Mohammad Monir Uddin
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
Mohammad Monir Uddin has a total of 85 co-authors. Here are the top co-authors by number of shared publications:
- Tanzim Hossain
North South Univ, Dept Elect & Comp Engn, Dhaka 1229, Bangladesh
5 shared publications - Jens Saak
Max Planck Institute for Dynamics of Complex Technical Systems, Magdeburg, Germany
4 shared publications - Kazi Shahriar Sanjid
Department of Electrical & Computer Engineering North South University -1229 Dhaka Bangladesh
4 shared publications Kife I. Bin Iqbal
4 shared publications- Mahtab Uddin
United International University
4 shared publications Motlubar Rahman
Jahangirnagar University
4 shared publications
Latest Publications
- 21 October 2026
- Published by Springer Nature in Modeling Earth Systems and Environment
- Vol. 12 (6) , 303
Exploring waveform dynamics through bifurcation, chaos, sensitivity, and multistability analysis
- 21 October 2026
- Published by Springer Nature in Modeling Earth Systems and Environment
- Vol. 12 (6) , 303
Exploring waveform dynamics through bifurcation, chaos, sensitivity, and multistability analysis
- 6 August 2026
- Published by Elsevier in Journal of Computational and Applied Mathematics
- Vol. 491
Model order reduction of sparse index-2 descriptor systems over limited frequency and time intervals
- 6 August 2026
- Published by Elsevier in Journal of Computational and Applied Mathematics
- Vol. 491
Model order reduction of sparse index-2 descriptor systems over limited frequency and time intervals
- Open Access
- 29 June 2026
- Published by Elsevier in Franklin Open
- Vol. 16
Structure-preserving extended balanced truncation techniques for approximation of a class of second-order index-1 descriptor systems
- 29 June 2026
- Published by Elsevier in Franklin Open
- Vol. 16
Open AccessStructure-preserving extended balanced truncation techniques for approximation of a class of second-order index-1 descriptor systems
- Open Access
ConvMambaNet: A Hybrid CNN-Mamba State Space Architecture for Accurate and Real-Time EEG Seizure Detection
Epilepsy is a chronic neurological disorder marked by recurrent seizures that can severely impact quality of life. Electroencephalography (EEG) remains the primary tool for monitoring neural activity and detecting seizures, yet automated analysis remains challenging due to the temporal complexity of EEG signals. This study introduces ConvMambaNet, a hybrid deep learning model that integrates Convolutional Neural Networks (CNNs) with the Mamba Structured State Space Model (SSM) to enhance temporal feature extraction. By embedding the Mamba-SSM block within a CNN framework, the model effectively captures both spatial and long-range temporal dynamics. Evaluated on the CHB-MIT Scalp EEG dataset, ConvMambaNet achieved a 99% accuracy and demonstrated robust performance under severe class imbalance. These results underscore the model's potential for precise and efficient seizure detection, offering a viable path toward real-time, automated epilepsy monitoring in clinical environments.
Open AccessConvMambaNet: A Hybrid CNN-Mamba State Space Architecture for Accurate and Real-Time EEG Seizure Detection
Epilepsy is a chronic neurological disorder marked by recurrent seizures that can severely impact quality of life. Electroencephalography (EEG) remains the primary tool for monitoring neural activity and detecting seizures, yet automated analysis remains challenging due to the temporal complexity of EEG signals. This study introduces ConvMambaNet, a hybrid deep learning model that integrates Convolutional Neural Networks (CNNs) with the Mamba Structured State Space Model (SSM) to enhance temporal feature extraction. By embedding the Mamba-SSM block within a CNN framework, the model effectively captures both spatial and long-range temporal dynamics. Evaluated on the CHB-MIT Scalp EEG dataset, ConvMambaNet achieved a 99% accuracy and demonstrated robust performance under severe class imbalance. These results underscore the model's potential for precise and efficient seizure detection, offering a viable path toward real-time, automated epilepsy monitoring in clinical environments.
- Open Access
OncoVision: Integrating Mammography and Clinical Data through Attention-Driven Multimodal AI for Enhanced Breast Cancer Diagnosis
OncoVision is a multimodal AI pipeline that combines mammography images and clinical data for better breast cancer diagnosis. Employing an attention-based encoder-decoder backbone, it jointly segments four ROIs - masses, calcifications, axillary findings, and breast tissues - with state-of-the-art accuracy and robustly predicts ten structured clinical features: mass morphology, calcification type, ACR breast density, and BI-RADS categories. To fuse imaging and clinical insights, we developed two late-fusion strategies. By utilizing complementary multimodal data, late fusion strategies improve diagnostic precision and reduce inter-observer variability. Operationalized as a secure, user-friendly web application, OncoVision produces structured reports with dual-confidence scoring and attention-weighted visualizations for real-time diagnostic support to improve clinician trust and facilitate medical teaching. It can be easily incorporated into the clinic, making screening available in underprivileged areas around the world, such as rural South Asia. Combining accurate segmentation with clinical intuition, OncoVision raises the bar for AI-based mammography, offering a scalable and equitable solution to detect breast cancer at an earlier stage and enhancing treatment through timely interventions.
Open AccessOncoVision: Integrating Mammography and Clinical Data through Attention-Driven Multimodal AI for Enhanced Breast Cancer Diagnosis
OncoVision is a multimodal AI pipeline that combines mammography images and clinical data for better breast cancer diagnosis. Employing an attention-based encoder-decoder backbone, it jointly segments four ROIs - masses, calcifications, axillary findings, and breast tissues - with state-of-the-art accuracy and robustly predicts ten structured clinical features: mass morphology, calcification type, ACR breast density, and BI-RADS categories. To fuse imaging and clinical insights, we developed two late-fusion strategies. By utilizing complementary multimodal data, late fusion strategies improve diagnostic precision and reduce inter-observer variability. Operationalized as a secure, user-friendly web application, OncoVision produces structured reports with dual-confidence scoring and attention-weighted visualizations for real-time diagnostic support to improve clinician trust and facilitate medical teaching. It can be easily incorporated into the clinic, making screening available in underprivileged areas around the world, such as rural South Asia. Combining accurate segmentation with clinical intuition, OncoVision raises the bar for AI-based mammography, offering a scalable and equitable solution to detect breast cancer at an earlier stage and enhancing treatment through timely interventions.
- Open Access
- 30 June 2025
- Published by Academia Romana Filiala Cluj in Journal of Numerical Analysis and Approximation Theory
- Vol. 54 (1) , 157-169
A comparative study on balanced truncation and projection onto the dominant eigenspace of the Gramian using Laguerre functions
This paper presents a comparative analysis of two model reduction techniques: balanced truncation and projection onto the dominant eigenspace of the Gramian. Both methods are evaluated through the lens of Laguerre functions which is a reduction technique based on Laguerre function expansion, that approximates the low-rank factors of the Controllability and Observability Gramians to produce approximately balanced systems without solving Lyapunov equations. We demonstrate the effectiveness of each approach in reducing the complexity of linear time-invariant (LTI) systems while preserving system dynamics. Numerical experiments highlight the strengths and weaknesses of both methods, showcasing their applicability to large-scale systems. By thoroughly analyzing both methods in conjunction with Laguerre functions, we contribute to the ongoing discourse in the field and lay the groundwork for future advancements in model reduction techniques.
- 30 June 2025
- Published by Academia Romana Filiala Cluj in Journal of Numerical Analysis and Approximation Theory
- Vol. 54 (1) , 157-169
Open AccessA comparative study on balanced truncation and projection onto the dominant eigenspace of the Gramian using Laguerre functions
This paper presents a comparative analysis of two model reduction techniques: balanced truncation and projection onto the dominant eigenspace of the Gramian. Both methods are evaluated through the lens of Laguerre functions which is a reduction technique based on Laguerre function expansion, that approximates the low-rank factors of the Controllability and Observability Gramians to produce approximately balanced systems without solving Lyapunov equations. We demonstrate the effectiveness of each approach in reducing the complexity of linear time-invariant (LTI) systems while preserving system dynamics. Numerical experiments highlight the strengths and weaknesses of both methods, showcasing their applicability to large-scale systems. By thoroughly analyzing both methods in conjunction with Laguerre functions, we contribute to the ongoing discourse in the field and lay the groundwork for future advancements in model reduction techniques.
- Open Access
- 8 March 2025
- Published by Elsevier in Machine Learning with Applications
- Vol. 20
Pioneering precision in lumbar spine MRI segmentation with advanced deep learning and data enhancement
- 8 March 2025
- Published by Elsevier in Machine Learning with Applications
- Vol. 20
Open AccessPioneering precision in lumbar spine MRI segmentation with advanced deep learning and data enhancement
- 28 December 2024
- Published by Springer Nature
- p. 365-379
Integrating Mamba Sequence Model and Hierarchical Upsampling Network for Accurate Semantic Segmentation of Multiple Sclerosis Lesion
- 28 December 2024
- Published by Springer Nature
- p. 365-379
Integrating Mamba Sequence Model and Hierarchical Upsampling Network for Accurate Semantic Segmentation of Multiple Sclerosis Lesion
- Open Access
- 30 September 2024
- Published by Springer Nature in Research Square
Pioneering Precision in Lumbar Spine MRI Segmentation with Advanced Deep Learning and Data Enhancement
This study presents an advanced approach to lumbar spine segmentation using deep learning techniques, focusing on addressing key challenges such as class imbalance and data preprocessing. Magnetic resonance imaging (MRI) scans of patients with low back pain are meticulously preprocessed to accurately represent three critical classes: vertebrae, spinal canal, and intervertebral discs (IVDs). By rectifying class inconsistencies in the data preprocessing stage, the fidelity of the training data is ensured. The modified U-Net model incorporates innovative architectural enhancements, including an upsample block with leaky Rectified Linear Units (ReLU) and Glorot uniform initializer, to mitigate common issues such as the dying ReLU problem and improve stability during training. Introducing a custom combined loss function effectively tackles class imbalance, significantly improving segmentation accuracy. Evaluation using a comprehensive suite of metrics showcases the superior performance of this approach, outperforming existing methods and advancing the current techniques in lumbar spine segmentation. These findings hold significant advancements for enhanced lumbar spine MRI and segmentation diagnostic accuracy.
- 30 September 2024
- Published by Springer Nature in Research Square
Open AccessPioneering Precision in Lumbar Spine MRI Segmentation with Advanced Deep Learning and Data Enhancement
This study presents an advanced approach to lumbar spine segmentation using deep learning techniques, focusing on addressing key challenges such as class imbalance and data preprocessing. Magnetic resonance imaging (MRI) scans of patients with low back pain are meticulously preprocessed to accurately represent three critical classes: vertebrae, spinal canal, and intervertebral discs (IVDs). By rectifying class inconsistencies in the data preprocessing stage, the fidelity of the training data is ensured. The modified U-Net model incorporates innovative architectural enhancements, including an upsample block with leaky Rectified Linear Units (ReLU) and Glorot uniform initializer, to mitigate common issues such as the dying ReLU problem and improve stability during training. Introducing a custom combined loss function effectively tackles class imbalance, significantly improving segmentation accuracy. Evaluation using a comprehensive suite of metrics showcases the superior performance of this approach, outperforming existing methods and advancing the current techniques in lumbar spine segmentation. These findings hold significant advancements for enhanced lumbar spine MRI and segmentation diagnostic accuracy.
- Open Access
Pioneering Precision in Lumbar Spine MRI Segmentation with Advanced Deep Learning and Data Enhancement
This study presents an advanced approach to lumbar spine segmentation using deep learning techniques, focusing on addressing key challenges such as class imbalance and data preprocessing. Magnetic resonance imaging (MRI) scans of patients with low back pain are meticulously preprocessed to accurately represent three critical classes: vertebrae, spinal canal, and intervertebral discs (IVDs). By rectifying class inconsistencies in the data preprocessing stage, the fidelity of the training data is ensured. The modified U-Net model incorporates innovative architectural enhancements, including an upsample block with leaky Rectified Linear Units (ReLU) and Glorot uniform initializer, to mitigate common issues such as the dying ReLU problem and improve stability during training. Introducing a custom combined loss function effectively tackles class imbalance, significantly improving segmentation accuracy. Evaluation using a comprehensive suite of metrics showcases the superior performance of this approach, outperforming existing methods and advancing the current techniques in lumbar spine segmentation. These findings hold significant advancements for enhanced lumbar spine MRI and segmentation diagnostic accuracy.
Open AccessPioneering Precision in Lumbar Spine MRI Segmentation with Advanced Deep Learning and Data Enhancement
This study presents an advanced approach to lumbar spine segmentation using deep learning techniques, focusing on addressing key challenges such as class imbalance and data preprocessing. Magnetic resonance imaging (MRI) scans of patients with low back pain are meticulously preprocessed to accurately represent three critical classes: vertebrae, spinal canal, and intervertebral discs (IVDs). By rectifying class inconsistencies in the data preprocessing stage, the fidelity of the training data is ensured. The modified U-Net model incorporates innovative architectural enhancements, including an upsample block with leaky Rectified Linear Units (ReLU) and Glorot uniform initializer, to mitigate common issues such as the dying ReLU problem and improve stability during training. Introducing a custom combined loss function effectively tackles class imbalance, significantly improving segmentation accuracy. Evaluation using a comprehensive suite of metrics showcases the superior performance of this approach, outperforming existing methods and advancing the current techniques in lumbar spine segmentation. These findings hold significant advancements for enhanced lumbar spine MRI and segmentation diagnostic accuracy.