GSGautam Sarkar

Gautam Sarkar

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Gautam Sarkar has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Multi-descriptor hybrid fusion of deep, latent and handcrafted features for reliable thermal tomographic image classification

    by Chayan Basak, Gautam Sarkar, Palash Kumar Kundu

    Thermal tomographic imaging, driven by sensor-based boundary measurements, provides a powerful non-invasive means for reconstructing internal temperature distributions in thermally driven flow systems, enabling predictive maintenance and quality assurance in industrial environments. However, accurate classification of thermal tomographic images remains challenging due to complex heating patterns and the limited availability of annotated datasets. This article presents a multi-descriptor hybrid feature-fusion framework for thermal tomographic image classification, built upon a ResNet-18 deep transfer learning backbone to extract discriminative representations of spatial temperature fields. To enhance robustness, deep features are fused with stacked autoencoder (SAE)-based latent and handcrafted ‘histogram of oriented gradients’ (HOG) descriptors refined through ‘principal component analysis’ (PCA). Tomographic dataset is synthetically constructed using COMSOL Multiphysics with FEM-based simulations of a contour inside a hot airflow chamber, emulating boundary sensor measurements under diverse heating and airflow conditions. The fused-feature set is evaluated using linear ‘support vector machine’ (SVM), ‘logistic regression’ (LR) and ‘linear discriminant analysis’ (LDA) classifiers. Performance is assessed through stratified five-fold cross-validation and holdout validation using overall accuracy, macro F1-score and Cohen’s kappa. Experimental results demonstrate that the proposed configuration consistently outperforms alternative hybrid variants and individual feature branches, achieving classification accuracies up to 99.05% with strong inter-class agreement. Ablation, ROC-AUC, centroid separability and noise-robustness analyses further confirm the compactness and discriminative power of the fused-feature space. The proposed framework offers a reliable solution for automated detection of heating patterns in thermal tomographic imaging, with strong potential for deployment in industrial condition monitoring and non-destructive evaluation systems.

  • FEATURE-FUSED STACKED AUTOENCODERS FOR ROBUST THERMAL TOMOGRAPHIC IMAGE CLASSIFICATION

    by Chayan Kumar Basak, Gautam Sarkar, Palash Kumar Kundu

    Thermal tomographic imaging is an emerging modality for analyzing internal heat-flow behaviour and identifying localized heating anomalies in complex engineering systems. Classifying such images remains challenging due to their high dimensionality, susceptibility to measurement noise and inadequate availability of annotated datasets. This study develops two lightweight deep feature-learning frameworks based on Stacked Autoencoders (SAE) and a proposed adaptive weighted Multi-Scale Feature-Fused SAE (MSFF-SAE) for robust classification of thermal tomographic images. The SAE captures hierarchical abstractions through progressive compression and reconstruction of input data, supported by sparsity regularization, L2 penalty, a fine-tuned supervised classifier and stochastic noise injection during training. The MSFF-SAE further enhances class separability by fusing multi-level latent features from different encoder depths with the bottleneck representation to preserve both local and global thermal cues. A synthetically generated dataset of 2,070 thermal tomographic images derived from a controlled hot air-flow chamber and COMSOL simulations is used for evaluation. Under a 5-fold cross-validation protocol, adaptive weighted MSFF-SAE achieves a classification accuracy of 97.78 ± 0.93%, outperforming the baseline SAE (96.96 ± 1.45%) with reduced inter-fold variability, indicating stable generalization. Both models exhibit low standard deviation (less than 2%) and macro-averaged ROC-AUC values exceeding 0.99 across folds. The noise-robustness analysis also confirms MSFF-SAE’s superior measurement noise-resilience under increasing Gaussian perturbations. These findings highlight the potential of feature-fused stacked autoencoders as efficient and noise-resilient learners for automated assessment of heating non-uniformities of thermal tomographic images.


  • Real-Time Implementation of Cloud-Based Indoor Illumination Monitoring System

    by Arijit Ghosh, Palash Kumar Kundu, Gautam Sarkar


  • Open Access

    Multi-Scale Feature Pyramid for Detection of Red Lesions in Fundus Images

    by Goutam Kumar Ghorai, Swagata Kundu, Gautam Sarkar, Ashis Kumar Dhara

    IJRTE is a most popular International Journal in Asia in the field Engineering & Technology.

  • Nested U-Net for Segmentation of Red Lesions in Retinal Fundus Images and Sub-image Classification for Removal of False Positives

    by Swagata Kundu, Vikrant Karale, Goutam Ghorai, Gautam Sarkar, Sambuddha Ghosh, Ashis Kumar Dhara

    Diabetic retinopathy is a pathological change of the retina that occurs for long-term diabetes. The patients become symptomatic in advanced stages of diabetic retinopathy resulting in severe non-proliferative diabetic retinopathy or proliferative diabetic retinopathy stages. There is a need of an automated screening tool for the early detection and treatment of patients with diabetic retinopathy. This paper focuses on the segmentation of red lesions using nested U-Net Zhou et al. (Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer, 2018) followed by removal of false positives based on the sub-image classification method. Different sizes of sub-images were studied for the reduction in false positives in the sub-image classification method. The network could capture semantic features and fine details due to dense convolutional blocks connected via skip connections in between down sampling and up sampling paths. False-negative candidates were very few and the sub-image classification network effectively reduced the falsely detected candidates. The proposed framework achieves a sensitivity of \(88.79\%\), precision of \(71.50\%\), and F1-Score of \(79.21\%\) for the DIARETDB1 data set Kalviainen and Uusutalo (Medical Image Understanding and Analysis, Citeseer, 2007). It outperforms the state-of-the-art networks such as U-Net Ronneberger et al. (International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, 2015) and attention U-Net Oktay et al. (Attention u-net: Learning where to look for the pancreas, 2018).


  • Two-Degree-of-Freedom based Model Reference Adaptive Control of Non-minimum Phase System

    by M. Pal, G. Sarkar, R. K. Barai, T. Roy

    This paper presents the design of the Two-Degree-of-Freedom (2DOF) based Model Reference Adaptive Control (MRAC) as a tracking control system for the Non-minimum Phase (NMP) system. Perfect set point tracking is possible by using a cascade-connected inverse and non-inverse transfer function model of the dynamic system. But this method is restricted to the minimum phase system only, whereas, NMP system produces unbounded output response using this inverse model technique. Though, adaptive inverse feed-forward control technique is an effective tracking control system, it also requires an inverse model of the system. To overcome this problem, a novel feed-forward MRAC scheme for the inverse NMP model and the State feedback controller of the non-inverse model has been proposed, and both the controller are decoupled in a 2DOF framework. The feed-forward control technique guaranteed the tracking performance using the Lyapunov stability theory, and the feedback counterpart enhances the steady-state performance of the NMP plant. The robustness of the asymptotic stability as well as tracking performance of the closed-loop NMP system has been ensured by the proposed 2DOF control based MRAC technique. The effectiveness of the proposed control structure initially has been verified by the MATLAB Simulink toolbox and, then the demand has been strengthened by the implementation of the same control logic in the real-time environment using analog simulation with Op-amp based hardware model.


  • Sleep Apnea Diagnosis by DWT-Based Kurtosis, Radar and Histogram Analysis of Electrocardiogram

    by Santanu Chattopadhyay, Gautam Sarkar, Arabinda Das

    Sleep Apnea is a serious breathing disorder that occurs when a person's breathing is interrupted during sleeping. People with sleep Apnea stop breathing repeatedly during their sleep, which means that the brain and rest of the body may not get enough oxygen. If left untreated, sleep Apnea can result in a number of health problems, including high blood pressure, stroke, heart failure, irregular heartbeats, heart attacks, and depression. This paper deals with sleep Apnea assessment by discrete wavelet-transformation-(DWT)-based kurtosis, radar and histogram analysis of electrocardiogram (ECG) signals. ECG signals are de-noised by passing them through well-known Savitzky–Golay FIR filter and then are decomposed at different DWT levels, and kurtosis of approximate and detailed coefficients at different DWT levels is measured. Kurtosis at different levels is compared for a healthy person and Apnea patients. Then, radars are formed by kurtosis and compared. Histogram analysis is done on both ECG signals and obtained kurtosis. The comparative study shows that up to DWT level-4, kurtosis of approximate coefficients of Apnea patients is lower than that of a healthy person. However, kurtosis of the approximate coefficient for Apnea patients is greater than that of a normal person at DWT level-7. Up to level 6, Kurtosis of detailed coefficients for Apnea patients is less than that of a normal person. Radar shapes and histogram peaks of ECG signal and kurtosis are also different between a normal person and Apnea patients. Probability in terms of a “p” value for Kurtosis at optimized DWT levels for Apnea patients has shown satisfactory outcome.