Md Abubakkar

Midwestern State University, Computer Science, Graduate Student

Followers

Following

Co-authors

Public Views

I am Md Abubakkar, a researcher and project manager passionate about applied machine learning, graph signal processing, and bioinformatics. I hold a master’s degree in Computer Science and have published multiple IEEE papers focused on Parkinson’s detection, sentiment analysis, and sequence data analysis. Currently, I lead supply chain and data-driven projects in the manufacturing sector while pursuing interdisciplinary research to build practical AI solutions for health and industry.
Supervisors: Dr. Nelson Passos

less

Related Authors

Harnain Kour 18dcs008

Michael Tadesse

Dalian University of Technology

University of Chinese Academy of Sciences

Guandong Xu

Tapotosh Ghosh

University of Dhaka, Bangladesh

Hafiz Hassaan Saeed

National University of Computer and Emerging Sciences

Devesh Srivastava

Interests

Uploads

Papers by Md Abubakkar

Explainable Suicide Risk Prediction with DeepFusion: A Hybrid Intelligence Approach

by Md Abubakkar, Imran Ahmad, Dill Mahzabina Tabila, Fowzy Alhussin Alsaud, and Sajib Debnath

2025 4th International Conference on Electronics Representation and Algorithm (ICERA), 2025

Social media sites have emerged as a significant and trustworthy source of information, with user... more Social media sites have emerged as a significant and trustworthy source of information, with users frequently sharing their feelings, thoughts, and opinions on them. These platforms may extract specific interests and trends from usergenerated material in real time by utilising developments in data mining technologies. In terms of gaining useful insights from such data, deep learning models have outperformed typical machine learning models. Three deep learning techniques-Deep Neural Network, Long Short Term Memory, and a CNN-LSTM hybrid model-are used in this study to estimate the likelihood that a tweet on X (previously known as twitter)may contain suicidal content.The feature extraction process relies heavily on the CNN component of the hybrid model. Using convolutional and max-pooling layers, it successfully recovers higher-level characteristics from the textual input. But the state-of-the-art natural language processing model LSTM excels at maintaining long-short-term relationships within tokens and sequences.Our research demonstrates that the CNN-LSTM hybrid model performs better than traditional deep learning models across a number of evaluation metrics, including accuracy, precision, sensitivity, and f1 score.

DownloadEdit

Interpretable Alzheimer's Disease Diagnosis via CNNs and MRI: An Explainable AI Approach

by Md Abubakkar, Mohammed Majbah Uddin, and Sajib Debnath

ICERA, 2025

Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that impairs memory, cogniti... more Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that impairs memory, cognition, and daily functioning, often accompanied by significant behavioral and personality changes in older adults. While there is currently no cure, treatment interventions are most effective during the early and middle stages, emphasizing the critical need for early diagnosis-especially as global aging trends contribute to a rising prevalence of AD. This study aims to enhance early detection of Alzheimer's Disease by leveraging machine learning and deep learning techniques on MRI scans from the Open Access Series of Imaging Studies (OASIS) dataset. We employed a diverse set of models, including Random Forest and Logistic Regression from classical machine learning, Extra Trees from ensemble learning, and Convolutional Neural Networks (CNNs) from deep learning. Performance was assessed using accuracy, precision, recall, and area under the curve (AUC). Results indicate that CNNs achieved the highest accuracy and AUC scores, while Extra Trees excelled in precision and recall-highlighting the potential of both deep learning and ensemble-based methods in supporting early AD diagnosis through neuroimaging.

DownloadEdit

A Comprehensive Framework Analysis of Cycle GAN-Based Modality Translation: Enhancing Brain Tumor Diagnostics from FLAIR to T2w

2025 4th International Conference on Electronics Representation and Algorithm (ICERA), Yogyakarta, Indonesia, 2025

Brain tumors remain a major healthcare challenge due to their complexity, high mortality rates, a... more Brain tumors remain a major healthcare challenge due to their complexity, high mortality rates, and profound impact on patients' lives, making accurate diagnosis and treatment crucial. Multi-modal MRI scans, particularly FLAIR and T2weighted (T2w) images, offer complementary information about tumor structure and progression. However, real-world clinical settings often face the challenge of missing imaging modalities, limiting comprehensive assessments. To address this issue, we propose a CycleGAN-based framework for translating between FLAIR and T2w MRI scans using the BraTS dataset from the Medical Decathlon Challenge. This dataset includes 3D MRI scans with segmentation masks outlining key tumor regions such as edema, non-enhancing tumor, and enhancing tumor. Our framework uses U-Net-based generators and PatchGAN discriminators, optimized with multiple loss functions, including adversarial, cycle consistency, structural similarity index (SSIM), and pixel-wise losses. These ensure that the generated images are both anatomically accurate and visually realistic. We apply preprocessing steps like intensity normalization, background removal, and data augmentation to maintain structural details and enhance training stability. Our quantitative evaluation shows promising results, achieving SSIM scores of 0.8226 for T2w and 0.7767 for FLAIR. Qualitative analysis further highlights improved tumor visibility and clearer anatomical structures, particularly around tumor boundaries. By addressing the challenge of incomplete imaging datasets, our method not only enhances data availability for tasks like tumor segmentation but also supports more comprehensive diagnostic workflows. This approach represents a step forward in advancing precision medicine for brain tumor analysis through multi-modal MRI synthesis.

DownloadEdit

Aspect-Based Sentiment Analysis of Amazon Product Reviews Using Machine Learning Models and Hybrid Feature Engineering

by Md Abubakkar, Fazle Karim, and Yousuf Abdullah Borna

2025 International Conference on New Trends in Computing Sciences (ICTCS), 2025

While sentiment analysis is a popular and significant research trend, aspect-based sentiment anal... more While sentiment analysis is a popular and significant research trend, aspect-based sentiment analysis (ABSA) requires more focus from researchers. The customer reviews of headphones and Bluetooth devices on Amazon are the main subject of this study. Several machine learning (ML) algorithms are used in the study, including Support Vector Machine (SVM), k-nearest Neighbors (KNN), Random Forest (RF), Naive Bayes (NB), Decision Tree (DT), Logistic Regression (LR). Additionally, a hybrid feature engineering technique combining TF-IDF (Term Frequency-Inverse Document Frequency) and word n-gram is applied, specifically utilizing word n-gram (1,4) in conjunction with TF-IDF. The results of evaluating these methods showed that, with an accuracy of 91%, SVM with hybrid word n-gram (1,3) produced the best outcomes. The research dataset exhibits imbalance, which is addressed by using the Matthews Correlation Coefficient (MCC) as an additional performance metric. This results in a score of 0.77. The results show that aspect-based sentiment analysis is effective in gaining insightful information from customer reviews of headphones and Bluetooth devices on Amazon. The SVM algorithm and the designated hybrid feature engineering technique perform better than the other.

Edit

NeuroSignal Precision: A Hierarchical Approach for Enhanced Insights in Parkinson's Disease Classification

by Md Abubakkar and Kazi Shaharair Sharif

2024 International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA), 2024

Parkinson's disease (PD) is a progressive neurological disorder that affects movement, posture, h... more Parkinson's disease (PD) is a progressive neurological disorder that affects movement, posture, handwriting, and speech. Parkinson's disease is challenging to diagnose early due to subtle symptoms that often go unnoticed, necessitating reliable and accurate classification models to aid clinical decision-making. This research introduces a comprehensive benchmarking of nine unified models, and a unique contribution of this research is the adaptation of the Tabular Transformer model for structured medical data, achieving an unprecedented accuracy of 99.49%, setting a new benchmark for Parkinson's disease classification. The proposed approach provides an advanced, adaptable framework that supports clinicians in making early, accurate diagnoses, ultimately improving patient care. In contrast to previous studies that predominantly emphasize traditional models, this research employs attention-based deep learning to capture complex feature interactions, achieving substantially higher accuracy. The study evaluates nine models: SVM, Decision Tree, Random Forest, AdaBoost, Gradient Boosting, XGBoost, KNN, CNN, and Tabular Transformer, achieving improved accuracy across all models compared to previous studies, marking a notable advancement in Parkinson's disease classification performance. The Transformer's attention mechanism captures intricate data patterns, providing clear advantages over traditional approaches and improving diagnostic precision for early-stage Parkinson's detection. Data preprocessing included the Synthetic Minority Over-sampling Technique for class balancing and feature standardization, with each model, from SVM and Decision Trees to CNN and XGBoost, optimized through Optuna for optimal performance. This research offers the medical field a versatile, high-accuracy framework that aids clinicians in timely and reliable PD diagnosis, potentially improving patient outcomes and advancing Parkinson's diagnostic tools for future clinical use.

DownloadEdit

A Comparative Framework Integrating Hybrid Convolutional and Unified Graph Neural Networks for Accurate Parkinson's Disease Classification

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), Yogyakarta, Indonesia, 2024

Parkinson's disease (PD) is a progressive neurodegenerative disorder, affects motor function and ... more Parkinson's disease (PD) is a progressive neurodegenerative disorder, affects motor function and is often challenging to diagnose due to the complex interplay of clinical features. This study integrates a comparative framework integrating hybrid Convolutional Neural Networks (PCNN) and graph-based models (GCN, GAT) to enhance Parkinson's disease (PD) diagnosis using structured medical data. PD, a progressive neurodegenerative disorder affecting motor function, poses diagnostic challenges due to complex clinical feature interactions. The PCNN employs 1D convolutions to capture local feature patterns, while GCN and GAT model intricate interdependencies between clinical variables by representing the dataset as a graph. Notably, GAT's attention mechanism dynamically prioritizes important features, improving interpretability and diagnostic precision. Through hyperparameter optimization with Optuna and addressing class imbalance using SMOTE, our approach achieved a peak accuracy of 97.44%, surpassing traditional methods. The comparative analysis reveals that while PCNN excels in classification accuracy, GAT's attention-based feature selection offers superior interpretability. This makes it a valuable tool for more precise Parkinson's disease detection in clinical applications. The integration of these models provides a comprehensive framework for PD diagnosis, leveraging both local and global feature extraction techniques. This study represents a significant advancement in applying advanced machine learning to neurodegenerative disease diagnostics, offering improved early detection and personalized treatment potential for Parkinson's disease.

DownloadEdit

Md Abubakkar

Uploads

Papers by Md Abubakkar

Log In