Hemanta Kumar Bhuyan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hemanta Kumar Bhuyan has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Vinayakumar Ravi
Prince Mohammad Bin Fahd University
10 shared publications Biswajit Brahma
McKesson Corporation
6 shared publications- Subhendu Kumar Pani
Krupajal Computer Academy, Biju Patnaik University of Technology, Bhubaneswar, India
5 shared publications - Biswajit Brahma
McKesson Corporation, 32559 Lake Bridgeport St, Fremont, CA 94555, USA
4 shared publications - Chinmay Chakraborty
Centre of Innovation and Research (COIR) in Medical Technology, KIIT Deemed to be University, Bhubaneswar, Odisha, India
4 shared publications - E. Laxmi Lydia
VR Siddhartha Engineering College(A), Siddhartha Academy of Higher Education (Deemed to be University)
4 shared publications
Latest Publications
- 1 November 2025
- Published by Springer Nature
- p. 479-496
Assessment of Freezing and Unfreezing Approach in VGG Model for Breast Cancer Detection
- 1 November 2025
- Published by Springer Nature
- p. 479-496
Assessment of Freezing and Unfreezing Approach in VGG Model for Breast Cancer Detection
- 1 November 2025
- Published by Springer Nature
- p. 945-960
Lung Cancer Detection Using Hyperparameter Techniques in Machine Learning Model
- 1 November 2025
- Published by Springer Nature
- p. 945-960
Lung Cancer Detection Using Hyperparameter Techniques in Machine Learning Model
- 1 November 2025
- Published by Springer Nature
- p. 859-875
Liver Disease Analysis Using Hyperparameter Optimization Methods in Machine Learning Model
- 1 November 2025
- Published by Springer Nature
- p. 859-875
Liver Disease Analysis Using Hyperparameter Optimization Methods in Machine Learning Model
- Open Access
- 30 June 2025
- Published by International Information and Engineering Technology Association in Traitement du Signal
- Vol. 42 (3) , 1353-1365
Mel-Spectrograms Based LSTM Model for Speech Emotion Recognition
- 30 June 2025
- Published by International Information and Engineering Technology Association in Traitement du Signal
- Vol. 42 (3) , 1353-1365
Open AccessMel-Spectrograms Based LSTM Model for Speech Emotion Recognition
- 1 January 2025
- Published by American Scientific Publishing Group (ASPG) LLC in Journal of Intelligent Systems and Internet of Things
- Vol. 16 (1) , 28-8-40
Leveraging Marine Predators Algorithm with Deep Learning Object Detection for Accurate and Efficient Detection of Pedestrians
American scientific publishing group
- 1 January 2025
- Published by American Scientific Publishing Group (ASPG) LLC in Journal of Intelligent Systems and Internet of Things
- Vol. 16 (1) , 28-8-40
Leveraging Marine Predators Algorithm with Deep Learning Object Detection for Accurate and Efficient Detection of Pedestrians
American scientific publishing group
- Open Access
- 30 December 2024
- Published by Green Publication
- Vol. 27 (4S) , 10506-10513
Convolutional methods for LungDisease DetectionUsing Deep Learning Model
The majority of illnesses are caused by alterations in the environment and food, as well as problems with the body's internal processes. For instance, pneumonia presents serious dangers to public health and can cause lung disorders as a result of lung infection. Accurately and promptly diagnosing lung infections is essential to saving lives. In order to address the aforementioned challenges with a variety of performance evaluations, a deep learning model utilizing several approaches (such as CNN, ResNet) is proposed to find out lung infection in human body. Specifically, our proposed model is thought to be evaluated for pneumonia. As a result, several sets of Chest X-ray (CXR) image data for pneumonia are taken into consideration for testing. The aforementioned dataset is used to illustrate the experiment, and the suggested techniques are used to assess it using certain evaluation measures. Comparative performance study shows that our suggested approaches perform noticeably better than current processes. According to the experiment, ResNet did well in terms of validation accuracy (64.69%), whereas CNN did well in terms of training accuracy (86.47%).
- 30 December 2024
- Published by Green Publication
- Vol. 27 (4S) , 10506-10513
Open AccessConvolutional methods for LungDisease DetectionUsing Deep Learning Model
The majority of illnesses are caused by alterations in the environment and food, as well as problems with the body's internal processes. For instance, pneumonia presents serious dangers to public health and can cause lung disorders as a result of lung infection. Accurately and promptly diagnosing lung infections is essential to saving lives. In order to address the aforementioned challenges with a variety of performance evaluations, a deep learning model utilizing several approaches (such as CNN, ResNet) is proposed to find out lung infection in human body. Specifically, our proposed model is thought to be evaluated for pneumonia. As a result, several sets of Chest X-ray (CXR) image data for pneumonia are taken into consideration for testing. The aforementioned dataset is used to illustrate the experiment, and the suggested techniques are used to assess it using certain evaluation measures. Comparative performance study shows that our suggested approaches perform noticeably better than current processes. According to the experiment, ResNet did well in terms of validation accuracy (64.69%), whereas CNN did well in terms of training accuracy (86.47%).
- Open Access
- 29 December 2024
- Published by Green Publication
- Vol. 27 (4S) , 10548-10556
Ensemble Model Based Disease Analysis in Healthcare System
Due to rising rates of illness and death brought on by changes in the environment and food supply, healthcare disease is a serious threat to human existence. Accurate diagnosis and prediction are essential for many healthcare alerts, including prevention, early detection, and treatment. With the use of various technology tools, medical personnel need more accurately monitor, predict, and diagnose disease problems. However, the majority of prediction models just identify if people are sick and seldom go on to assess how serious the sickness is happened. In this work, we suggested a machine learning-based model for cardiac issue prediction that can simultaneously manage complicated and binary classifications. Machine learning techniques like Random Forest, K-Nearest Neighbours (KNN), and logistic regression are often used in data processing, and they have all shown promise in the prediction of cardiac disease. Additionally, we used the aforementioned techniques to create the ensemble model, illustrate the associated experiments, and contrast them with conventional techniques. According to assessment measures, the ensemble model performs exceptionally well. According to our experiment, SVM + RF performed better than other approaches and achieved 98% accuracy.
- 29 December 2024
- Published by Green Publication
- Vol. 27 (4S) , 10548-10556
Open AccessEnsemble Model Based Disease Analysis in Healthcare System
Due to rising rates of illness and death brought on by changes in the environment and food supply, healthcare disease is a serious threat to human existence. Accurate diagnosis and prediction are essential for many healthcare alerts, including prevention, early detection, and treatment. With the use of various technology tools, medical personnel need more accurately monitor, predict, and diagnose disease problems. However, the majority of prediction models just identify if people are sick and seldom go on to assess how serious the sickness is happened. In this work, we suggested a machine learning-based model for cardiac issue prediction that can simultaneously manage complicated and binary classifications. Machine learning techniques like Random Forest, K-Nearest Neighbours (KNN), and logistic regression are often used in data processing, and they have all shown promise in the prediction of cardiac disease. Additionally, we used the aforementioned techniques to create the ensemble model, illustrate the associated experiments, and contrast them with conventional techniques. According to assessment measures, the ensemble model performs exceptionally well. According to our experiment, SVM + RF performed better than other approaches and achieved 98% accuracy.
- 27 December 2024
- Published by World Scientific Pub Co Pte Ltd in Journal of Information & Knowledge Management
- Vol. 24 (01)
Mutual Information-Based Generalisation Gap Analysis Using Deep Learning Model
Most deep learning models face difficulties in analysing image information due to the concept of information bottlenecks and their corresponding methodologies. But, the information bottleneck is used for discarding redundant data and trying to maximise in favour of data directly relevant to the task-oriented information. However, managing information bottlenecks is challenging in the learning model process. Although convolutional neural networks are designed for small-scale processing, their inductive bias makes it difficult to learn contextual features. Thus, we have considered the theoretical learning model to justify the advantages of information bottleneck in deep learning model. We tried to use a fundamental information bottleneck in the vision transformer model. The channel density module cleans up task-related data, while the collected image representations are encouraged to be diverse through local connections in cumulative local transformer blocks. We considered the encoder and decoder methods that analyse the information bottleneck techniques in the deep learning model. This paper presents a rigorous learning theory that mathematically links information bottlenecks for generalisation errors, demonstrating the usefulness of information bottlenecks in deep learning. Our approach suggests that limiting information bottlenecks is crucial for managing errors in deep learning techniques. We conducted experiments across various mathematical models and learning environments to test the validity of our new mathematical insights. In many cases, generalisation errors correspond to unwanted information at hidden levels. We have considered boundary approaches using various scaling parameters and dimensions for the degree of information bottleneck. As per the estimation loss and error by different correlation approaches using generalisation gap methods, we found Spearman correlation having loss (0.86) and error (0.758), whereas Pearson correlation having loss (0.85) and error (0.76), respectively. We also considered outputs for model compression metrics and analysed them through comparative performance.
- 27 December 2024
- Published by World Scientific Pub Co Pte Ltd in Journal of Information & Knowledge Management
- Vol. 24 (01)
Mutual Information-Based Generalisation Gap Analysis Using Deep Learning Model
Most deep learning models face difficulties in analysing image information due to the concept of information bottlenecks and their corresponding methodologies. But, the information bottleneck is used for discarding redundant data and trying to maximise in favour of data directly relevant to the task-oriented information. However, managing information bottlenecks is challenging in the learning model process. Although convolutional neural networks are designed for small-scale processing, their inductive bias makes it difficult to learn contextual features. Thus, we have considered the theoretical learning model to justify the advantages of information bottleneck in deep learning model. We tried to use a fundamental information bottleneck in the vision transformer model. The channel density module cleans up task-related data, while the collected image representations are encouraged to be diverse through local connections in cumulative local transformer blocks. We considered the encoder and decoder methods that analyse the information bottleneck techniques in the deep learning model. This paper presents a rigorous learning theory that mathematically links information bottlenecks for generalisation errors, demonstrating the usefulness of information bottlenecks in deep learning. Our approach suggests that limiting information bottlenecks is crucial for managing errors in deep learning techniques. We conducted experiments across various mathematical models and learning environments to test the validity of our new mathematical insights. In many cases, generalisation errors correspond to unwanted information at hidden levels. We have considered boundary approaches using various scaling parameters and dimensions for the degree of information bottleneck. As per the estimation loss and error by different correlation approaches using generalisation gap methods, we found Spearman correlation having loss (0.86) and error (0.758), whereas Pearson correlation having loss (0.85) and error (0.76), respectively. We also considered outputs for model compression metrics and analysed them through comparative performance.
- 9 October 2024
- Published by Springer Nature
- p. 13-28
Development of a Hybrid Deep Learning Model for Car Crash Prediction Using Driver’s Behavioral Pattern
- 9 October 2024
- Published by Springer Nature
- p. 13-28
Development of a Hybrid Deep Learning Model for Car Crash Prediction Using Driver’s Behavioral Pattern