Abu Bakr Siddique
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
Abu Bakr Siddique has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Shadman Sakib
Department of EECS University of Hyogo Himeji Japan
12 shared publications - Mohammad Mahmudur Rahman Khan10 shared publications
- Rezoana Bente Arif
Dept. of EEE International University of Business Agriculture and Technology Bangladesh
10 shared publications Mohammad Mahmudur Rahman Khan
Department of ECE, Vanderbilt University, Nashville, Tennessee-37240, USA
9 shared publicationsRezoana Bente Arif
Dept. of EEE, International University of Business Agriculture and Technology, Bangladesh
7 shared publications- Shadman Sakib
Mobile Pervasive & Sensor Computing Lab and Department of Information Systems University of Maryland Baltimore County (UMBC) Baltimore Maryland USA
5 shared publications
Latest Publications
- Open Access
- 4 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 218-225
Neuromorphic Silicon Neuron Controller for Adaptive Deep Brain Stimulation in Parkinson’s Disease
Parkinson’s disease (PD) affects millions worldwide and causes severe motor symptoms. Adaptive deep brain stimulation (aDBS) delivers physiologically informed stimulation that can track fluctuations in PD motor symptoms, enabling more intelligent DBS control. However, most existing aDBS approaches are primarily algorithm- and software-driven, with limited efforts toward circuit realization, particularly low-power and implantable integrated circuits. This paper presents the Silicon Leaky Integrate-and-Fire Deep Brain Stimulation (SiLIF-DBS) controller, a neuromorphic silicon neuron stimulator implemented with metal-oxide-semiconductor (CMOS) technology. For system-level evaluation, a simplified computational model of the SiLIF-DBS controller is derived and embedded within a Parkinsonian cortico-basal ganglia framework for closed-loop validation. The system is driven by beta-band subthalamic nucleus local field potentials (STN-LFPs), with their average rectified value (Beta ARV) used as the control biomarker. Our SiLIF-DBS controller for aDBS suppresses pathological beta activity while consuming only 25% of the power required by open-loop stimulation and achieving a suppression efficiency of \(5.85\%\) /μ W. Overall, our SiLIF-DBS controller achieves strong beta suppression at substantially reduced power, delivering high suppression efficiency that demonstrates it is a viable foundation for low-power implantable aDBS.- 4 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 218-225
Open AccessNeuromorphic Silicon Neuron Controller for Adaptive Deep Brain Stimulation in Parkinson’s Disease
Parkinson’s disease (PD) affects millions worldwide and causes severe motor symptoms. Adaptive deep brain stimulation (aDBS) delivers physiologically informed stimulation that can track fluctuations in PD motor symptoms, enabling more intelligent DBS control. However, most existing aDBS approaches are primarily algorithm- and software-driven, with limited efforts toward circuit realization, particularly low-power and implantable integrated circuits. This paper presents the Silicon Leaky Integrate-and-Fire Deep Brain Stimulation (SiLIF-DBS) controller, a neuromorphic silicon neuron stimulator implemented with metal-oxide-semiconductor (CMOS) technology. For system-level evaluation, a simplified computational model of the SiLIF-DBS controller is derived and embedded within a Parkinsonian cortico-basal ganglia framework for closed-loop validation. The system is driven by beta-band subthalamic nucleus local field potentials (STN-LFPs), with their average rectified value (Beta ARV) used as the control biomarker. Our SiLIF-DBS controller for aDBS suppresses pathological beta activity while consuming only 25% of the power required by open-loop stimulation and achieving a suppression efficiency of \(5.85\%\) /μ W. Overall, our SiLIF-DBS controller achieves strong beta suppression at substantially reduced power, delivering high suppression efficiency that demonstrates it is a viable foundation for low-power implantable aDBS. - 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Oceanic Engineering
- Vol. 51 (2) , 1574-1591
UStyle: Waterbody Style Transfer of Underwater Scenes by Depth-Guided Feature Synthesis
The concept of “waterbody style” transfer remains largely unexplored in the underwater imaging literature. Traditional image style transfer (STx) methods emphasize artistic and photorealistic blending that fails to preserve geometry in high-scattering underwater environments. The wavelength-dependent attenuation and depth-dependent backscattering of underwater optics further complicate STx learning from unpaired data. We introduce UStyle, the first data-driven framework for transferring waterbody styles across underwater images without needing reference images or explicit scene information. We propose a novel depth-aware whitening and coloring transform that incorporates physics-based waterbody synthesis for perceptually consistent stylization while preserving scene structure. We also integrate carefully designed loss functions to maintain color, lightness, structural integrity, frequency-domain features, and high-level content in VGG and CLIP spaces. Comprehensive experimental analyses show that UStyle surpasses state-of-the-art methods that rely solely on reconstruction loss. In addition, we present the UF7D data set, a curated benchmark of high-resolution underwater images across seven waterbody styles.
- 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Oceanic Engineering
- Vol. 51 (2) , 1574-1591
UStyle: Waterbody Style Transfer of Underwater Scenes by Depth-Guided Feature Synthesis
The concept of “waterbody style” transfer remains largely unexplored in the underwater imaging literature. Traditional image style transfer (STx) methods emphasize artistic and photorealistic blending that fails to preserve geometry in high-scattering underwater environments. The wavelength-dependent attenuation and depth-dependent backscattering of underwater optics further complicate STx learning from unpaired data. We introduce UStyle, the first data-driven framework for transferring waterbody styles across underwater images without needing reference images or explicit scene information. We propose a novel depth-aware whitening and coloring transform that incorporates physics-based waterbody synthesis for perceptually consistent stylization while preserving scene structure. We also integrate carefully designed loss functions to maintain color, lightness, structural integrity, frequency-domain features, and high-level content in VGG and CLIP spaces. Comprehensive experimental analyses show that UStyle surpasses state-of-the-art methods that rely solely on reconstruction loss. In addition, we present the UF7D data set, a curated benchmark of high-resolution underwater images across seven waterbody styles.
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (10) , 1-11
Single-Step Latent Diffusion for Underwater Image Restoration
Underwater image restoration algorithms seek to restore the color, contrast, and appearance of a scene that is imaged underwater. They are a critical tool in applications ranging from marine ecology and aquaculture to underwater construction and archaeology. While existing pixel-domain diffusion-based image restoration approaches are effective at restoring simple scenes with limited depth variation, they are computationally intensive and often generate unrealistic artifacts when applied to scenes with complex geometry and significant depth variation. In this work we overcome these limitations by combining a novel network architecture (SLURPP) with an accurate synthetic data generation pipeline. SLURPP combines pretrained latent diffusion models-which encode strong priors on the geometry and depth of scenes-with an explicit scene decomposition-which allows one to model and account for the effects of light attenuation and backscattering. To train SLURPP we design a physics-based underwater image synthesis pipeline that applies varied and realistic underwater degradation effects to existing terrestrial image datasets. This approach enables the generation of diverse training data with dense medium/degradation annotations. We evaluate our method extensively on both synthetic and real-world benchmarks and demonstrate state-of-the-art performance. Notably, SLURPP is over $200\times$ faster than existing diffusion-based methods while offering $\sim 3 dB$ improvement in PSNR on synthetic benchmarks. It also offers compelling qualitative improvements on real-world data. Project website https://tianfwang.github.io/slurpp/.- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (10) , 1-11
Single-Step Latent Diffusion for Underwater Image Restoration
Underwater image restoration algorithms seek to restore the color, contrast, and appearance of a scene that is imaged underwater. They are a critical tool in applications ranging from marine ecology and aquaculture to underwater construction and archaeology. While existing pixel-domain diffusion-based image restoration approaches are effective at restoring simple scenes with limited depth variation, they are computationally intensive and often generate unrealistic artifacts when applied to scenes with complex geometry and significant depth variation. In this work we overcome these limitations by combining a novel network architecture (SLURPP) with an accurate synthetic data generation pipeline. SLURPP combines pretrained latent diffusion models-which encode strong priors on the geometry and depth of scenes-with an explicit scene decomposition-which allows one to model and account for the effects of light attenuation and backscattering. To train SLURPP we design a physics-based underwater image synthesis pipeline that applies varied and realistic underwater degradation effects to existing terrestrial image datasets. This approach enables the generation of diverse training data with dense medium/degradation annotations. We evaluate our method extensively on both synthetic and real-world benchmarks and demonstrate state-of-the-art performance. Notably, SLURPP is over $200\times$ faster than existing diffusion-based methods while offering $\sim 3 dB$ improvement in PSNR on synthetic benchmarks. It also offers compelling qualitative improvements on real-world data. Project website https://tianfwang.github.io/slurpp/.- Open Access
Detection of COVID-19 Disease from Chest X-Ray Images: A Deep Transfer Learning Framework
World economy as well as public health have been facing a devastating effect caused by the disease termed as Coronavirus (COVID-19). A significant step of COVID-19 affected patient’s treatment is the faster and accurate detection of the disease which is the motivation of this study. In this paper, implementation of a deep transfer learning-based framework using a pre-trained network (ResNet-50) for detecting COVID-19 from the chest X-rays was done. Our dataset consists of 2905 chest X-ray images of three categories: COVID-19 affected (219 cases), Viral Pneumonia affected (1345 cases), and Normal Chest X-rays (1341 cases). The implemented neural network demonstrates significant performance in classifying the cases with an overall accuracy of 96%. Most importantly, the model has shown a significantly good performance over the current research-based methods in detecting the COVID-19 cases in the test dataset (Precision = 1.00, Recall = 1.00, F1-score = 1.00 and Specificity = 1.00). Therefore, our proposed approach can be adapted as a reliable method for faster and accurate COVID-19 affected case detection.
Open AccessDetection of COVID-19 Disease from Chest X-Ray Images: A Deep Transfer Learning Framework
World economy as well as public health have been facing a devastating effect caused by the disease termed as Coronavirus (COVID-19). A significant step of COVID-19 affected patient’s treatment is the faster and accurate detection of the disease which is the motivation of this study. In this paper, implementation of a deep transfer learning-based framework using a pre-trained network (ResNet-50) for detecting COVID-19 from the chest X-rays was done. Our dataset consists of 2905 chest X-ray images of three categories: COVID-19 affected (219 cases), Viral Pneumonia affected (1345 cases), and Normal Chest X-rays (1341 cases). The implemented neural network demonstrates significant performance in classifying the cases with an overall accuracy of 96%. Most importantly, the model has shown a significantly good performance over the current research-based methods in detecting the COVID-19 cases in the test dataset (Precision = 1.00, Recall = 1.00, F1-score = 1.00 and Specificity = 1.00). Therefore, our proposed approach can be adapted as a reliable method for faster and accurate COVID-19 affected case detection.
- Open Access
Prediction of Temperature and Rainfall in Bangladesh using Long Short Term Memory Recurrent Neural Networks
Temperature and rainfall have a significant impact on economic growth as well as the outbreak of seasonal diseases in a region. In spite of that inadequate studies have been carried out for analyzing the weather pattern of Bangladesh implementing the artificial neural network. Therefore, in this study, we are implementing a Long Short-term Memory (LSTM) model to forecast the month-wise temperature and rainfall by analyzing 115 years (1901-2015) of weather data of Bangladesh. The LSTM model has shown a mean error of -0.38oC in case of predicting the month-wise temperature for 2 years and -17.64mm in case of predicting the rainfall. This prediction model can help to understand the weather pattern changes as well as studying seasonal diseases of Bangladesh whose outbreaks are dependent on regional temperature and/or rainfall.
Open AccessPrediction of Temperature and Rainfall in Bangladesh using Long Short Term Memory Recurrent Neural Networks
Temperature and rainfall have a significant impact on economic growth as well as the outbreak of seasonal diseases in a region. In spite of that inadequate studies have been carried out for analyzing the weather pattern of Bangladesh implementing the artificial neural network. Therefore, in this study, we are implementing a Long Short-term Memory (LSTM) model to forecast the month-wise temperature and rainfall by analyzing 115 years (1901-2015) of weather data of Bangladesh. The LSTM model has shown a mean error of -0.38oC in case of predicting the month-wise temperature for 2 years and -17.64mm in case of predicting the rainfall. This prediction model can help to understand the weather pattern changes as well as studying seasonal diseases of Bangladesh whose outbreaks are dependent on regional temperature and/or rainfall.
- Open Access
Electrocardiogram Heartbeat Classification Using Convolutional Neural Networks for the Detection of Cardiac Arrhythmia
The classification of the electrocardiogram (ECG) signal has a vital impact on identifying heart-related diseases. This can ensure the premature finding of heart disease and the proper selection of the patient's customized treatment. However, the detection of arrhythmia is a challenging task to perform manually. This justifies the necessity of a technique for automatic detection of abnormal heart signals. Therefore, our work is based on the classification of five classes of ECG arrhythmic signals from Physionet's MIT-BIH Arrhythmia Dataset. Artificial Neural Networks (ANN) have demonstrated significant success in ECG signal classification. Our proposed model is a Convolutional Neural Network (CNN) customized to categorize the ECG signals. Our result testifies that the planned CNN model can successfully categorize arrhythmia with an overall accuracy of 95.2%. The average precision and recall of the proposed model are 95.2% and 95.4%, respectively. This model can effectively be used to detect irregularities of heart rhythm at an early stage.
Open AccessElectrocardiogram Heartbeat Classification Using Convolutional Neural Networks for the Detection of Cardiac Arrhythmia
The classification of the electrocardiogram (ECG) signal has a vital impact on identifying heart-related diseases. This can ensure the premature finding of heart disease and the proper selection of the patient's customized treatment. However, the detection of arrhythmia is a challenging task to perform manually. This justifies the necessity of a technique for automatic detection of abnormal heart signals. Therefore, our work is based on the classification of five classes of ECG arrhythmic signals from Physionet's MIT-BIH Arrhythmia Dataset. Artificial Neural Networks (ANN) have demonstrated significant success in ECG signal classification. Our proposed model is a Convolutional Neural Network (CNN) customized to categorize the ECG signals. Our result testifies that the planned CNN model can successfully categorize arrhythmia with an overall accuracy of 95.2%. The average precision and recall of the proposed model are 95.2% and 95.4%, respectively. This model can effectively be used to detect irregularities of heart rhythm at an early stage.
- Open Access
Deep Convolutional Neural Networks Model-based Brain Tumor Detection in Brain MRI Images
Diagnosing Brain Tumor with the aid of Magnetic Resonance Imaging (MRI) has gained enormous prominence over the years, primarily in the field of medical science. Detection and/or partitioning of brain tumors solely with the aid of MR imaging is achieved at the cost of immense time and effort and demands a lot of expertise from engaged personnel. This substantiates the necessity of fabricating an autonomous model brain tumor diagnosis. Our work involves implementing a deep convolutional neural network (DCNN) for diagnosing brain tumors from MR images. The dataset used in this paper consists of 253 brain MR images where 155 images are reported to have tumors. Our model can single out the MR images with tumors with an overall accuracy of 96%. The model outperformed the existing conventional methods for the diagnosis of brain tumor in the test dataset (Precision = 0.93, Sensitivity = 1.00, and F1-score = 0.97). Moreover, the proposed model's average precision-recall score is 0.93, Cohen's Kappa 0.91, and AUC 0.95. Therefore, the proposed model can help clinical experts verify whether the patient has a brain tumor and, consequently, accelerate the treatment procedure.
Open AccessDeep Convolutional Neural Networks Model-based Brain Tumor Detection in Brain MRI Images
Diagnosing Brain Tumor with the aid of Magnetic Resonance Imaging (MRI) has gained enormous prominence over the years, primarily in the field of medical science. Detection and/or partitioning of brain tumors solely with the aid of MR imaging is achieved at the cost of immense time and effort and demands a lot of expertise from engaged personnel. This substantiates the necessity of fabricating an autonomous model brain tumor diagnosis. Our work involves implementing a deep convolutional neural network (DCNN) for diagnosing brain tumors from MR images. The dataset used in this paper consists of 253 brain MR images where 155 images are reported to have tumors. Our model can single out the MR images with tumors with an overall accuracy of 96%. The model outperformed the existing conventional methods for the diagnosis of brain tumor in the test dataset (Precision = 0.93, Sensitivity = 1.00, and F1-score = 0.97). Moreover, the proposed model's average precision-recall score is 0.93, Cohen's Kappa 0.91, and AUC 0.95. Therefore, the proposed model can help clinical experts verify whether the patient has a brain tumor and, consequently, accelerate the treatment procedure.
- Open Access
Performance Evaluation of t-SNE and MDS Dimensionality Reduction Techniques with KNN, ENN and SVM Classifiers
The central goal of this paper is to establish two commonly available dimensionality reduction (DR) methods i.e. t-distributed Stochastic Neighbor Embedding (t-SNE) and Multidimensional Scaling (MDS) in Matlab and to observe their application in several datasets. These DR techniques are applied to nine different datasets namely CNAE9, Segmentation, Seeds, Pima Indians diabetes, Parkinsons, Movement Libras, Mammographic Masses, Knowledge, and Ionosphere acquired from UCI machine learning repository. By applying t-SNE and MDS algorithms, each dataset is transformed to the half of its original dimension by eliminating unnecessary features from the datasets. Subsequently, these datasets with reduced dimensions are fed into three supervised classification algorithms for classification. These classification algorithms are K Nearest Neighbors (KNN), Extended Nearest Neighbors (ENN), and Support Vector Machine (SVM). Again, all these algorithms are implemented in Matlab. The training and test data ratios are maintained as ninety percent: ten percent for each dataset. Upon accuracy observation, the efficiency for every dimensionality technique with availed classification algorithms is analyzed and the performance of each classifier is evaluated.
Open AccessPerformance Evaluation of t-SNE and MDS Dimensionality Reduction Techniques with KNN, ENN and SVM Classifiers
The central goal of this paper is to establish two commonly available dimensionality reduction (DR) methods i.e. t-distributed Stochastic Neighbor Embedding (t-SNE) and Multidimensional Scaling (MDS) in Matlab and to observe their application in several datasets. These DR techniques are applied to nine different datasets namely CNAE9, Segmentation, Seeds, Pima Indians diabetes, Parkinsons, Movement Libras, Mammographic Masses, Knowledge, and Ionosphere acquired from UCI machine learning repository. By applying t-SNE and MDS algorithms, each dataset is transformed to the half of its original dimension by eliminating unnecessary features from the datasets. Subsequently, these datasets with reduced dimensions are fed into three supervised classification algorithms for classification. These classification algorithms are K Nearest Neighbors (KNN), Extended Nearest Neighbors (ENN), and Support Vector Machine (SVM). Again, all these algorithms are implemented in Matlab. The training and test data ratios are maintained as ninety percent: ten percent for each dataset. Upon accuracy observation, the efficiency for every dimensionality technique with availed classification algorithms is analyzed and the performance of each classifier is evaluated.
- Open Access
Implementation of Fruits Recognition Classifier using Convolutional Neural Network Algorithm for Observation of Accuracies for Various Hidden Layers
Fruit recognition using Deep Convolutional Neural Network (CNN) is one of the most promising applications in computer vision. In recent times, deep learning based classifications are making it possible to recognize fruits from images. However, fruit recognition is still a problem for the stacked fruits on weighing scale because of the complexity and similarity. In this paper, a fruit recognition system using CNN is proposed. The proposed method uses deep learning techniques for the classification. We have used Fruits-360 dataset for the evaluation purpose. From the dataset, we have established a dataset which contains 17,823 images from 25 different categories. The images are divided into training and test dataset. Moreover, for the classification accuracies, we have used various combinations of hidden layer and epochs for different cases and made a comparison between them. The overall performance losses of the network for different cases also observed. Finally, we have achieved the best test accuracy of 100% and a training accuracy of 99.79%.
Open AccessImplementation of Fruits Recognition Classifier using Convolutional Neural Network Algorithm for Observation of Accuracies for Various Hidden Layers
Fruit recognition using Deep Convolutional Neural Network (CNN) is one of the most promising applications in computer vision. In recent times, deep learning based classifications are making it possible to recognize fruits from images. However, fruit recognition is still a problem for the stacked fruits on weighing scale because of the complexity and similarity. In this paper, a fruit recognition system using CNN is proposed. The proposed method uses deep learning techniques for the classification. We have used Fruits-360 dataset for the evaluation purpose. From the dataset, we have established a dataset which contains 17,823 images from 25 different categories. The images are divided into training and test dataset. Moreover, for the classification accuracies, we have used various combinations of hidden layer and epochs for different cases and made a comparison between them. The overall performance losses of the network for different cases also observed. Finally, we have achieved the best test accuracy of 100% and a training accuracy of 99.79%.
- Open Access
Unsupervised Segmentation Algorithms' Implementation in ITK for Tissue Classification via Human Head MRI Scans
Tissue classification is one of the significant tasks in the field of biomedical image analysis. Magnetic Resonance Imaging (MRI) is of great importance in tissue classification especially in the areas of brain tissue classification which is able to recognize anatomical areas of interest such as surgical planning, monitoring therapy, clinical drug trials, image registration, stereotactic neurosurgery, radiotherapy etc. The task of this paper is to implement different unsupervised classification algorithms in ITK and perform tissue classification (white matter, gray matter, cerebrospinal fluid (CSF) and background of the human brain). For this purpose, 5 grayscale head MRI scans are provided. In order of classifying brain tissues, three algorithms are used. These are: Otsu thresholding, Bayesian classification and Bayesian classification with Gaussian smoothing. The obtained classification results are analyzed in the results and discussion section.
Open AccessUnsupervised Segmentation Algorithms' Implementation in ITK for Tissue Classification via Human Head MRI Scans
Tissue classification is one of the significant tasks in the field of biomedical image analysis. Magnetic Resonance Imaging (MRI) is of great importance in tissue classification especially in the areas of brain tissue classification which is able to recognize anatomical areas of interest such as surgical planning, monitoring therapy, clinical drug trials, image registration, stereotactic neurosurgery, radiotherapy etc. The task of this paper is to implement different unsupervised classification algorithms in ITK and perform tissue classification (white matter, gray matter, cerebrospinal fluid (CSF) and background of the human brain). For this purpose, 5 grayscale head MRI scans are provided. In order of classifying brain tissues, three algorithms are used. These are: Otsu thresholding, Bayesian classification and Bayesian classification with Gaussian smoothing. The obtained classification results are analyzed in the results and discussion section.