Dr. Sanjay Chakraborty is currently working as an Assistant Professor at JIS University. He completed his Ph.D. thesis at the University of Calcutta. He completed his MTech from the National Institute of Technology, Raipur. He completed his B-Tech from the West Bengal University of Technology. He has published 54 research papers in various international journals, conferences, and book chapters. He has published two international authored books. His areas of interest are Data Mining & machine learning, feature subset selection, and quantum computing. He has a total of 11 years of teaching and research experience. He worked as a reviewer in several international conferences and SCI, SCOPUS journals including BMC Medical Informatics and Decision Making Journal, Scientific Reports Springer Nature, IEEE Transactions on Computational Social Systems, International Journal of Machine Learning and Cybernetics, Concurrency and Computation: Practice and Experience Journal Wiley, Egyptian Informat
EDUCATION
B.Tech from W.B.U.T (MAKAUT) in IT, M.Tech from NIT Raipur and Ph.D. (Tech) from University of Calcutta
RESEARCH INTERESTS
Quantum Computing, Machine learning, Data Mining
65
Scopus Publications
2076
Scholar Citations
20
Scholar h-index
31
Scholar i10-index
Scopus Publications
Generative artificial intelligence in fifth-generation education systems: A systematic review Sanjay Chakraborty Engineering Applications of Artificial Intelligence, 2026 Generative artificial intelligence is increasingly transforming education by enabling adaptive learning environments, personalized instructional support, and collaborative knowledge creation, while also assisting research, assessment, and academic administration. In the context of fifth-generation education systems, the integration of generative artificial intelligence offers new opportunities to enhance student engagement, support innovative pedagogical practices, and improve scholarly productivity. This study presents a systematic review of recent research on the adoption of generative artificial intelligence in primary, secondary, and higher education institutions, using established guidelines for systematic literature reviews and bibliometric analysis. The review examines applications of generative artificial intelligence for learners, educators, and researchers, and identifies key challenges including academic integrity risks, algorithmic bias, ethical concerns, data privacy issues, and unequal access to advanced educational technologies. By analyzing research trends, thematic relationships, and existing gaps, this study provides insights for the design of adaptive learning systems, the promotion of responsible use of artificial intelligence in education, and the direction of future research efforts. Overall, the findings highlight the potential of generative artificial intelligence to support human–machine collaboration, lifelong learning, and inclusive educational environments, offering practical guidance for policymakers, educators, and engineers seeking to apply artificial intelligence for meaningful educational impact.
Scaling transformers for time series forecasting: do pretrained large models outperform small-scale alternatives? Sanjay Chakraborty, Ibrahim Delibasoglu, Fredrik Heintz Artificial Intelligence Review, 2026 Large pre-trained models have demonstrated remarkable capabilities across domains, but their comparative effectiveness in time series forecasting, especially against smaller, efficient models, remains underexplored. This work empirically examines whether pre-trained large-scale time series models (LSTSMs) trained on diverse datasets can outperform traditional non-pretrained small-scale transformers in forecasting tasks. We specifically compare large models trained from scratch against those benefiting from pretraining to measure the direct impact of transfer learning on forecasting performance. We analyze state-of-the-art (SOTA) pre-trained universal time series models (e.g., Moirai, GPT4TS, Timer, CALF, LLM4TS) alongside conventional small-scale transformers, evaluating accuracy and computational efficiency across multiple benchmarks. We further conduct an extensive ablation study across varying fine-tuning data sizes (10%, 25%, and 75%) to assess few-shot, moderate, and near full-data adaptation capabilities. Additionally, explainability of large time series models is examined using comprehensiveness via feature ablation, occlusion, integrated gradients and gradient shap methods. Besides that, interpretability of pretraining and finetuning strategies is also examined using spectral metrics via WeightWatcher to quantify layer-wise generalization and representation quality, while theoretical and quantitative computational complexity analyses, including parameter counts, training time, model sizes, and inference latency, highlight the trade-offs between predictive performance and resource efficiency. Our findings reveal the strengths and limitations of pre-trained large-scale models, providing insights into their suitability for time series tasks compared to task-specific small-scale architectures. The results highlight scenarios where pretraining offers advantages and where simpler models remain competitive.
A survey of AI-supported materials informatics Sanjay Chakraborty, Jonas Björk, Martin Dahlqvist, Johanna Rosen, Fredrik Heintz Computer Science Review, 2026 The evolution from traditional artificial intelligence (AI) to advanced AI is explored in the predictive and structural analysis in materials informatics, highlighting how advancements in machine learning have revolutionised the discovery and design of new materials and molecular structures. It examines how traditional AI, with its reliance on heuristic models and empirical data, has paved the way for the emergence of generative AI, which leverages advanced machine learning frameworks to predict material properties, structural design and analysis and synthesise new materials. The work highlights key developments, compares the effectiveness of various approaches, relevant databases and software frameworks in material informatics, and discusses the transformative impact of traditional and advanced AI in accelerating materials discovery and innovation. Through a detailed analysis of recent advancements, challenges, and future prospects, this paper aims to offer valuable insights into the evolving landscape of AI-driven materials informatics.
Intervention-Aware Time Series Modeling: Capturing and Evaluating Feature Dependencies Ibrahim Delibasoglu, Sanjay Chakraborty, Fredrik Heintz, Mattias Tiger Proceedings of the Aaai Conference on Artificial Intelligence, 2026 Understanding how localized changes in one variable affect others in multivariate time series is essential for diagnostics and decision-making in complex systems. Existing models often fail to capture realistic inter-feature dynamics when simulating "what-if" scenarios, leading to inaccurate or uncorrelated reconstructions. We propose CFORVAE, a variational autoencoder framework that explicitly addresses this limitation by combining temporal decomposition with frequency-domain feature correlation modeling. Our architecture uses a dual-path encoding of trend and seasonal components, each projected into attention-pooled latent spaces, and applies Fourier Neural Operators (FNO) to capture cross-feature dependencies in the spectral domain. This decomposition-correlation design enables component-specific latent manipulation and ensures that local modifications propagate realistically across correlated variables. Through extensive experiments, we show that CFORVAE outperforms state-of-the-art baselines in preserving temporal and feature-level dependencies, especially under adjustment-based reconstructions, making it a powerful tool for interpretable "what-if" analysis and diagnostics.
Exploring Deep Learning Models for COVID-19 Detection from CT-Scan and X-Ray Images Shirshendu Das, Hrit Saha, Soumyajit Pal, Sayantan Paul, Sanjay Chakraborty Artificial Intelligence in Healthcare Trends Applications and Future Directions, 2026 This chapter focuses on COVID-19 classification using CNN models and their different versions. The chapter utilizes a dataset of X-ray images collected from confirmed COVID-19 patients, as well as non-COVID-19 patients. Deep learning models, specifically convolutional neural networks (CNNs), are employed to learn and extract meaningful features from the X-ray images. Multiple CNN models, including popular architectures like VGG-16, ResNet-50, and InceptionV3, are trained and fine-tuned on the dataset to learn discriminative features indicative of COVID-19 infection. The ensemble model aggregates the outputs of the constituent models, using techniques such as voting or weighted averaging to make the final classification decision. The results demonstrate that the ensemble of CNN models achieves superior performance compared to individual models. The ensemble model consistently outperforms the individual models in terms of sensitivity, specificity, and accuracy. The ensemble of CNN models demonstrates its potential as a valuable decision-support system for healthcare professionals.
Advancing delignification in the pulp and paper industry: Multivariate time series forecasting, explainability, and simulation analysis Ibrahim Delibasoglu, Sanjay Chakraborty, Fredrik Heintz, Fredrik Wernersson Brodin, Andreas Darnell Journal of Intelligent Manufacturing, 2026 This work explores the application of state-of-the-art techniques of time series forecasting to the delignification process in the pulp and paper industry, aiming to enhance sustainability and efficiency. While traditional machine learning models, such as Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM), have been widely used, recent advancements in time series architectures provide significant improvements in prediction accuracy. This study adopts cutting-edge time series architectures and integrates them with explainability techniques (Explainable Artificial Intelligence, XAI) to analyze critical features and their temporal saliency, providing insights into the most influential variables in the delignification process. For a sequence length of 96, Crossformer attains the lowest error of 0.625±0.032, while for a sequence length of 24, LMS-AutoTSF achieves the lowest error of 0.281±0.0001. Additionally, we perform simulation analyses using the identified important features to evaluate the effects of input parameter changes–such as temperature or H-factor adjustments–on correlated variables and the target Kappa number. To model these interdependencies and generate realistic input scenarios, we employ a Conditional Variational Autoencoder (CVAE), which enables the adjustment of one input feature while automatically adapting correlated features in a coherent and interpretable manner. This allows for counterfactual simulations that help operators understand the dynamic impact of process modifications on the overall system behavior. By leveraging advanced forecasting models, XAI-driven feature analysis, and CVAE-based simulation studies, we aim to improve prediction accuracy, optimize resource usage, and enhance operational efficiency. This work underscores the potential of combining modern time series forecasting, explainability techniques, and generative modeling to advance delignification processes, contributing to a more sustainable future for the pulp and paper industry. We further extend our experimental analysis to another industrial pulp dataset comprising a large number of instances, where Crossformer achieves the lowest error of 0.283 ± 0.112, followed by LMS-AutoTSF with the second-lowest error of 0.367 ± 0.136, across average prediction lengths of 12, 24, and 48.
Deep Learning and X-Ray Imaging Innovations for Pneumonia Infection Diagnosis: Introducing DeepPneuNet Sanjay Chakraborty, Tirthajyoti Nag, Saroj Kumar Pandey, Jayasree Ghosh, Lopamudra Dey Computational Intelligence, 2025 This paper aims to develop a new deep learning model (DeepPneuNet) and evaluate its performance in predicting Pneumonia infection diagnosis based on patients' chest x‐ray images. We have collected 5856 chest x‐ray images that are labeled as either “pneumonia” or “normal” from a public forum. Before applying the DeepPneuNet model, a necessary feature extraction and feature mapping have been done on the input images. Conv2D layers with a 1 × 1 kernel size are followed by ReLU activation functions to make up the model. These layers are in charge of recognizing important patterns and features in the images. A MaxPooling 2D procedure is applied to minimize the spatial size of the feature maps after every two Conv2D layers. The sparse categorical cross‐entropy loss function trains the model, and the Adam optimizer with a learning rate of 0.001 is used to optimize it. The DeepPneuNet provides 90.12% accuracy for diagnosis of the Pneumonia infection for a set of real‐life test images. With 9,445,586 parameters, the DeepPneuNet model exhibits excellent parameter efficiency. DeepPneuNet is a more lightweight and computationally efficient alternative when compared to the other pre‐trained models. We have compared accuracies for predicting Pneumonia diagnosis of our proposed DeepPneuNet model with some state‐of‐the‐art deep learning models. The proposed DeepPneuNet model is more advantageous than the existing state‐of‐the‐art learning models for Pneumonia diagnosis with respect to accuracy, precision, recall, F‐score, training parameters, and training execution time.
A Brief Concept on Machine Learning Sanjay Chakraborty, SK Hafizul Islam, Debabrata Samanta Eai Springer Innovations in Communication and Computing, 2022
Effect of watermarking in vector quantization based image compression Soumyo Bose, Madhulika, Suvojit Acharjee, Shatadru Roy Chowdhury, Sayan Chakraborty, Nilanjan Dey 2014 International Conference on Control Instrumentation Communication and Computational Technologies Iccicct 2014, 2014
Generative artificial intelligence in fifth-generation education systems: A systematic review S Chakraborty Engineering Applications of Artificial Intelligence 173, 114463 , 2026 2026 Citations: 29
ETIA: Ensemble trading indicator analysis for improved market forecasting with enhanced deep learning and asymmetric cryptography S Banik, S Maity, S Chakraborty SN Business & Economics 6 (174), https://doi.org/10.1007/s43546-026-01174 , 2026 2026
Empowering healthcare 5.0 with deep learning: techniques, trends, and future directions PK Maji, S Chakraborty, A Sadiq, S Basu, K Ghosh Artificial Intelligence Review , 2026 2026
Advancing delignification in the pulp and paper industry: Multivariate time series forecasting, explainability, and simulation analysis I Delibasoglu, S Chakraborty, F Heintz, F Wernersson Brodin, A Darnell Journal of Intelligent Manufacturing, 1-36 , 2026 2026
Intervention-Aware Time Series Modeling: Capturing and Evaluating Feature Dependencies I Delibasoglu, S Chakraborty, F Heintz, M Tiger 40th Annual AAAI Conference on Artificial Intelligence (AAAI-26) (Core Rank … , 2026 2026
Scaling transformers for time series forecasting: do pretrained large models outperform small-scale alternatives? S Chakraborty, I Delibasoglu, F Heintz Artificial Intelligence Review 59 (62) , 2026 2026 Citations: 3
A survey of AI-supported materials informatics S Chakraborty, J Björk, M Dahlqvist, J Rosen, F Heintz Computer Science Review 59, 100845 , 2026 2026 Citations: 10
Exploring Deep Learning Models for COVID-19 Detection from CT-Scan and X-Ray Images S Das, H Saha, S Pal, S Paul, S Chakraborty Artificial Intelligence in Healthcare, 173-186 , 2026 2026 Citations: 1
Creative and Modern Variants of Symmetric-Key Block Cypher Algorithms: A Novel Comprehensive Approach S Banik, S Maity, S Chakraborty 2025 4th International Conference on Applied Artificial Intelligence and … , 2025 2025
Advancing EEG Signal Classification Using Hybrid Deep Learning Architectures and Kolmogorov–Arnold Networks M Paul, S Chakraborty, S Basu, K Majumder International Conference On Data Mining And Information Security, 499-522 , 2025 2025
Enhancing Educational Environments: Object Recognition and Relationship Inference through YOLO in Education 5.0 A Ghosh, S Bhattacharya, S Roy, S Ray, R Upadhyay, S Chakraborty Advances in Health Informatics, Intelligent Systems and Networking … , 2025 2025
Hierarchical Patch Based Transformer with Learnable Weighted Loss Optimization for Multivariate Time Series Forecasting S Chakraborty, I Delibasoglu, F Heintz Available at SSRN 5400868 , 2025 2025
Proceedings of International Conference on Data Analytics and Insights N Chaki, ND Roy, S Chakraborty, P Debnath, XS Yang https://link.springer.com/book/9789819623280 1234, LNNS, Springer , 2025 2025 Citations: 1
Enhancing Time Series Forecasting with Fuzzy Attention-Integrated Transformers S Chakraborty, F Heintz arXiv preprint arXiv:2504.00070 , 2025 2025 Citations: 4
Integrating Quantum-Classical Attention in Patch Transformers for Enhanced Time Series Forecasting S Chakraborty, F Heintz arXiv preprint arXiv:2504.00068 , 2025 2025 Citations: 3
Deep Learning and X-Ray Imaging Innovations for Pneumonia Infection Diagnosis: Introducing DeepPneuNet S Chakraborty, T Nag, SK Pandey, J Ghosh, L Dey Computational Intelligence 41 (1), e70029 , 2025 2025 Citations: 4
Deep learning inspired game-based cognitive assessment for early dementia detection PK Maji, S Acharya, P Paul, S Chakraborty, S Basu Engineering Applications of Artificial Intelligence 142, 109901 , 2025 2025 Citations: 8
Supervised learning approaches for predicting Ebola-Human Protein-Protein interactions L Dey, S Chakraborty Gene 942 (1), 149228 , 2025 2025 Citations: 4
Enhancing Autism Detection: Comparative Analysis of Pre-Trained Models via Transfer Learning and Ensemble Deep Learning S Chakraborty, T Nag, SK Pandey, J Ghosh, L Dey Researchgate , 2025 2025
Multi-objective, Multi-class and Multi-label Data Classification with Class Imbalance S Chakraborty, L Dey Springer, STNIC 1, 10.1007/978-981-97-9622-9 , 2024 2024 Citations: 4
MOST CITED SCHOLAR PUBLICATIONS
Sentiment Analysis of Review Datasets Using Naïve Bayes’ and K-NN Classifier L Dey, S Chakraborty, A Biswas, B Bose, S Tiwari International Journal of Information Engineering and Electronic Business … , 2016 2016 Citations: 415
A Review on Application of Data Mining Techniques to Combat Natural Disasters S Goswami, S Chakraborty, S Ghosh, A Chakrabarti, B Chakraborty Ain Shams Engineering Journal (ASEJ) (IF-6.0) 9 (3), 365-378 , 2018 2018 Citations: 255
Analysis and study of incremental k-means clustering algorithm S Chakraborty, NK Nagwani High Performance Architecture and Grid Computing, CCIS, Springer, 338-341 , 2011 2011 Citations: 176
Machine Learning Techniques for Sequence-based Prediction of Viral-Host Interactions between SARS-CoV-2 and Human Proteins L Dey, S Chakraborty, A Mukhopadhyay Biomedical Journal 43 (5), 438-450 , 2020 2020 Citations: 138
Performance comparison of incremental k-means and incremental dbscan algorithms S Chakraborty, NK Nagwani, L Dey International Journal of Computer Application 27 (11), 14-18 , 2011 2011 Citations: 110
An AI-Based Medical Chatbot Model for Infectious Disease Prediction S Chakraborty, H Pal, S Ghatak, SK Pandey, A Kumar, KU Singh, ... IEEE Access 10 (10.1109/ACCESS.2022.3227208), 128469 - 128483 , 2022 2022 Citations: 105
EEG based emotion classification using “Correlation Based Subset Selection” D Das Chakladar, S Chakraborty Cognitive Systems Research (Biologically Inspired Cognitive Architectures) 24 , 2018 2018 Citations: 79
A Hybrid Quantum Feature Selection Algorithm using a Quantum Inspired Graph Theoretic Approach S Chakraborty, S Hossian Shaikh, A Chakrabarti, R Ghosh Applied Intelligence 50 (6), 1775–1793 , 2020 2020 Citations: 69
An Image Denoising Technique using Quantum Wavelet Transform S Chakraborty, S Hossian Shaikh, A Chakrabarti, R Ghosh Journal of Theoretical Physics 59 (11), 3348-3371 , 2020 2020 Citations: 60
Quantum image processing: challenges and future research issues S Chakraborty, SB Mandal, SH Shaikh International Journal of Information Technology 14 (1), 475–489 , 2018 2018 Citations: 50
A Study and Comparison of Deep Learning based Potato Leaf Disease Detection and Classification Techniques using Explainable AI H Pal, S Ghatak, S Chakraborty, SK Pandey, S Maity, D Show, L Dey Multimedia Tools and Applications 83 (26), 42485–42518 , 2023 2023 Citations: 43
Weather Forecasting using Incremental K-means Clustering S Chakraborty, NK Nagwani, L Dey arXiv preprint arXiv:1406.4756 , 2012 2012 Citations: 41
Multi-target way of cursor movement in brain computer interface using unsupervised learning D Das Chakladar, S Chakraborty Cognitive Systems Research(Biologically Inspired Cognitive Architectures) 25 , 2018 2018 Citations: 30
Generative artificial intelligence in fifth-generation education systems: A systematic review S Chakraborty Engineering Applications of Artificial Intelligence 173, 114463 , 2026 2026 Citations: 29
Detection and Classification of Novel Attacks and Anomaly in IoT Network using Rule based Deep Learning Model S Chakraborty, S Kumar Pandey, S Maity, L Dey SN Computer Science 5 (1056), 10.1007/s42979-024-03429-5 , 2024 2024 Citations: 28
Convex-hull & DBSCAN clustering to predict future weather R Dey, S Chakraborty 6th International IEEE Conference and Workshop on Computing and … , 2015 2015 Citations: 25
Data Classification and Incremental Clustering in Data Mining and Machine Learning S Chakraborty, S Hafizul Islam, D Samanta Springer Cham (ISBN:978-3-030-93087-5) Authored Book 3, XXI, 196 , 2022 2022 Citations: 24
Feature Extraction and Classification in Brain-Computer Interfacing: Future Research Issues and Challenges D Das Chakladar, S Chakraborty Natural Computing for Unsupervised Learning, 101-131 , 2019 2019 Citations: 22
Filter Based Feature Selection Methods using Hill Climbing Approach S Goswami, S Chakraborty, P Guha, A Tarafdar, A Kedia Natural Computing for Unsupervised Learning, 213-234 , 2019 2019 Citations: 22
An approach of feature selection using graph-theoretic heuristic and hill climbing S Goswami, AK Das, P Guha, A Tarafdar, S Chakraborty, A Chakrabarti, ... Pattern Analysis and Applications 22 (2), 615–631 , 2019 2019 Citations: 21
SOCIAL, ECONOMIC, or ACADEMIC BENEFITS
To be a part of the Research & Development wing in the field of Machine Learning and Quantum Computing. I would like to take up a challenging role in active institute-industrial research activities, which will fulfill my longing to relentless learning. My priority is to make significant contributions towards the innovation and research activity of the organization. I belong to through a continuous process of application of mind and acquired expertise. I am really interested and enthusiastic about quantum machine learning and quantum image processing and its applications in academics as well as industry.
