Ariful (me) is a PhD (all but dissertation) in artificial intelligence with a specialization in medical image analysis and AI-driven healthcare systems. Artificial Intelligence at Inje University, Republic of Korea, where his research focused on developing advanced deep learning models for cancer diagnosis using multimodal biomedical data. My work primarily centers on computational pathology, including whole slide image (WSI) analysis, tumor detection, and multimodal learning by integrating imaging and clinical information. During my PhD, I did 3 AI manufacturing projects for Korean manufacturing companies. Ariful’s research interests extend to emerging areas such as federated learning, privacy-preserving AI, and agentic AI systems for healthcare, with the goal of building scalable and trustworthy solutions for real-world clinical deployment. I am a current committee member of 3 IEEE conferences.
EDUCATION
PhD - Major AI in Healthcare, Inje University, Republic of Korea.
Masters of Science - Major AI, Inje University, Republic of Korea.
Bachelor of Science in Computer Science & Engineering, World University of Bangladesh, Dhaka, Bangladesh.
RESEARCH, TEACHING, or OTHER INTERESTS
Artificial Intelligence, Computer Science, Health Informatics, Computer Vision and Pattern Recognition
34
Scopus Publications
1225
Scholar Citations
15
Scholar h-index
23
Scholar i10-index
Scopus Publications
KFYO: Fusing vision and biomechanics for accurate pitch evaluation in real-time baseball using deep learning techniques Gohar Asad, Md Ariful Islam Mozumder, Proloy Kumar Mondal, Rashedul Islam Sumon, Hee- Cheol Kim Heliyon, 2026 Baseball is rapidly growing in global popularity, making accurate ball detection and pitch evaluation crucial for performance analysis. Advanced computer vision techniques now enable precise real-time tracking and assessment of pitches. This study presents an advanced deep learning-based pipeline that detects, tracks, and evaluates baseball pitches by analyzing video sequences from professional broadcasts and amateur pitching sessions. It can detect high-speed baseballs in high-frame-rate videos using the You Only Look Once version 12 (YOLOv12) object detection framework, ensuring accurate tracking from when the ball is thrown from the pitcher's hand to when the catcher catches it. The model is trained on labeled images, which include footage from professional leagues such as MLB and KBO, self-recorded training videos, and amateur games. The pipeline mainly consists of three modules such as baseball detection by YOLOv12, trajectory determination by centroid-based tracking and Kalman filtering, velocity calculation based on video frame time data and aerodynamics, pose estimation and dynamic prediction of strike zone by YOLOv8-Pose and MoveNet for body posture analysis at the time of pitcher release, which automatically classifies the pitch as "ball" or "strike". To overcome the limitations of YOLOv3-tiny and YOLOv5s, YOLOv12 uses an anchor-free head layer, advanced feature pyramid aggregation, and mixed precision (AMP) training, improving performance in detecting small and fast-moving objects. Our proposed YOLOv12 model performed exemplary, reaching a mAP@50 of 0.945, mAP@50–95 of 0.60, precision of 0.91, recall of 0.89, and F1-score of 0.90 (at confidence threshold 0.39), with mAP with an average inference time of 8.6 ms per frame resulting in a throughput of approximately 116 frames per second. These findings prove that it is very effective when it comes to real-time and high-speed applications. Combining biomechanics and visual analysis, it helps with training, performance evaluation, and broadcasting by analyzing statistics such as player speed, spin trajectory, and pitch results.
Integrating Auditing and Inspection into Metaverse-Based Healthcare and Pharmaceutical Supply Chains Muhammad Mohsan Sheeraz, Md Ariful Islam Mozumder, Abdullah Yousafzai, Ibrar Yaqoob International Conference on Advanced Communication Technology Icact, 2026 Metaverse-based healthcare and pharmaceutical supply chains aim to enhance operations by providing greater visibility, virtual representations of facilities and material flows, and innovative methods for coordination and training. However, these metaverse-based systems largely overlook critical regulatory functions, such as auditing and inspection. Audit planning, evidence review, and deviation assessment remain only loosely integrated with the live data streams and digital twin models available on these platforms. Consequently, risk oversight continues to be episodic and reactive, rather than continuous and proactive. To address this gap, we propose an architecture specifically designed to integrate auditing and inspection into metaverse-based healthcare and pharmaceutical supply chain environments. We integrate heterogeneous operational and sensor data with edge and cloud services, an analytics engine, and an immersive metaverse platform hosting interactive digital-twin models of facilities, logistics assets, and processes. We build on this infrastructure with a data lifecycle model supported by three algorithms for data collection, preprocessing, and analysis and risk assessment, enabling compliance-oriented monitoring and prioritization of anomalies and potential non-compliance events. We also consider constraints affecting metaverse-based audits, including technical limitations (i.e., connectivity, latency, device capabilities, and integration), regulatory requirements (i.e., data integrity, audit trails, and validation), and adoption and ethical considerations (i.e., training, human factors, privacy, and trust). Overall, we provide a structured blueprint for future implementations and empirical studies of immersive and data-driven audits in regulated metaverse-based healthcare and pharmaceutical supply chains.
APB-FLDPA: Adaptive Personalized Blockchain-Federated Learning With Differential Privacy and Attention for Privacy-Preserving Healthcare Analytics Md Kamran Hussin Chowdhury, Proloy Kumar Mondal, Md Ariful Islam Mozumder, Hee Cheol Kim, Haewon Byeon Healthcare Technology Letters, 2026 Developing robust medical artificial intelligence (AI) requires collaboration across multiple institutions, but strict data protection regulations such as HIPAA and GDPR prevent centralized patient data sharing. Existing federated learning (FL) methods often exhibit 15%–30% performance degradation in real‐world clinical settings due to data heterogeneity, security threats, and privacy constraints. We present APB‐FLDPA, a privacy‐preserving federated learning framework for secure multi‐hospital disease prediction. APB‐FLDPA integrates five key innovations: (i) adaptive Byzantine‐resilient aggregation using dynamic client trust scoring, (ii) self‐attention for automated clinical feature importance, (iii) selective differential privacy applied at the final aggregation stage, (iv) cluster‐aware personalization to handle cross‐institutional heterogeneity, and (v) a lightweight blockchain module to ensure model integrity. Evaluated across five institutions using large‐scale Diabetes (183,000 patients) and Thyroid (6840 patients) datasets, APB‐FLDPA achieved 90.8% accuracy for diabetes and 83.8% accuracy for thyroid disease, with minimal performance loss (<0.2%) compared to centralized learning. Statistical tests confirmed significant improvements, and selective differential privacy outperformed conventional methods by 5.6% in accuracy. These results show that APB‐FLDPA provides a scalable, high‐performance and privacy‐compliant solution for real‐world federated medical AI.
Empowering Home Security Through Wall-Crossing Activity Detection Using Vision Cameras and Convolutional Long Short-Term Architecture Muhammad Omair Khan, Haleem Farman, Md Ariful Islam Mozumder, Bilal Jan, Moustafa M. Nasralla, Hee-Cheol Kim IEEE Sensors Journal, 2025 Smart home automation (SHA) has significantly enhanced homes’ convenience, comfort, security, and safety. It has gained widespread use due to its intelligent monitoring and quick response capabilities. The current state of SHA enables effective monitoring and motion detection. However, false notifications remain a significant challenge, as they can cause unnecessary alarms in intrusion detection systems. To address this, we propose an intelligent model for a smart home security system (SHSS) that uses computer vision techniques to detect trespasser movement near the boundary wall. We employ a generalized convolutional long short-term memory (ConvLSTM) deep learning (DL) model to process a sequence of input video frames captured by a vision sensor (camera) positioned to monitor the boundary wall. The model extracts features from the frames using convolutional layers and learns temporal dependencies between consecutive frames using long short-term memory (LSTM) cells. Upon detecting suspicious activity, the system immediately alerts the homeowner. To support this, we created a large-scale dataset with various environmental conditions and scenarios, such as morning, afternoon, and night, focusing on wall crossing and intrusion detection. The dataset consists of 456 videos, with each class (normal and wall crossing) containing 228 videos. In computer vision, datasets are crucial for object detection. To the best of our knowledge, no publicly available dataset exists for wall crossing and intrusion detection at an early stage. Therefore, we took the initiative to fill this gap. We trained the ConvLSTM model using our dataset to achieve optimal results. The proposed model is compared with other convolutional neural network (CNN) models highlighted in the results section. The ConvLSTM model we proposed attained a validation accuracy of 95%, a test accuracy of 97%, an F1-score of 0.97, a precision of 0.98, and a recall of 0.97, surpassing other CNN-LSTM models such as Xception, ResNet50, VGG16, EfficientNetV2B0, MobileNet, DenseNet121, and ViVit. We have compared our proposed ConvLSTM model with several pretrained models (including ViViT), all of which were fine-tuned and evaluated on our newly generated wall-crossing intrusion dataset for a fair comparison. Our model outperforms these baselines in accuracy and efficiency. In addition, our system demonstrated a real-time inference speed of 0.10 s, making it well-suited for practical implementation in an SHSS.
ETRC-net: Efficient transformer for grading renal cell carcinoma in histopathological images Mohsin Raza, Umme E Farwa, Md Ariful Islam Mozumder, Joo Mon-il, Hee-Cheol Kim Computers and Electrical Engineering, 2025 Renal cell carcinoma (RCC), the most prevalent form of kidney cancer, accounts for nearly 85 % of kidney cancer-related deaths. Manual diagnosis of RCC from histopathology images relies heavily on the expertise of pathologists, often leading to variability in results. Although deep learning methods have been explored for disease diagnosis, research on RCC remains limited, and existing approaches are insufficient for accurate grading. Since each RCC stage requires a distinct treatment plan, reliable grading is crucial, as errors can result in inappropriate therapies and poor patient outcomes. To address this challenge, we propose the Efficient Transformer for Renal Classification Network (ETRC Net), a novel deep learning framework specifically designed for accurate RCC classification from histopathology images. ETRC Net combines EfficientNet with Squeeze-and-Excitation (SE) blocks for enhanced feature representation and a customized Vision Transformer encoder to capture global context and long-range dependencies. The SE blocks adaptively recalibrate channel-wise responses, enabling the model to focus on relevant features while suppressing less informative ones. We evaluate ETRC Net on the Kasturba Medical College (KMC) dataset, achieving 94.37 % accuracy, 94.54 % precision, 94.37 % recall, and an F1-score of 94.37 %. On the Lung and Colon dataset, it further demonstrates superior generalization with 99.92 % accuracy, 99.64 % precision, 99.71 % recall, and a 99.80 % F1-score. Compared to state-of-the-art methods, ETRC Net delivers higher accuracy with fewer trainable parameters and lower computational cost. Its efficiency and scalability make itfor resource constrained clinical environments, offering a robust and intelligent solution for early RCC diagnosis.
An Integrated Architecture for Colorectal Polyp Segmentation: The µ-Net Framework with Explainable AI Mehedi Hasan Emon, Proloy Kumar Mondal, Md Ariful Islam Mozumder, Hee Cheol Kim, Maria Lapina, Mikhail Babenko, Mohammed Saleh Ali Muthanna Diagnostics, 2025 Objectives: Colorectal cancer (CRC) is the second-deadliest cancer globally, with an estimated 52,900 additional deaths expected in the United States by 2025. Early detection through colonoscopy significantly reduces CRC mortality by enabling the removal of pre-cancerous polyps. However, manual visual inspection of colonoscopy images is time-consuming, tedious, and prone to human error. This study aims to develop an automated and reliable polyp segmentation and classification method to improve CRC screening. Methods: We propose a novel deep learning architecture called µ-Net for accurate polyp segmentation in colonoscopy images. The model was trained and evaluated using the Kvasir-SEG dataset. To ensure transparency and reliability, we incorporated Explainable AI (XAI) techniques, including saliency maps and Grad-CAM, to highlight regions of interest and interpret the model’s decision-making process. Results: The µ-Net model achieved a Dice coefficient of 94.02%, outperforming other available segmentation models in accuracy, indicating its strong potential for clinical deployment. Integrating XAI provided meaningful visual explanations, enhancing trust in model predictions. Conclusions: The proposed µ-Net framework significantly improves the Precision and efficiency of automated polyp screening. Its ability to segment, classify, and interpret colonoscopy images enables early detection and supports clinical decision-making. This comprehensive approach offers a valuable tool for CRC prevention, ultimately contributing to better patient outcomes.
A Lightweight Deep Learning and Sorting-Based Smart Parking System for Real-Time Edge Deployment Muhammad Omair Khan, Muhammad Asif Raza, Md Ariful Islam Mozumder, Ibad Ullah Azam, Rashadul Islam Sumon, Hee Cheol Kim Appliedmath, 2025 As cities grow denser, the demand for efficient parking systems becomes more critical to reduce traffic congestion, fuel consumption, and environmental impact. This paper proposes a smart parking solution that combines deep learning and algorithmic sorting to identify the nearest available parking slot in real time. The system uses several pre-trained convolutional neural network (CNN) models—VGG16, ResNet50, Xception, LeNet, AlexNet, and MobileNet—along with a lightweight custom CNN architecture, all trained on a custom parking dataset. These models are integrated into a mobile application that allows users to view and request nearby parking spaces. A merge sort algorithm ranks available slots based on proximity to the user. The system is validated using benchmark datasets (CNR-EXT and PKLot), demonstrating high accuracy across diverse weather conditions. The proposed system shows how applied mathematical models and deep learning can improve urban mobility through intelligent infrastructure.
Automatic Fracture Detection Convolutional Neural Network with Multiple Attention Blocks Using Multi-Region X-Ray Data Rashadul Islam Sumon, Mejbah Ahammad, Md Ariful Islam Mozumder, Md Hasibuzzaman, Salam Akter, Hee-Cheol Kim, Mohammad Hassan Ali Al-Onaizan, Mohammed Saleh Ali Muthanna, Dina S. M. Hassan Life, 2025 Accurate detection of fractures in X-ray images is important to initiate appropriate medical treatment in time—in this study, an advanced combined attention CNN model with multiple attention mechanisms was developed to improve fracture detection by deeply representing features. Specifically, our model incorporates squeeze blocks and convolutional block attention module (CBAM) blocks to improve the model’s ability to focus on relevant features in X-ray images. Using computed tomography X-ray images, this study assesses the diagnostic efficacy of the artificial intelligence (AI) model before and after optimization and compares its performance in detecting fractures or not. The training and evaluation dataset consists of fractured and non-fractured X-rays from various anatomical locations, including the hips, knees, lumbar region, lower limb, and upper limb. This gives an extremely high training accuracy of 99.98 and a validation accuracy 96.72. The attention-based CNN thus showcases its role in medical image analysis. This aspect further complements a point we highlighted through our research to establish the role of attention in CNN architecture-based models to achieve the desired score for fracture in a medical image, allowing the model to generalize. This study represents the first steps to improve fracture detection automatically. It also brings solid support to doctors addressing the continued time to examination, which also increases accuracy in diagnosing fractures, improving patients’ outcomes significantly.
KFYO: Fusing vision and biomechanics for accurate pitch evaluation in real-time baseball using deep learning techniques G Asad, MAI Mozumder, PK Mondal, RI Sumon, HC Kim Heliyon 12 (10) , 2026 2026
Integrating Auditing and Inspection into Metaverse-Based Healthcare and Pharmaceutical Supply Chains MM Sheeraz, MAI Mozumder, A Yousafzai, I Yaqoob 2026 28th International Conference on Advanced Communications Technology … , 2026 2026
APB‐FLDPA: Adaptive Personalized Blockchain‐Federated Learning With Differential Privacy and Attention for Privacy‐Preserving Healthcare Analytics MKH Chowdhury, PK Mondal, MAI Mozumder, HC Kim, H Byeon Healthcare Technology Letters 13 (1), e70079 , 2026 2026
NOVA: A Novel Multi-Scale Adaptive Vision Architecture for Accurate and Efficient Automated Diagnosis of Malaria Using Microscopic Blood Smear Images MN Hosen, MA Islam Mozumder, PK Mondal, H Cheol Kim Electronics 14 (24), 4861 , 2025 2025
MedAttnNet: A Novel Architecture for Precise Brain Cancer Classification PK Mondal, C Mondal, MAI Mozumder, DS Pham, HC Kim 2025 International Conference on Digital Image Computing: Techniques and … , 2025 2025
ETRC-net: Efficient transformer for grading renal cell carcinoma in histopathological images M Raza, UE Farwa, MAI Mozumder, J Mon-il, HC Kim Computers and Electrical Engineering 128, 110747 , 2025 2025 Citations: 3
A ResNet-50–UNet Hybrid with Whale Optimization Algorithm for Accurate Liver Tumor Segmentation PK Mondol, MA Islam Mozumder, H Cheol Kim, M Hassan Ali Al-Onaizan, ... Diagnostics 15 (23), 2975 , 2025 2025 Citations: 2
An Integrated Architecture for Colorectal Polyp Segmentation: The µ-Net Framework with Explainable AI MH Emon, PK Mondal, MAI Mozumder, HC Kim, M Lapina, M Babenko, ... Diagnostics 15 (22), 2890 , 2025 2025 Citations: 2
Empowering Home Security Through Wall Crossing Activity Detection Using Vision Cameras and Convolutional Long Short-Term Architecture MO Khan, H Farman, MAI Mozumder, B Jan, MM Nasralla, HC Kim IEEE Sensors Journal , 2025 2025 Citations: 1
Innovations and challenges of AI in film: a methodological framework for future exploration SMI Uddin, RI Sumon, MA Islam Mozumder, MK Hussin Chowdhury, ... ACM Transactions on Multimedia Computing, Communications and Applications 21 … , 2025 2025 Citations: 28
Automatic fracture detection convolutional neural network with multiple attention blocks using multi-region X-ray data RI Sumon, M Ahammad, MAI Mozumder, M Hasibuzzaman, S Akter, ... Life 15 (7), 1135 , 2025 2025 Citations: 11
Attention-Driven Self-Supervised Deep Learning for Ovarian Cancer Prediction and Classification Using Whole Slide MAI Mozumder, RI Sumon, ZU Khan, HC Kim 2025 5th International Conference on Electrical, Computer and Energy … , 2025 2025
Prediction of early diabetes using an XGBoost classifier and explaining the influence of the attributes on the metaheuristic algorithm PK Mondal, MAI Mozumder, RI Sumon, HC Kim 2025 5th International Conference on Electrical, Computer and Energy … , 2025 2025
Comparative study of cell nuclei segmentation based on computational and handcrafted features using machine learning algorithms RI Sumon, MAI Mozumdar, S Akter, SMI Uddin, MHA Al-Onaizan, ... Diagnostics 15 (10), 1271 , 2025 2025 Citations: 9
Foundation Models in Digital Pathology Imaging: Next-Generation AI for Healthcare Transformation MAI Mozumder, RI Sumon, MN Kaysar, I Ahmed, A Sumiraj, HC Kim 2025 1st International Conference on Secure IoT, Assured and Trusted … , 2025 2025 Citations: 1
Innovative Deep Learning Strategies for Early Detection of Brain Tumours in MRI Scans with a Modified ResNet50V2 Approach HCK Rashadul Islam Sumon, Md Ariful Islam Mazumder, Salma Akter, Shah ... 2025 27th International Conference on Advanced Communications Technology … , 2025 2025 Citations: 5
Skin cancer detection using transfer learning models and ensemble approach to enhanced diagnostic accuracy HC Kim, MAI Mozumder, RI Sumon, TPT Armand, M Omair 2025 27th International Conference on Advanced Communications Technology … , 2025 2025 Citations: 11
A deep Learning-Based approach for precise emotion recognition in domestic animals using EfficientNetB5 architecture RI Sumon, H Ali, S Akter, SMI Uddin, MAI Mozumder, HC Kim Eng 6 (1), 9 , 2025 2025 Citations: 27
Automated Pipeline for Robust Cat Activity Detection Based on Deep Learning and Wearable Sensor Data MAI Mozumder, TP Theodore Armand, RI Sumon, SM Imtiyaj Uddin, ... Sensors 24 (23), 7436 , 2024 2024 Citations: 8
Deep learning-based anomaly detection using one-dimensional convolutional neural networks (1D CNN) in machine centers (MCT) and computer numerical control (CNC) machines A Athar, MAI Mozumder, S Ali, HC Kim PeerJ Computer Science 10, e2389 , 2024 2024 Citations: 15
MOST CITED SCHOLAR PUBLICATIONS
Overview: Technology roadmap of the future trend of metaverse based on IoT, blockchain, AI technique, and medical domain metaverse activity MAI Mozumder, MM Sheeraz, A Athar, S Aich, HC Kim 2022 24th international conference on advanced communication technology … , 2022 2022 Citations: 433
Metaverse for digital anti-aging healthcare: an overview of potential use cases based on artificial intelligence, blockchain, IoT technologies, its challenges, and future … MAI Mozumder, TPT Armand, SM Imtiyaj Uddin, A Athar, RI Sumon, ... Applied Sciences 13 (8), 5127 , 2023 2023 Citations: 128
BFLIDS: Blockchain-driven federated learning for intrusion detection in IoMT networks K Begum, MAI Mozumder, MI Joo, HC Kim Sensors 24 (14), 4591 , 2024 2024 Citations: 90
Applications and possible challenges of healthcare metaverse A Athar, SM Ali, MAI Mozumder, S Ali, HC Kim 2023 25th International Conference on Advanced Communication Technology … , 2023 2023 Citations: 62
Natural language processing influence on digital socialization and linguistic interactions in the integration of the metaverse in regular social life RI Sumon, SMI Uddin, S Akter, MAI Mozumder, MO Khan, HC Kim Electronics 13 (7), 1331 , 2024 2024 Citations: 59
Technological Roadmap of the Future Trend of Metaverse based on IoT, Blockchain, and AI Techniques in Metaverse Education MAI Mozumder, A Athar, TPT Armand, MM Sheeraz, SMI Uddin, HC Kim ICACT Transactions on Advanced Communications Technology (ICACT-TACT), 1414-1423 , 2023 2023 Citations: 51
The metaverse applications for the finance industry, its challenges, and an approach for the metaverse finance industry MAI Mozumder, ATP Theodore, A Athar, HC Kim 2023 25th international conference on advanced communication technology … , 2023 2023 Citations: 44
Developing a low-cost IoT-based remote cardiovascular patient monitoring system in Cameroon TPT Armand, MAI Mozumder, S Ali, AO Amaechi, HC Kim Healthcare 11 (2), 199 , 2023 2023 Citations: 35
Exploring deep learning and machine learning techniques for histopathological image classification in lung cancer diagnosis RI Sumon, MAI Mazumdar, SMI Uddin, HC Kim 2024 International Conference on Electrical, Computer and Energy … , 2024 2024 Citations: 32
Innovations and challenges of AI in film: a methodological framework for future exploration SMI Uddin, RI Sumon, MA Islam Mozumder, MK Hussin Chowdhury, ... ACM Transactions on Multimedia Computing, Communications and Applications 21 … , 2025 2025 Citations: 28
A deep Learning-Based approach for precise emotion recognition in domestic animals using EfficientNetB5 architecture RI Sumon, H Ali, S Akter, SMI Uddin, MAI Mozumder, HC Kim Eng 6 (1), 9 , 2025 2025 Citations: 27
A deep CNN-based salinity and freshwater fish identification and classification using deep learning and machine learning W Rahman, MM Rahman, MAI Mozumder, RI Sumon, SA Chelloug, ... Sustainability 16 (18), 7933 , 2024 2024 Citations: 26
Blockchain system for trustless healthcare data sharing with hyperledger fabric in action MM Sheeraz, MAI Mozumder, MO Khan, MU Abid, MI Joo, HC Kim 2023 25th International Conference on Advanced Communication Technology … , 2023 2023 Citations: 20
Long short-term memory (LSTM)-based dog activity detection using accelerometer and gyroscope A Hussain, K Begum, TPT Armand, MAI Mozumder, S Ali, HC Kim, MI Joo Applied Sciences 12 (19), 9427 , 2022 2022 Citations: 19
Deep learning-based anomaly detection using one-dimensional convolutional neural networks (1D CNN) in machine centers (MCT) and computer numerical control (CNC) machines A Athar, MAI Mozumder, S Ali, HC Kim PeerJ Computer Science 10, e2389 , 2024 2024 Citations: 15
Enhanced Nuclei Segmentation in Histopathology Image Leveraging RGB Channels through Triple-Encoder and Single-Decoder Architectures HCK Rashadul Islam Sumon, Md Ariful Islam Mazumdar, Shah Muhammad Imtiyaj ... IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication … , 2023 2023 Citations: 14
AI-Based Logistics System Overview and a Workflow for Digital Freight Forwarding in Logistics MAI Mozumder, RI Sumon, Z Khan, SMI Uddin, MO Khan, HC Kim 2024 26th International Conference on Advanced Communications Technology … , 2024 2024 Citations: 12
Enhancing patient’s confidence and trust in remote monitoring systems using Natural Language Processing in the medical Metaverse TPT Armand, M Joo, MAI Mozumder, HC Kim, KS Carole International Conference on Intelligent Metaverse Technologies … , 2023 2023 Citations: 12
Automatic fracture detection convolutional neural network with multiple attention blocks using multi-region X-ray data RI Sumon, M Ahammad, MAI Mozumder, M Hasibuzzaman, S Akter, ... Life 15 (7), 1135 , 2025 2025 Citations: 11
Skin cancer detection using transfer learning models and ensemble approach to enhanced diagnostic accuracy HC Kim, MAI Mozumder, RI Sumon, TPT Armand, M Omair 2025 27th International Conference on Advanced Communications Technology … , 2025 2025 Citations: 11
