Amartya Chakraborty
Verified @gmail.com
Scopus Publications
- A novel approach towards balanced emotion analysis through synthetic augmentation of facial landmark trajectories
Mehuli Chatterjee, Ishita Kar, Stobak Dutta, Amartya Chakraborty, Arunangshu Pal
Discover Applied Sciences, 2026
Mental health is essential for well-being, but poorly managed emotions can lead to depression and anxiety. Early emotion recognition systems support timely intervention. While physiological signals like ECG and EEG are accurate, they are invasive for everyday use. This study uses Facial Landmark Trajectories, namely EMO features, from the ASCERTAIN dataset, a non-invasive method tracking facial movements to capture authentic emotions. In contrast to the original dataset, in our work these emotions are classified into four valence-arousal quadrants: High Arousal High Valence (HAHV), High Arousal Low Valence (HALV), Low Arousal High Valence (LAHV), and Low Arousal Low Valence (LALV). To address the inherent class imbalance in this 4-class problem, the SMOTE, GAN, and CTGAN techniques are utilized to generate synthetic data for balanced classes. Four machine learning models, namely, KNN, SVM, Decision Tree, and Random Forest are tested on the augmented datasets, evaluated via confusion matrices and density plots for identifying overfitting. Experimental results demonstrate that CTGAN shows the least overfitting, with synthetic data closely matching the original and Random Forest achieving the highest accuracy (75%) and balanced true positive rates (>40% for all classes), demonstrating the potential utility of using Facial Landmark Trajectories for the development of an efficient automated emotion recognition system. - A Novel Hypergraph-Based Social Network
Soumyajit Naskar, Tarik Anowar, Amartya Chakraborty, Nandini Mukherjee
Lecture Notes in Networks and Systems, 2026 - PHYSIGEN: Physiological signal generation for class imbalance mitigation based on generative AI and machine learning
Stobak Dutta, Amartya Chakraborty, Anirban Mitra, Pushan Kumar Dutta, Alvaro Rocha
Innovation and Emerging Technologies, 2026
The study of emotion recognition is quite popular in recent years due to the impact of emotions on human behavior and social interactions. Understanding and identifying emotions has become very crucial nowadays because it influences decision-making, communication, and relationships. Emotion recognition can be performed in two different ways—unimodal or multimodal, depending on the number of physiological signals used. In this work, a multimodal approach has been adopted to classify emotions in four quadrants of the valence–arousal plane. This study uniquely compares synthetic minority over-sampling technique (SMOTE) and conditional generative adversarial network (CTGAN) for multimodal physiological emotion recognition and introduces a class-conditional CTGAN strategy that enhances minority-class sample diversity. The physiological signals that have been used are ECG, EEG, and Galvanic Skin Response (GSR), taken from the ASCERTAIN dataset, which is inherently class imbalanced. To address the class imbalance issue, data augmentation techniques like SMOTE and CTGAN are used to balance the dataset. The study evaluates the performance of Decision Tree (DTree), support vector machine (SVM), logistic regression (LR), linear discriminant analysis (LDA), and k-Nearest Neighbors (kNN) in emotion classification. It is observed that CTGAN-based augmentation improved SVM accuracy from 46.8% to 71.74%, while recognition of the minority class HAHV increased from 3.8% (original) to 47.2% (CTGAN). Similar improvements were observed across LR and LDA, demonstrating that generative adversarial network (GAN)-based synthesis significantly enhances minority-class detection. - Topic and opinion infused hypergraphs for influence maximization
Amartya Chakraborty, Nandini Mukherjee
Physics Letters Section A General Atomic and Solid State Physics, 2025 - Heart Disease Prediction: A Clustering-Based Clinical Decision Support Approach
Rajendrani Mukherjee, Amartya Chakraborty, Shibaprasad Sen, Sudip Naskar
Machine Learning in Biomedical and Health Informatics Current Applications and Challenges, 2025
Heart disease is a common cause of death worldwide. Nowadays, several CDS (clinical decision support) systems are helping to avert the disease to great extent. In this research, an effort has been made to use different clustering techniques (k-means, k-medoids, hierarchical agglomerative clustering (HAC)) on standard heart disease datasets. An estimate has been done regarding the prediction accuracy of each cluster using machine learning classifier KNN (k-nearest neighbour). Experimental results indicated that hierarchical agglomerative clustering (HAC) is highly effective in terms of producing clusters with high prediction accuracy over k-means and k-medoids based clustering. While hierarchical agglomerative clustering (HAC) produced clusters with higher prediction accuracy, the time taken to perform HAC was slightly higher than k-means and k-medoids execution. - Unimodal EEG-Based Emotion Recognition: Addressing Class Imbalance with Supervised Learning Models
Samyak Dasgupta, Stobak Dutta, Amartya Chakraborty, Gitosree Khan
Proceedings 2025 IEEE 3rd International Symposium on Sustainable Energy Signal Processing and Cybersecurity Isssc 2025, 2025
One of the most popular and interesting fields of research in recent years is recognition. Though emotion does not have any formal definition it is emotion that plays a significant role in our day-to-day life. Various internal as well as external factors are there that may cause a change in emotional states. As in this busy world keeping an eye on mental health has become an important point so the identification and recognition of emotional states has also become the need of this hour. So we need to develop some effective methods for proper recognition of emotional states with higher accuracy. There are different methods through which emotion can be recognized as per the state-of-the-art literature. In this study, the authors employed a unimodal framework utilizing EEG signals to recognize emotions within the four quadrants of the valence–arousal space. The research was carried out in two distinct stages. In the first stage, a class-imbalanced dataset was analyzed, followed by the application of techniques to mitigate the imbalance issue. In both stages, various supervised machine learning algorithms were utilized for emotion classification. The outcomes revealed that the Decision Tree (DTree) model exhibited better performance on imbalanced data, while the K-Nearest Neighbour (KNN) algorithm produced higher accuracy with the balanced dataset.. - Leveraging the Commerce Graph for Optimizing Digital Commerce
Subrata Paul, Amartya Chakraborty, Stobak Dutta, Keya Das Ghosh, Anirban Mitra
Procedia Computer Science, 2025
As a dynamic network that links important elements of the commerce ecosystem, including buyers, sellers, products, and transactions, the Commerce Graph is a ground-breaking development in digital commerce. By using advanced centrality metrics, such as degree, betweenness, and closeness, to identify key consumers and products, this study exemplifies its capacity for transformation. The findings show that the most important roles in the network are played by customers with higher centrality ratings (such as IDs 66, 91, and 47) and well-known products (such as IDs 102, 104, and 100). With the top buyers in 2018 displaying noteworthy engagement tendencies, temporal research reveals changing customer behaviours. Additionally, buyer and product clusters are found using community detection employing the Louvain algorithm, allowing segmentation tactics to maximise marketing and consumer engagement. The study offers practical insights that may be used to improve corporate operations and identify targets for customized promotions. This study makes the Commerce Graph an essential tool for tackling issues like scalability and incorporating sophisticated algorithms. - Performance evaluation of a new Kalman filter based peer-to-peer tracking scheme for indoor environment
S. Chattaraj, Amartya Chakraborty, Biplab Das
Internet Technology Letters, 2024
Peer‐to‐peer tracking through smartphone sensor data is in demand due to its usefulness in location‐based services. A person carrying a smartphone device could be tracked by another smartphone through real time signal processing. Due to the distortion of GPS signals in indoor environment, Kalman filter based data fusion techniques are popularly applied to integrate various sensor data. Such an approach suffers failure in the absence of external aiding and thus entails peer tracking only through the smartphone's navigation sensor data. In this context, accurate estimation of heading error between the leaders and followers' trajectory is very much crucial. The present work demonstrates one novel Kalman filter‐based measurement matching approach for accurate estimation of the aforesaid heading error. Less than 1 meter of accuracy in the final position estimation has been achieved through this method which is comparable with other state of the art techniques as reported in literatures. Moreover, the system does not depend on any external aiding which makes it adaptable to any unknown indoor location. - CAGSI: A Classification Approach towards Gait Speed Identification
Amartya Chakraborty, Suvendu Chattaraj
Human Centric Intelligent Systems, 2024
The last few decades have witnessed a remarkable amount of research addressing numerous challenges in the domain of human activity recognition. One popular problem in this domain has been that of gait analysis. A subproblem in this domain is to identify the speed of a mobile object through gait analysis. Apart from clinical diagnostic applications, the detection of the speed of a person is also important in remote health monitoring, tracking of the mentally incompetent, and determining proper ambulatory assistive devices for the orthopaedically impaired. Gait analysis-related problems commonly deal with large volumes of interrelated data for which machine-learning techniques have been proven effective. However, the size of the feature set used in such problems is a crucial factor. The choice of a large feature set may complicate the approach for long-term analysis. The present work addresses the problem of human walking speed classification through the machine learning approach. Data was experimentally collected with the mobile phone sensors carried by volunteers of different physiques. Only the acceleration readings along the three axes of the accelerometer are considered for further experimentation. Although walking speed is a personal trait, four classes of data have been curated, namely, slow walking, moderate walking, fast walking, and sitting. The speeds of the walks were not pre-defined so the volunteers performed the walks as per their own comfort, which enhances the challenge of distinguishing between sensor signals of varying speed. Experiments have been performed using different supervised learning algorithms with only acceleration data. The performance of the learning models has been analyzed with the help of accuracy, precision, recall, f1-score, and the ROC curve in a One-vs-Rest approach. The results demonstrate that the performance of this system for walking speed identification is comparable to state-of-the-art works. Our work has a unique perspective as it uses a primary dataset comprising only three features. - Information spread in opinionated social networks
Amartya Chakraborty, Nandini Mukherjee
ACM International Conference Proceeding Series, 2024
The proposed work develops a framework for opinion-aware network formulation from online topical networks and its subsequent analysis. Novel concepts of opinion class and opinion compatibility are proposed for a context-aware graph-reduce approach. Experiments highlight how the context-sensitive framework enables faster influence maximisation over the network using existing Greedy and CELF models of influence spread. - Context-aware Community Detection in the Russia-Ukraine Conflict Network
Amartya Chakraborty, Deepamoy Pal, Nandini Mukherjee
ACM International Conference Proceeding Series, 2024 - VOiCE: Voter Opinion in Community Exploration - a Case Study of Indian Elections
Amartya Chakraborty, M. Mahabub A. Khoda, Subhankar Naskar, Nandini Mukherjee
2024 IEEE Silchar Subsection Conference Silcon 2024, 2024 - Analysis and mining of an election-based network using large-scale twitter data: a retrospective study
Amartya Chakraborty, Nandini Mukherjee
Social Network Analysis and Mining, 2023 - UltraSense: A non-intrusive approach for human activity identification using heterogeneous ultrasonic sensor grid for smart home environment
Arindam Ghosh, Amartya Chakraborty, Dhruv Chakraborty, Mousumi Saha, Sujoy Saha
Journal of Ambient Intelligence and Humanized Computing, 2023 - A Multi-modal Approach for Emotion Recognition Through the Quadrants of Valence–Arousal Plane
Stobak Dutta, Brojo Kishore Mishra, Anirban Mitra, Amartya Chakraborty
SN Computer Science, 2023 - A deep-CNN based low-cost, multi-modal sensing system for efficient walking activity identification
Amartya Chakraborty, Nandini Mukherjee
Multimedia Tools and Applications, 2023 - How the ‘Things’ Speak: The Usage and Applications of Sensors in IoT
Amartya Chakraborty
Intelligent Systems for Ioe Based Smart Cities, 2023 - A narrative review on the characterisation of automated human emotion detection systems using biomedical sensors and machine intelligence
Stobak Dutta, Brojo Kishore Mishra, Anirban Mitra, Amartya Chakraborty
International Journal of Reasoning Based Intelligent Systems, 2023 - MATRA: An Automated System for MATernal Risk Assessment
Amartya Chakraborty, Stobak Dutta, Ankur Biswas, Prasenjit Das, Surendra Nath Bhagat, Subhankar Guha
Smart Innovation Systems and Technologies, 2023 - On Identifying Communities in Online Hate Speech
Ayusha Burman, Shaswata Karan, Shreya Mallik, Drishti Majee, Mayukh Bal, Sumit Anand, Amartya Chakraborty
2023 International Conference on New Frontiers in Communication Automation Management and Security Iccams 2023, 2023 - Application of machine intelligence in IoT enabled healthcare monitoring systems: A case study based approach
Smart and Secure Internet of Healthcare Things, 2022 - Correction to: HumanSense: a framework for collective human activity identification using heterogeneous sensor grid in multi-inhabitant smart environments (Personal and Ubiquitous Computing, (2022), 26, 3, (521-540), 10.1007/s00779-020-01402-6)
Arindam Ghosh, Amartya Chakraborty, Joydeep Kumbhakar, Mousumi Saha, Sujoy Saha
Personal and Ubiquitous Computing, 2022 - HumanSense: a framework for collective human activity identification using heterogeneous sensor grid in multi-inhabitant smart environments
Arindam Ghosh, Amartya Chakraborty, Joydeep Kumbhakar, Mousumi Saha, Sujoy Saha
Personal and Ubiquitous Computing, 2022 - A Low-Cost IMU-Based Wearable System for Precise Identification of Walk Activity Using Deep Convolutional Neural Network
Amartya Chakraborty, Nandini Mukherjee
Studies in Computational Intelligence, 2022 - A Novel Centrality-based Measure for Election Network Analysis
Amartya Chakraborty, Nikhil Badyal, Aman Sharma, Nandini Mukherjee
Proceedings 2022 IEEE Silchar Subsection Conference Silcon 2022, 2022 - An Analysis of Emotion Recognition Based on GSR Signal
Stobak Dutta, Brojo Kishore Mishra, Anirban Mitra, Amartya Chakraborty
Ecs Transactions, 2022 - A robust approach for effective spam detection using supervised learning techniques
Amartya Chakraborty, Suvendu Chattaraj, Sangita Karmakar, Shillpi Mishrra
Machine Learning Techniques and Analytics for Cloud Security, 2021 - On Exploring the Role of Feature Processing in Gait-based Gender Identification
Amartya Chakraborty, Stobak Dutta, Surendra Nath Bhagat, Subhankar Guha, Ankur Biswas, Parnava Roy
Proceedings 2021 19th Oits International Conference on Information Technology Ocit 2021, 2021 - Around the world in 60 days: an exploratory study of impact of COVID-19 on online global news sentiment
Amartya Chakraborty, Sunanda Bose
Journal of Computational Social Science, 2020 - Global Positioning System Based Automated Railway Level Crossing
Shankha Banerjee, Sayan Mondal, Amartya Chakraborty, Suvendu Chattaraj
2020 International Conference on Computer Electrical and Communication Engineering Iccece 2020, 2020 - On automatizing recognition of multiple human activities using ultrasonic sensor grid
Arindam Ghosh, Anubrata Sanyal, Amartya Chakraborty, Praveen Kumar Sharma, Mousumi Saha, Subrata Nandi, Sujoy Saha
2017 9th International Conference on Communication Systems and Networks Comsnets 2017, 2017
RECENT SCHOLAR PUBLICATIONS
- Heart Disease Prediction: A Clustering-Based Clinical Decision Support Approach
R Mukherjee, A Chakraborty, S Sen, S Naskar
Machine Learning in Biomedical and Health Informatics, 43-54 , 2025
2025
Citations: 1 - Topic and opinion infused hypergraphs for influence maximization
A Chakraborty, N Mukherjee
Physics Letters A 545, 130507 , 2025
2025
Citations: 3 - Leveraging the Commerce Graph for Optimizing Digital Commerce
S Paul, A Chakraborty, S Dutta, KD Ghosh, A Mitra
Procedia Computer Science 259, 1072-1081 , 2025
2025
Citations: 1 - VOiCE: Voter Opinion in Community Exploration-a Case Study of Indian Elections
A Chakraborty, MMA Khoda, S Naskar, N Mukherjee
2024 IEEE Silchar Subsection Conference (SILCON 2024), 1-6 , 2024
2024 - Performance evaluation of a new Kalman filter based peer‐to‐peer tracking scheme for indoor environment
S Chattaraj, A Chakraborty, B Das
Internet Technology Letters 7 (6), e529 , 2024
2024 - CAGSI: A Classification Approach towards Gait Speed Identification
A Chakraborty, S Chattaraj
Human-Centric Intelligent Systems 4 (1), 161-170 , 2024
2024
Citations: 1 - Context-aware Community Detection in the Russia-Ukraine Conflict Network
A Chakraborty, D Pal, N Mukherjee
Proceedings of the 25th International Conference on Distributed Computing … , 2024
2024
Citations: 1 - Information spread in opinionated social networks
A Chakraborty, N Mukherjee
Proceedings of the 7th Joint International Conference on Data Science … , 2024
2024
Citations: 3 - Proposed Model for Emotion Recognition Using Physiological Signal
S Dutta, BK Mishra, A Mitra, A Chakraborty
Available at SSRN 4667544 , 2023
2023 - On Identifying Communities in Online Hate Speech
A Burman, S Karan, S Mallik, D Majee, M Bal, S Anand, A Chakraborty
2023 International Conference on New Frontiers in Communication, Automation … , 2023
2023 - A Multi-modal Approach for Emotion Recognition Through the Quadrants of Valence–Arousal Plane
S Dutta, BK Mishra, A Mitra, A Chakraborty
SN Computer Science 4 (5), 460 , 2023
2023
Citations: 7 - A deep-CNN based low-cost, multi-modal sensing system for efficient walking activity identification
A Chakraborty, N Mukherjee
Multimedia Tools and Applications 82 (11), 16741-16766 , 2023
2023
Citations: 17 - Analysis and mining of an election-based network using large-scale twitter data: a retrospective study
A Chakraborty, N Mukherjee
Social Network Analysis and Mining 13 (1), 74 , 2023
2023
Citations: 14 - A narrative review on the characterisation of automated human emotion detection systems using biomedical sensors and machine intelligence
S Dutta, BK Mishra, A Mitra, A Chakraborty
International Journal of Reasoning-based Intelligent Systems 15 (3-4), 266-276 , 2023
2023 - How the ‘Things’ Speak: The Usage and Applications of Sensors in IoT
A Chakraborty
Intelligent Systems for IoE Based Smart Cities 1, 190-212 (23) , 2023
2023 - Application of Machine Intelligence in IoT-Enabled Healthcare Monitoring Systems: A Case Study-Based Approach
A Chakraborty, S Adhikary, A Ghosh, PS Paul
Smart and Secure Internet of Healthcare Things, 49-70 , 2022
2022
Citations: 5 - MATRA: An Automated System for MATernal Risk Assessment
A Chakraborty, S Dutta, A Biswas, P Das, SN Bhagat, S Guha
Human-Centric Smart Computing: Proceedings of ICHCSC 2022, 183-189 , 2022
2022
Citations: 1 - A Novel Centrality-based Measure for Election Network Analysis
A Chakraborty, N Badyal, A Sharma, N Mukherjee
2022 IEEE Silchar Subsection Conference (SILCON), 1-6 , 2022
2022
Citations: 3 - An analysis of emotion recognition based on GSR signal
S Dutta, BK Mishra, A Mitra, A Chakraborty
Electrochemical Society Transactions 107 (1), 12535-12542 , 2022
2022
Citations: 42 - On Analyzing the Twitter Usage and Sentiment in India During the Second Wave of COVID-19
A Chakraborty, A Iqbal, S Guha, SN Bhagat, S Dutta, P Roy, A Biswas
Applications of Machine Intelligence in Engineering, 499-509 , 2022
2022
Citations: 2
MOST CITED SCHOLAR PUBLICATIONS
- UltraSense: A non-intrusive approach for human activity identification using heterogeneous ultrasonic sensor grid for smart home environment
A Ghosh, A Chakraborty, D Chakraborty, M Saha, S Saha
Journal of Ambient Intelligence and Humanized Computing, 1-22 , 2019
2019
Citations: 43 - An analysis of emotion recognition based on GSR signal
S Dutta, BK Mishra, A Mitra, A Chakraborty
Electrochemical Society Transactions 107 (1), 12535-12542 , 2022
2022
Citations: 42 - Around the world in 60 days: an exploratory study of impact of COVID-19 on online global news sentiment
A Chakraborty, S Bose
Journal of Computational Social Science 3 (2), 367 - 400 , 2020
2020
Citations: 39 - On automatizing recognition of multiple human activities using ultrasonic sensor grid
A Ghosh, A Sanyal, A Chakraborty, PK Sharma, M Saha, S Nandi, S Saha
2017 9th International Conference on Communication Systems and Networks … , 2017
2017
Citations: 38 - A deep-CNN based low-cost, multi-modal sensing system for efficient walking activity identification
A Chakraborty, N Mukherjee
Multimedia Tools and Applications 82 (11), 16741-16766 , 2023
2023
Citations: 17 - Analysis and mining of an election-based network using large-scale twitter data: a retrospective study
A Chakraborty, N Mukherjee
Social Network Analysis and Mining 13 (1), 74 , 2023
2023
Citations: 14 - Global Positioning System Based Automated Railway Level Crossing
S Banerjee, S Mondal, A Chakraborty, S Chattaraj
2020 International Conference on Computer, Electrical & Communication … , 2020
2020
Citations: 10 - HumanSense: a framework for collective human activity identification using heterogeneous sensor grid in multi-inhabitant smart environments
A Ghosh, A Chakraborty, J Kumbhakar, M Saha, S Saha
2020
Citations: 10 - A Multi-modal Approach for Emotion Recognition Through the Quadrants of Valence–Arousal Plane
S Dutta, BK Mishra, A Mitra, A Chakraborty
SN Computer Science 4 (5), 460 , 2023
2023
Citations: 7 - Application of Machine Intelligence in IoT-Enabled Healthcare Monitoring Systems: A Case Study-Based Approach
A Chakraborty, S Adhikary, A Ghosh, PS Paul
Smart and Secure Internet of Healthcare Things, 49-70 , 2022
2022
Citations: 5 - Topic and opinion infused hypergraphs for influence maximization
A Chakraborty, N Mukherjee
Physics Letters A 545, 130507 , 2025
2025
Citations: 3 - Information spread in opinionated social networks
A Chakraborty, N Mukherjee
Proceedings of the 7th Joint International Conference on Data Science … , 2024
2024
Citations: 3 - A Novel Centrality-based Measure for Election Network Analysis
A Chakraborty, N Badyal, A Sharma, N Mukherjee
2022 IEEE Silchar Subsection Conference (SILCON), 1-6 , 2022
2022
Citations: 3 - A Robust Approach for Effective Spam Detection Using Supervised Learning Techniques
A Chakraborty, S Chattaraj, S Karmakar, S Mishrra
Machine Learning Techniques and Analytics for Cloud Security, 171 , 2021
2021
Citations: 3 - Machine learning based Indian spam recognition
A Chakraborty, S Karmakar, S Chattaraj
TTIC 3, 10-16 , 2019
2019
Citations: 3 - On Analyzing the Twitter Usage and Sentiment in India During the Second Wave of COVID-19
A Chakraborty, A Iqbal, S Guha, SN Bhagat, S Dutta, P Roy, A Biswas
Applications of Machine Intelligence in Engineering, 499-509 , 2022
2022
Citations: 2 - A Low-Cost IMU-Based Wearable System for Precise Identification of Walk Activity Using Deep Convolutional Neural Network
A Chakraborty, N Mukherjee
Big Data Intelligence for Smart Applications, 117-140 , 2022
2022
Citations: 2 - Heart Disease Prediction: A Clustering-Based Clinical Decision Support Approach
R Mukherjee, A Chakraborty, S Sen, S Naskar
Machine Learning in Biomedical and Health Informatics, 43-54 , 2025
2025
Citations: 1 - Leveraging the Commerce Graph for Optimizing Digital Commerce
S Paul, A Chakraborty, S Dutta, KD Ghosh, A Mitra
Procedia Computer Science 259, 1072-1081 , 2025
2025
Citations: 1 - CAGSI: A Classification Approach towards Gait Speed Identification
A Chakraborty, S Chattaraj
Human-Centric Intelligent Systems 4 (1), 161-170 , 2024
2024
Citations: 1
