tweets using Machine Learning Approaches
Social Media Mining for Health Smm4h 2021 Proceedings of the 6th Workshop and Shared Tasks, 2021
Performance Gain in Low Resource MT with Transfer Learning: An Analysis concerning Language Families
Sainik Kumar Mahata, Subhabrata Dutta, Dipankar Das, Sivaji Bandyopadhyay
ACM International Conference Proceeding Series, 2020
Normalization of Numeronyms using NLP Techniques
Avishek Garain, Sainik Kumar Mahata, Subhabrata Dutta
2020 IEEE Calcutta Conference Calcon 2020 Proceedings, 2020
JUNLP@Dravidian-CodeMix-FIRE2020: Sentiment classification of code-mixed tweets using bi-directional RNN and language tags
Ceur Workshop Proceedings, 2020
JUNLP at SemEval-2020 Task 9: Sentiment Analysis of Hindi-English code mixed data using Grid Search Cross Validation
Avishek Garain, Sainik Mahata, Dipankar Das
14th International Workshops on Semantic Evaluation Semeval 2020 Co Located 28th International Conference on Computational Linguistics Coling 2020 Proceedings, 2020
Analyzing Code-Switching Rules for Englishâ€“Hindi Code-Mixed Text
Sainik Kumar Mahata, Sushnat Makhija, Ayushi Agnihotri, Dipankar Das
Advances in Intelligent Systems and Computing, 2020
Code-mixed to monolingual translation framework
Sainik Kumar Mahata, Soumil Mandal, Dipankar Das, Sivaji Bandyopadhyay
ACM International Conference Proceeding Series, 2019
MTIL2017: Machine translation using recurrent neural network on statistical machine translation
Sainik Kumar Mahata, Dipankar Das, Sivaji Bandyopadhyay
Journal of Intelligent Systems, 2019
Sentiment analysis at SEPLN (TASS)-2019: Sentiment analysis at tweet level using deep learning
Ceur Workshop Proceedings, 2019
JUMT at WMT2019 news translation task: A hybrid approach to machine translation for Lithuanian to English
Riktim Mondal, Shankha Raj Nayek, Aditya Chowdhury, Santanu Pal, Sudip Kumar Naskar, Josef van Genabith
Wmt 2019 4th Conference on Machine Translation Proceedings of the Conference, 2019
JUCBNMT at WMT2018 News Translation Task: Character Based Neural Machine Translation of Finnish to English
Wmt 2018 3rd Conference on Machine Translation Proceedings of the Conference, 2018
BUCC2017: A hybrid approach for identifying parallel sentences in comparable corpora
Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2017
WMT2016: A Hybrid Approach to Bilingual Document Alignment
Sainik Mahata, Dipankar Das, Santanu Pal
Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2016
Tamper detection of electrocardiographic signal using watermarked bio-hash code in wireless cardiology
Nilanjan Dey, Monalisa Dey, Sainik Kumar Mahata, Achintya Das, Sheli Sinha Chaudhuri
International Journal of Signal and Imaging Systems Engineering, 2015
Electrocardiogram feature based inter-human biometric authentication system
Monalisa Dey, Nilanjan Dey, Sainik Kumar Mahata, Sayan Chakraborty, Suvojit Acharjee, Achintya Das
Proceedings International Conference on Electronic Systems Signal Processing and Computing Technologies Icesc 2014, 2014

RECENT SCHOLAR PUBLICATIONS

Prediction and Analysis of High Power pcLED’s Useful Life Using Machine Learning Model: A ML Predictions with Physical Degradation Result
A Chakraborty, SK Mahata, R Ganguly, M Mitra
Iranian Journal of Science and Technology, Transactions of Electrical … , 2026
2026
Decompose, Route, Retrieve: A Modular NLP Pipeline Implementing Multi-Hop Architecture for Answering Complex Questions Over Heterogeneous Sources
D Shome, A Sengupta, SK Mahata
2026 9th International Conference on Electronics, Materials Engineering … , 2026
2026
Multi-Modal Forensic Retrieval Framework Combining Semantic Clip Embeddings with Biometric Attribute Analysis for Suspect Identification
A Ghosh, R Paul, SK Mahata
2026 9th International Conference on Electronics, Materials Engineering … , 2026
2026
A Hybrid AI Framework Integrating Machine Learning and Large Language Models for Intelligent Crop Recommendation
T Saha, R Ghosh, T Dutta, P Sarkar, R Saha, SK Mahata
2026 9th International Conference on Electronics, Materials Engineering … , 2026
2026
Dense Semantic Compression: A Low-Dimensional Siamese Architecture for Efficient Paraphrase Detection
S Raha, A Kumar, SK Mahata
2026 9th International Conference on Electronics, Materials Engineering … , 2026
2026
Sentiment Analysis Using Machine Learning: A Comprehensive Study
A Das, AK Singh, SK Mahata
2026 9th International Conference on Electronics, Materials Engineering … , 2026
2026
Dynamics of Character Embeddings in Indian Mythology: A Physics-Informed Neural Networks Approach
A Paul, A Goswami, SK Mahata, D Das
Proceedings of the 17th annual meeting of the Forum for Information … , 2025
2025
Neural Machine Translation Using LSTM and Attention
S Datta, DJ Wilson, SK Mahata
International Conference on Data Analytics and Insights, 291-301 , 2025
2025
Detecting Disfluencies—Overcoming
D Saha, A Mondal, SK Mahata, D Das, S Bandyopadhyay
Proceedings of International Conference on Data Analytics and Insights … , 2025
2025
A Cascaded Speech-to-Speech Translation System for Bengali to English
A Sarkar, A Sen, SK Mahata
International Conference on Computational Intelligence, Data Science and … , 2025
2025
Emotion Detection in Text Using BERT
S Suman, A Sen, SK Mahata, D Sarkar, M Dey, K Chatterjee
International Conference on Computational Intelligence, Data Science and … , 2025
2025
Gen AI lens: Precision Diagnostics Through Interactive Segmentation and User centric Innovation in Medical Imaging
A Chattopadhyay, A Saha, A Dey, G Ghosh, SK Mahata
2025 8th International Conference on Electronics, Materials Engineering … , 2025
2025
Sentiment Analysis Using LSTM Model for Emotion Detection
M Dam, S Roy, D Sarkar, SK Mahata
2025 8th International Conference on Electronics, Materials Engineering … , 2025
2025
Citations: 3
A Survey on Recent Advancements in Neural Machine Translation
S Datta, DJ Wilson, SK Mahata
International Conference on Smart Systems and Wireless Communication, 187-200 , 2024
2024
Security threats in agentic ai system
R Khan, S Sarkar, SK Mahata, E Jose
arXiv preprint arXiv:2410.14728 , 2024
2024
Citations: 43
Enhancing Educational Feedback—A Paradigm Shift Through AI-Driven Chatbots
S Ghosh, S Sharma, SK Mahata
International Conference on Data Analytics and Insights, 431-443 , 2024
2024
Mood Capture Music Recommendation System
U Chattopadhyay, A Basu, SK Mahata
International Conference on Data Analytics and Insights, 213-225 , 2024
2024
A Comparative Study of Cascade and End-to-End Speech Translation for Linguistic Diversity in India
A Sen, A Sarkar, SK Mahata
International Conference on Data Analytics and Insights, 227-238 , 2024
2024
Parallel Corpus Development Using Machine Translation Check for updates
SK Mahata, J Gupta, K Kumari, M Dey, A Mondal, D Sarkar
Intelligent IT Solutions for Sustainability in Industry 5.0 Paradigm: Select … , 2024
2024
SETA-extractive to abstractive summarization with a similarity-based attentional encoder-decoder model
M Dey, SK Mahata, A Mondal, D Das
ECTI Transactions on Computer and Information Technology (ECTI-CIT) 18 (3 … , 2024
2024
Citations: 1

MOST CITED SCHOLAR PUBLICATIONS

Mtil2017: Machine translation using recurrent neural network on statistical machine translation
SK Mahata, D Das, S Bandyopadhyay
Journal of Intelligent Systems , 2018
2018
Citations: 77
Preparing bengali-english code-mixed corpus for sentiment analysis of indian languages
S Mandal, SK Mahata, D Das
arXiv preprint arXiv:1803.04000 , 2018
2018
Citations: 53
Security threats in agentic ai system
R Khan, S Sarkar, SK Mahata, E Jose
arXiv preprint arXiv:2410.14728 , 2024
2024
Citations: 43
SMT vs NMT: a comparison over Hindi and Bengali simple sentences
S Mahata, S Mandal, D Das, S Bandyopadhyay
Proceedings of the 15th International Conference on Natural Language … , 2018
2018
Citations: 37
Tamper detection of electrocardiographic signal using watermarked bio–hash code in wireless cardiology
N Dey, M Dey, SK Mahata, A Das, SS Chaudhuri
International Journal of Signal and Imaging Systems Engineering 8 (1), 46-58 , 2015
2015
Citations: 36
Electrocardiogram feature based inter-human biometric authentication system
M Dey, N Dey, SK Mahata, S Chakraborty, S Acharjee, A Das
2014 International Conference on Electronic Systems, Signal Processing and … , 2014
2014
Citations: 32
Simplification of English and Bengali sentences for improving quality of machine translation
SK Mahata, A Garain, D Das, S Bandyopadhyay
Neural Processing Letters 54 (4), 3115-3139 , 2022
2022
Citations: 22
Code-mixed to monolingual translation framework
SK Mahata, S Mandal, D Das, S Bandyopadhyay
Proceedings of the 11th Annual Meeting of the Forum for Information … , 2019
2019
Citations: 21
Wmt2016: A hybrid approach to bilingual document alignment
S Mahata, D Das, S Pal
Proceedings of the First Conference on Machine Translation: Volume 2, Shared … , 2016
2016
Citations: 17
Classification of COVID19 tweets using machine learning approaches
A Mondal, S Mahata, M Dey, D Das
Proceedings of the Sixth Social Media Mining for Health (# SMM4H) Workshop … , 2021
2021
Citations: 15
Sentiment classification of code-mixed tweets using bi-directional RNN and language tags
S Mahata, D Das, S Bandyopadhyay
Proceedings of the First Workshop on Speech and Language Technologies for … , 2021
2021
Citations: 13
BUCC2017: A Hybrid Approach for Identifying Parallel Sentences in Comparable Corpora
SB Sainik Kumar Mahata, Dipankar Das
10th Workshop on Building and Using Comparable Corpora, 56-59 , 2017
2017
Citations: 13
JUNLP at SemEval-2020 Task 9: Sentiment analysis of hindi-english code mixed data using grid search cross validation
A Garain, S Mahata, D Das
Proceedings of the Fourteenth Workshop on Semantic Evaluation, 1276-1280 , 2020
2020
Citations: 11
JUNLP@ Dravidian-CodeMix-FIRE2020: Sentiment classification of code-mixed tweets using bi-directional RNN and language tags
SK Mahata, D Das, S Bandyopadhyay
arXiv preprint arXiv:2010.10111 , 2020
2020
Citations: 11
Disease prediction from drug information using machine learning
S Das, SK Mahata, A Das, K Deb
American Journal of Electronics & Communication 1 (4), 16-21 , 2021
2021
Citations: 10
Normalization of numeronyms using nlp techniques
A Garain, SK Mahata, S Dutta
2020 IEEE Calcutta Conference (CALCON), 7-9 , 2020
2020
Citations: 10
Development of pos tagger for english-bengali code-mixed data
T Raha, S Mahata, D Das, S Bandyopadhyay
Proceedings of the 16th International Conference on Natural Language … , 2019
2019
Citations: 10
Investigating the roles of sentiment in machine translation
SK Mahata, D Das, S Bandyopadhyay
Machine Translation 35 (4), 687-709 , 2021
2021
Citations: 9
Analyzing code-switching rules for english–hindi code-mixed text
SK Mahata, S Makhija, A Agnihotri, D Das
Emerging Technology in Modelling and Graphics: Proceedings of IEM Graph 2018 … , 2019
2019
Citations: 9
A Novel Approach of Steganography using Hill Cipher
SK Mahata, PM Anupam Mondal, Deepak Kumar
International Journal of Computer Application, 29-31 , 2013
2013
Citations: 9

Sainik Kumar Mahata

EDUCATION

RESEARCH INTERESTS

Scopus Publications

RECENT SCHOLAR PUBLICATIONS

MOST CITED SCHOLAR PUBLICATIONS