Aminul Islam
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Aminul Islam has a total of 70 co-authors. Here are the top co-authors by number of shared publications:
- Anindya Nag
Department of Computer Science & Engineering Northern University of Business and Technology Khulna Khulna Bangladesh
6 shared publications Abu Sufian
University of Leicester
3 shared publications- Mohammad Abu Tareq Rony
Department of Statistics, Noakhali Science and Technology University, Noakhali, Bangladesh
3 shared publications - Rejwan Bin Sulaiman
Department of Computer Science and Engineering, Northumbria University, London E1 7HT, UK
3 shared publications - Shabbir Ahmed Shuvo
Offenburg University of Applied Sciences Germany
3 shared publications Sm Firoz Ahmed Fahim
American International University Bangladesh,Department of Computer Science Engineering,Dhaka,Bangladesh
3 shared publications
Latest Publications
- Open Access
- 15 July 2025
- Published by MDPI AG in Cardiogenetics
- Vol. 15 (3) , 19
Integrated Deep Learning Framework for Cardiac Risk Stratification and Complication Analysis in Leigh’s Disease
Background: Leigh’s Disease is a rare mitochondrial disorder primarily affecting the central nervous system, with frequent secondary cardiac manifestations such as hypertrophic and dilated cardiomyopathies. Early detection of cardiac complications is crucial for patient management, but manual interpretation of cardiac MRI is labour-intensive and subject to inter-observer variability. Methodology: We propose an integrated deep learning framework using cardiac MRI to automate the detection of cardiac abnormalities associated with Leigh’s Disease. Four CNN architectures—Inceptionv3, a custom 3-layer CNN, DenseNet169, and EfficientNetB2—were trained on preprocessed MRI data (224 × 224 pixels), including left ventricular segmentation, contrast enhancement, and gamma correction. Morphological features (area, aspect ratio, and extent) were also extracted to aid interpretability. Results: EfficientNetB2 achieved the highest test accuracy (99.2%) and generalization performance, followed by DenseNet169 (98.4%), 3-layer CNN (95.6%), and InceptionV3 (94.2%). Statistical morphological analysis revealed significant differences in cardiac structure between Leigh’s and non-Leigh’s cases, particularly in area (212,097 vs. 2247 pixels) and extent (0.995 vs. 0.183). The framework was validated using ROC (AUC = 1.00), Brier Score (0.000), and cross-validation (mean sensitivity = 1.000, std = 0.000). Feature embedding visualisation using PCA, t-SNE, and UMAP confirmed class separability. Grad-CAM heatmaps localised relevant myocardial regions, supporting model interpretability. Conclusions: Our deep learning-based framework demonstrated high diagnostic accuracy and interpretability in detecting Leigh’s disease-related cardiac complications. Integrating morphological analysis and explainable AI provides a robust and scalable tool for early-stage detection and clinical decision support in rare diseases.
- 15 July 2025
- Published by MDPI AG in Cardiogenetics
- Vol. 15 (3) , 19
Open AccessIntegrated Deep Learning Framework for Cardiac Risk Stratification and Complication Analysis in Leigh’s Disease
Background: Leigh’s Disease is a rare mitochondrial disorder primarily affecting the central nervous system, with frequent secondary cardiac manifestations such as hypertrophic and dilated cardiomyopathies. Early detection of cardiac complications is crucial for patient management, but manual interpretation of cardiac MRI is labour-intensive and subject to inter-observer variability. Methodology: We propose an integrated deep learning framework using cardiac MRI to automate the detection of cardiac abnormalities associated with Leigh’s Disease. Four CNN architectures—Inceptionv3, a custom 3-layer CNN, DenseNet169, and EfficientNetB2—were trained on preprocessed MRI data (224 × 224 pixels), including left ventricular segmentation, contrast enhancement, and gamma correction. Morphological features (area, aspect ratio, and extent) were also extracted to aid interpretability. Results: EfficientNetB2 achieved the highest test accuracy (99.2%) and generalization performance, followed by DenseNet169 (98.4%), 3-layer CNN (95.6%), and InceptionV3 (94.2%). Statistical morphological analysis revealed significant differences in cardiac structure between Leigh’s and non-Leigh’s cases, particularly in area (212,097 vs. 2247 pixels) and extent (0.995 vs. 0.183). The framework was validated using ROC (AUC = 1.00), Brier Score (0.000), and cross-validation (mean sensitivity = 1.000, std = 0.000). Feature embedding visualisation using PCA, t-SNE, and UMAP confirmed class separability. Grad-CAM heatmaps localised relevant myocardial regions, supporting model interpretability. Conclusions: Our deep learning-based framework demonstrated high diagnostic accuracy and interpretability in detecting Leigh’s disease-related cardiac complications. Integrating morphological analysis and explainable AI provides a robust and scalable tool for early-stage detection and clinical decision support in rare diseases.
- 3 May 2025
- Published by Springer Nature
- p. 341-359
Healthcare Cost Patterns and Prediction: Investigating Personal Datasets Using Data Analytics
- 3 May 2025
- Published by Springer Nature
- p. 341-359
Healthcare Cost Patterns and Prediction: Investigating Personal Datasets Using Data Analytics
- 17 March 2025
- Published by Springer Nature
- p. 231-243
A Novel Approach for Performance Evaluation and Effectiveness of Data-Driven Heart Disease Diagnosis
- 17 March 2025
- Published by Springer Nature
- p. 231-243
A Novel Approach for Performance Evaluation and Effectiveness of Data-Driven Heart Disease Diagnosis
- 27 February 2025
- Published by Springer Nature
- p. 321-339
Exploring Efficient Model for Agricultural Commodity Price Prediction Using Data Analytics
- 27 February 2025
- Published by Springer Nature
- p. 321-339
Exploring Efficient Model for Agricultural Commodity Price Prediction Using Data Analytics
- Open Access
- 1 January 2025
- Published by Elsevier in SSRN Electronic Journal
AI in VLSI Design Advances and Challenges: Living in the Complex Nature of Integrated Devices
This article investigates vital VLSI configuration progress, including nanotechnology, 3D coordination, high-level materials, Framework on-Chip (SoC) plan, and state-of-the-art bundling advancements. Security concerns about equipment weaknesses and the consistent apparition of financial and mechanical oldness further confuse the scene. Looking forward, the article frames arising patterns in VLSI configuration, including simulated intelligence joining, quantum processing structures, neuromorphic figuring, and photonics combination. It proposes expected arrangements, like cooperative environments, advancements in warm administration, security-by-plan standards, coordinated techniques, and expanded interest in schooling. The end considers the ramifications for the future, stressing the requirement for consistent variation, interdisciplinary joint effort, and a groundbreaking way to deal with bridling the maximum capacity of coordinated gadgets in the mind-boggling universe of the VLSI plan.
- 1 January 2025
- Published by Elsevier in SSRN Electronic Journal
Open AccessAI in VLSI Design Advances and Challenges: Living in the Complex Nature of Integrated Devices
This article investigates vital VLSI configuration progress, including nanotechnology, 3D coordination, high-level materials, Framework on-Chip (SoC) plan, and state-of-the-art bundling advancements. Security concerns about equipment weaknesses and the consistent apparition of financial and mechanical oldness further confuse the scene. Looking forward, the article frames arising patterns in VLSI configuration, including simulated intelligence joining, quantum processing structures, neuromorphic figuring, and photonics combination. It proposes expected arrangements, like cooperative environments, advancements in warm administration, security-by-plan standards, coordinated techniques, and expanded interest in schooling. The end considers the ramifications for the future, stressing the requirement for consistent variation, interdisciplinary joint effort, and a groundbreaking way to deal with bridling the maximum capacity of coordinated gadgets in the mind-boggling universe of the VLSI plan.
- 22 November 2024
- Published by Springer Nature
- p. 431-445
Assessing Bank Loan Applicant (Credit Score) Through ML: A Comparative Approach
- 22 November 2024
- Published by Springer Nature
- p. 431-445
Assessing Bank Loan Applicant (Credit Score) Through ML: A Comparative Approach
- 22 November 2024
- Published by Springer Nature
- p. 1-14
Assessing Cybersecurity Threats: The Application of NLP in Advanced Threat Intelligence Systems
- 22 November 2024
- Published by Springer Nature
- p. 1-14
Assessing Cybersecurity Threats: The Application of NLP in Advanced Threat Intelligence Systems
- 17 October 2024
- Published by Springer Nature
- p. 583-597
Unleashing Modified Deep Learning Models in Efficient COVID-19 Detection
- 17 October 2024
- Published by Springer Nature
- p. 583-597
Unleashing Modified Deep Learning Models in Efficient COVID-19 Detection
- 25 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 321-327
Utilization of Encoding, Early Stopping, Hyper Parameter Tuning, and Machine Learning Models for Bank Fraud Detection
An effective fraud detection system must protect millions of clients for a secure banking system, which can be achieved using machine learning and AI. In this article, authors have applied four supervised machine learning models: k-nearest neighbors (KNN), random forest (RF), decision tree, and logistic regression (LR) algorithm to detect bank fraud for a synthetic dataset having 1,00,000 rows and 32 columns. Adequate preprocessing, decoding, rigorous feature engineering, validation, performance evaluation, and explanation have allowed the readers to understand the whole study. The algorithms' accuracy is similar for label encoding, which is not prescribed. Still, a significant AUC of 98% has been achieved in Gradient Boosting Models. Further application of this study can be done in real-life cases of banks, insurance, and finance institutions.
- 25 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 321-327
Utilization of Encoding, Early Stopping, Hyper Parameter Tuning, and Machine Learning Models for Bank Fraud Detection
An effective fraud detection system must protect millions of clients for a secure banking system, which can be achieved using machine learning and AI. In this article, authors have applied four supervised machine learning models: k-nearest neighbors (KNN), random forest (RF), decision tree, and logistic regression (LR) algorithm to detect bank fraud for a synthetic dataset having 1,00,000 rows and 32 columns. Adequate preprocessing, decoding, rigorous feature engineering, validation, performance evaluation, and explanation have allowed the readers to understand the whole study. The algorithms' accuracy is similar for label encoding, which is not prescribed. Still, a significant AUC of 98% has been achieved in Gradient Boosting Models. Further application of this study can be done in real-life cases of banks, insurance, and finance institutions.