Light weight encryption technique: a cellular automaton based approach for securing health records Shamama Anwar, Prashant Pranav, Supreeti Kamilya Scientific Reports, 2025 Digitization has led to enormous data generation that needs to be maintained and shared regularly across different platforms. The healthcare industry strives on this enormous data sharing as it forms the backbone of the industry. But such large platforms always face security concerns in terms of privacy preservation and unauthorized access. To overcome this, a robust encryption mechanism is needed to ensure smooth sharing facility but another consideration is the complexity involved in the encryption process. Although many encryption techniques exist, the need of the present situation is to shift to light weight encryption techniques to facilitate quick and efficient data protection schemes. The paper introduces an ultra light weight encryption technique based on the PRESENT algorithm coupled with cellular automaton to provide an added benefit in key generation. The algorithm has been tested on some benchmark tests like the NIST test suite and Diehard test to show its efficacy.
Predictive Modelling of cardiovascular Disease Survival Using Mutual Information and Machine Learning Across Varying Sample Sizes Vijayalakshmi. Sarraju, Jaya Pal, Supreeti. Kamilya International Journal of Basic and Applied Sciences, 2025 In clinical data analytics, predicting survival outcomes for cardiovascular disease (CVD) is a challenging task with practical implications. Using three different datasets, this study investigates how sample size affects machine learning performance and generalizability. The methodology combines statistical sample-size analysis with mutual information gain, a filter-based, scalable, and domain-agnostic feature selection strategy, to identify clinically essential features. Mutual information gain measures the dependency between each predictor and the target variable, ensuring computational efficiency and applicability to large-scale data. Machine learning classifiers, support vector machines (SVMs) and logistic regression (LR), are employed to assess predictive performance across varying population sizes. Experimental results demonstrate that increasing the sample size improves model accuracy by up to 10%, recall by 5–8%, and maintains consistent specificity. Furthermore, to enhance clinical reliability, the models are evaluated using the Area Under the Receiver Operating Characteristic Curve (AUC-ROC), where SVM achieved an AUC of 0.965 and LR achieved 0.937, validating strong discriminatory power; Also, SHAP-based feature attribution is used to improve interpretability, identifying that larger sample sizes provide more stable and clinically meaningful explanations.
EchoCNN-Denoiser: a reservoir computing inspired deep learning model for enhanced synthetic aperture radar image despeckling Swarna Aishwarya Twinkle, Supreeti Kamilya, Jit Mukherjee Journal of Applied Remote Sensing, 2025 The occurrence of speckle noise in synthetic aperture radar (SAR) images significantly impacts the accurate extraction of essential information for remote sensing applications. To address this issue, a denoising model, named EchoCNN-Denoiser, is proposed that utilizes the combined strengths of convolutional neural networks (CNN) and reservoir computing (RC) to effectively minimize speckle noise and improve the quality of SAR images. RC offers a method that employs the temporal processing capabilities of recurrent neural network (RNN) without the complexity of training them. We utilized CNN for spatial feature extraction from SAR images, and echo state network (ESN), a concept of RC, is utilized for capturing temporal dependencies, resulting in a robust framework for SAR image denoising. CNN extracts hierarchical features using convolution and pooling operations and the ESN transforms these features into a higher-dimensional space through a sparsely connected reservoir. To optimize performance, the reservoir-to-output weights are trained with parameters such as spectral radius, input scaling, and sparsity. Through extensive experiments on real and virtual SAR datasets, the proposed technique demonstrates superior performance in noise reduction compared with existing methods. The model is also validated using multiple evaluation techniques. Initially, our model is compared against traditional filters and other deep learning denoising methods to evaluate its relative performance which is tested using image quality metrics such as peak signal-to-noise ratio, structural similarity index measure, equivalent number of looks, perception-based image quality evaluator and blind/referenceless image spatial quality evaluator, and perceptual index, achieving scores of 30.01, 0.90, 9.48, 27.22, 41.65, and 34.44, respectively. Following that, layer-wise relevance propagation (LRP) is applied to gain a deeper understanding of the model predictions. The heatmaps obtained from LRP visualization confirm that EchoCNN-Denoiser effectively preserves essential image structures while reducing noise. Further, a paired t-test is conducted to statistically assess the effectiveness of the model. Finally, an ablation study is performed to evaluate the contribution of each component to the overall performance of the model. These validations demonstrate the effectiveness of EchoCNN-Denoiser in producing high-quality, despeckled SAR images. As noise reduction is the primary step of SAR image processing, the proposed technique has several applications in remote sensing, by significantly enhancing the SAR image quality.
IoT-Enabled Methane Monitoring and LSTM-Based Forecasting System for Enhanced Safety in Underground Coal Mining Soumyadeep Paty, Arindam Biswas, Sonia Djebali, Guillaume Guerard, Supreeti Kamilya ACM Transactions on Internet of Things, 2025 Ensuring safety in the mining industry is a critical concern for a nation's industrial advancement. Industry 4.0, characterized by the integration of advanced technologies, is at the forefront of efforts to enhance mining practices. Coal seams contain a range of hydrocarbon gases, predominantly methane, which is released in significant quantities during mining operations. Effectively mitigating methane emissions is imperative. The inclusion of methane forecasting allows for the early identification of potential methane emissions, hence resulting in significance enhancement in mine safety. The research work is focused on real-time remote monitoring and cloud-based forecasting of methane levels in underground coal mines. An Industrial Internet of Things (IIoT) device is developed for data acquisition in underground coal mines, capturing essential parameters such as methane concentration, temperature, and humidity. The collected data are utilized to train a long short-term memory based multivariate forecasting model. The trained model is subsequently deployed in the cloud. The experiment is performed in a mine of Eastern Coalfields Limited, India. After the deployment of the proposed model, the developed IIoT device transmits real-time data, obtained from the mine, to the cloud. Based on the real-time data, our model conducts methane forecasting and communicates results back to the IIoT device. The device issues immediate alerts when methane levels surpass predefined thresholds. This ensures enhanced safety in mining operations by providing warnings for both current and forecasted methane concentrations. The forecasted methane concentrations, along with real-time data, are accessible through mobile applications and a web-based dashboard. The accuracy of the proposed model is measured by mean absolute error, mean absolute percentage error, and root mean square error, which demonstrate values of 156.95 ppm, 4.23%, and 191.53 ppm, respectively. A comparative study is performed where our model is evaluated against the multivariate multilayer perceptron, vector autoregression, and auto-regressive integrated moving average models. The comparative study demonstrates that our developed model outperforms the others, showing superior results.
Assessing Cognitive Load Levels via TAR-Based EEG Analysis and Machine Learning Models Md Riyaz Ansari, Supreeti Kamilya, Shamama Anwar Conference Proceedings 2025 IEEE Silchar Subsection Conference IEEE Silcon 2025, 2025 Cognitive load (CL) refers to the mental effort placed on working memory while processing, understanding, and carrying out a task. Assessing the level of cognitive load is crucial for ensuring effective learning, safe performance, and adaptive system design. The present work detects the level of cognitive load (high, medium and low) using electroencephalogram (EEG) signals through a machine learning approach. The EEG dataset, obtained from the publicly available PhysioNet EEGMAT database, includes recordings from 36 healthy individuals performing a mental arithmetic task involving serial subtraction. The EEG signals undergo preprocessing using Independent Component Analysis (ICA) for artifact removal, Z-score normalization for standardization, and feature extraction through Welch’s method to calculate power spectral density (PSD) across different frequency bands. The study computes Theta/Alpha Ratio (TAR) to label cognitive load into three categories: low, medium, and high. The classification models include Logistic Regression (LR) and Support Vector Machines (SVM) with linear, RBF, polynomial, and sigmoid kernels. The study applies stratified 5-fold and 10-fold cross-validation (CV) to evaluate performance. Logistic regression in 10-fold CV achieves the highest classification accuracy of 91.85% while maintaining low CPU execution time. However, SVM with linear and polynomial kernel also provides quite a good accuracy with very low CPU time. These findings demonstrate that combining TAR-based labeling with EEG-derived spectral features and efficient machine learning models enables accurate, interpretable, and real-time classification of cognitive load for Brain–Computer Interface (BCI) applications.
INFERENTIAL STATISTICS-DRIVEN LOGISTIC REGRESSION MODEL FOR CARDIOVASCULAR DISEASE PREDICTION Vijayalakshmi Sarraju International Journal of Applied Mathematics, 2025 Cardiovascular diseases (CVDs) are widely recognisedas primary contributors to global mortality, necessitatingthe development of precise predictive models that provideclear explanations for early detection and facilitate effectiveinterventions. A logistic regression model incorporating inferential statistical methods into the analysis offers a solution for enhanced reliability and interpretability in predicting cardiovascular diseases using clinical data. The analysis employed correlation tests, combined with chi-squaretests and independent t-statistics, to identify key factors,including patient age, blood pressure, cholesterol levels, glucose measures, exercise activity, smoking habits, and alcohol intake. The model generalisation improved significantlyby using the Synthetic Minority Over-sampling Technique(SMOTE) to manage class imbalance problems. The implemented model attained exceptional scores with a 95.2% accuracy rate, 94.8% precision, 96.1% recall, 95.4% F1-score,and 97.2% AUC-ROC. Real-time Medical applications andreliability assessments rely on confusion matrix analysis,ROC curve examination, calibration plots, and feature importance assessment. The training loss curves verified thatconvergence occurred during the training process. The analytical results demonstrate that logistic regression performswell, generating computations that are both clinically usefuland statistically comprehensive, while promoting preventivecardiovascular healthcare
A Deep Learning Technique for Real-Time Detection of Cognitive Load Using Optimal Number of EEG Electrodes Subashis Karmakar, Supreeti Kamilya, Chiranjib Koley, Tandra Pal IEEE Transactions on Instrumentation and Measurement, 2025 Cognitive load analysis has the potential to significantly enhance brain–computer interfaces (BCIs) by enabling adaptive assistance based on the cognitive state of individuals. This article presents a real-time approach for detecting cognitive load through electroencephalogram (EEG) signals, with a focus on optimizing computational resources, such as CPU time, memory, and the number and positioning of EEG electrodes. The study investigates various brain regions, including the prefrontal, frontal, parietal, temporal, and occipital areas, which are critical for identifying cognitive shifts. By leveraging established knowledge of EEG frequency band changes, the research constructs a 2-D brain state image using the Lambert cylindrical equal-area projection and an appropriate interpolation method to represent active brain regions. These 2-D images are then processed by a lightweight convolutional neural network (CNN) designed to distinguish between cognitive and resting states. To validate the proposed model, three EEG datasets were employed: one prepared by the authors through experiments involving 15 healthy subjects and two publicly available datasets. The model achieved an overall accuracy of 95.81% for previously seen subjects and 92.73% for entirely new subjects, utilizing only five electrodes (one prefrontal and four frontal). Furthermore, the model is demonstrated to be suitable for implementation in digital systems with limited computational resources, while maintaining performance and meeting real-time system requirements.
Identification of different types of rocks and ores using cellular automata assisted CNN models: an application of mining Industry S Paty, S Kamilya Natural Computing 25 (1), 14 , 2026 2026
Minimality, transitivity and sensitivity of non-uniform cellular automata S Kamilya, J Kari, K Paturi arXiv preprint arXiv:2605.22762 , 2026 2026
Assessing Cognitive Load Levels via TAR-Based EEG Analysis and Machine Learning Models MR Ansari, S Kamilya, S Anwar 2025 IEEE Silchar Subsection Conference (SILCON), 1-4 , 2025 2025
Light weight encryption technique: a cellular automaton based approach for securing health records: S. Anwar et al. S Anwar, P Pranav, S Kamilya Scientific Reports 15 (1), 23945 , 2025 2025
Cellular Automata Technology: 4th Asian Symposium, ASCAT 2025, Ranchi, India, March 6–8, 2025, Revised Selected Papers S Kamilya, S Das, E Formenti Springer Nature , 2025 2025
Subject-Specific Temporal Analysis of Cognitive Load Using fNIRS: A Machine Learning Approach S Kamilya, H Ritesh, C Shashank Vinod, S Karmakar, T Pal Intelligent Computing-Proceedings of the Computing Conference, 378-392 , 2025 2025
Quantum Dot Cellular Automata: Breaking Barriers in Electronics Circuitry for Tomorrow’s Technologies S Kamilya, S Paty Advances in Quantum Inspired Artificial Intelligence: Techniques and … , 2025 2025 Citations: 1
Circuitry for Tomorrow's Technologies S Kamilya, S Paty Advances in Quantum Inspired Artificial Intelligence: Techniques and … , 2025 2025
EchoCNN-Denoiser: a reservoir computing inspired deep learning model for enhanced synthetic aperture radar image despeckling SA Twinkle, S Kamilya, J Mukherjee Journal of Applied Remote Sensing 19 (2), 026501-026501 , 2025 2025 Citations: 4
Despeckling Images Using Elementary Cellular Automata S Aishwarya Twinkle, S Kamilya, J Mukherjee Asian Symposium on Cellular Automata Technology, 191-202 , 2025 2025
IoT-enabled methane monitoring and LSTM-based forecasting system for enhanced safety in underground coal mining S Paty, A Biswas, S Djebali, G Guerard, S Kamilya ACM Transactions on Internet of Things 6 (1), 1-29 , 2025 2025 Citations: 12
INFERENTIAL STATISTICS-DRIVEN LOGISTIC REGRESSION MODEL FOR CARDIOVASCULAR DISEASE PREDICTION V Sarraju, J Pal, S Kamilya International Journal of Applied Mathematics 38 (4s) , 2025 2025
A Deep Learning Technique for Real-Time Detection of Cognitive Load Using Optimal Number of EEG Electrodes S Karmakar, S Kamilya, C Koley, T Pal IEEE Transactions on Instrumentation and Measurement 74, 1-11 , 2024 2024 Citations: 9
Edge Preserving Multiplicative Noise Removal of SAR Images Through Convolutional Neural Network and Anisotropic Diffusion SA Twinkle, S Kamilya, J Mukherjee 2024 IEEE India Geoscience and Remote Sensing Symposium (InGARSS), 1-4 , 2024 2024 Citations: 1
Impact of Variable Sample Size on the Efficiency of Support Vector Machines in Cardiovascular Disease Detection V Sarraju, J Pal, S Kamilya 2024 Second International Conference on Advances in Information Technology … , 2024 2024
SRS: Gender-based heart disease prediction using stratified random sampling approach V Sarraju, J Pal, S Kamilya AIP Conference Proceedings 3164 (1), 020005 , 2024 2024 Citations: 2
On Elementary Second Order Cellular Automata E Formenti, S Kamilya Asian Symposium on Cellular Automata Technology, 204-218 , 2024 2024 Citations: 1
Rock Image Classification Using CNN Assisted with Pre-processed Cellular Automata-Based Grain Detected Images S Paty, S Kamilya Asian Symposium on Cellular Automata Technology, 153-167 , 2024 2024
Water Informatics: Challenges and Solutions Using State of Art Technologies A Biswas, S Kamilya, SL Peng Springer Verlag, Singapore , 2024 2024 Citations: 1
Water Informatics S Kamilya, A Biswas, SL Peng 2024
MOST CITED SCHOLAR PUBLICATIONS
Real time detection of cognitive load using fNIRS: A deep learning approach S Karmakar, S Kamilya, P Dey, PK Guhathakurta, M Dalui, TK Bera, ... Biomedical Signal Processing and Control 80, 104227 , 2023 2023 Citations: 60
A study of chaos in cellular automata S Kamilya, S Das International Journal of Bifurcation and Chaos 28 (03), 1830008 , 2018 2018 Citations: 26
A study of chaos in non-uniform cellular automata S Kamilya, S Das Communications in Nonlinear Science and Numerical Simulation 76, 116-131 , 2019 2019 Citations: 23
IoT-enabled methane monitoring and LSTM-based forecasting system for enhanced safety in underground coal mining S Paty, A Biswas, S Djebali, G Guerard, S Kamilya ACM Transactions on Internet of Things 6 (1), 1-29 , 2025 2025 Citations: 12
A Deep Learning Technique for Real-Time Detection of Cognitive Load Using Optimal Number of EEG Electrodes S Karmakar, S Kamilya, C Koley, T Pal IEEE Transactions on Instrumentation and Measurement 74, 1-11 , 2024 2024 Citations: 9
Nilpotency and periodic points in non-uniform cellular automata S Kamilya, J Kari Acta Informatica 58 (4), 319-333 , 2021 2021 Citations: 9
SACAs:(Non-uniform) Cellular Automata that Converge to a Single Fixed Point. S Kamilya, S Adak, S Das, BK Sikdar Journal of Cellular Automata 14 , 2019 2019 Citations: 7
EchoCNN-Denoiser: a reservoir computing inspired deep learning model for enhanced synthetic aperture radar image despeckling SA Twinkle, S Kamilya, J Mukherjee Journal of Applied Remote Sensing 19 (2), 026501-026501 , 2025 2025 Citations: 4
Identification of rock images in mining industry: an application of deep learning technique S Paty, S Kamilya International Conference on Advances in Data Science and Computing … , 2022 2022 Citations: 4
SRS: Gender-based heart disease prediction using stratified random sampling approach V Sarraju, J Pal, S Kamilya AIP Conference Proceedings 3164 (1), 020005 , 2024 2024 Citations: 2
A Cellular Automaton-Based Technique for Estimating Mineral Resources. S Paty, S Kamilya Complex Systems 32 (2) , 2023 2023 Citations: 2
A cellular automata-based approach on assessment of thickness of stratified mineral deposits S Paty, S Adak, S Kamilya Asian Symposium on Cellular Automata Technology, 105-114 , 2023 2023 Citations: 2
Grade estimation of mineral resources: an application of cellular automata S Paty, S Kamilya Asian Symposium on Cellular Automata Technology, 45-54 , 2022 2022 Citations: 2
Simulation of Non-uniform Cellular Automata by Classical Cellular Automata and Its Application in Embedded Systems. S Kamilya, S Das, BK Sikdar Journal of Cellular Automata 16 , 2021 2021 Citations: 2
Quantum Dot Cellular Automata: Breaking Barriers in Electronics Circuitry for Tomorrow’s Technologies S Kamilya, S Paty Advances in Quantum Inspired Artificial Intelligence: Techniques and … , 2025 2025 Citations: 1
Edge Preserving Multiplicative Noise Removal of SAR Images Through Convolutional Neural Network and Anisotropic Diffusion SA Twinkle, S Kamilya, J Mukherjee 2024 IEEE India Geoscience and Remote Sensing Symposium (InGARSS), 1-4 , 2024 2024 Citations: 1
On Elementary Second Order Cellular Automata E Formenti, S Kamilya Asian Symposium on Cellular Automata Technology, 204-218 , 2024 2024 Citations: 1
Water Informatics: Challenges and Solutions Using State of Art Technologies A Biswas, S Kamilya, SL Peng Springer Verlag, Singapore , 2024 2024 Citations: 1
Performance Analysis of Supervised Learning Algorithms on Different Applications V Sarraju, J Pal, S Kamilya CS & IT Conference Proceedings 12 (19) , 2022 2022 Citations: 1
Cellular automata: chaos, convergence and unification S Kamilya Ph. D. Thesis, Indian Institute of Engineering Science and Technology … , 2021 2021 Citations: 1
