BioSignal-AI Research Lab: Advancing Biomedical Intelligence

Explore cutting-edge developments in biosignal analysis, machine learning algorithms, and AI-driven health technologies. BioSignal-AI Research Lab pioneers innovative solutions for biomedical data interpretation and intelligent healthcare systems.

Ongoing Research Projects

Intelligent Point-of-Care Device for Real-Time Pneumothorax Diagnosis

  • Dr. Moin Bhuiyan’s research is centered on developing innovative techniques for the rapid and accurate diagnosis of Pneumothorax, a potentially life-threatening lung condition. He has devoted several years to the development of a Portable Pulmonary Injuries Diagnostic Device (PPIDD), engineered to detect Pneumothorax on-site, enabling timely and effective medical intervention.
  • The device integrates advanced signal acquisition and processing technologies, with Dr. Bhuiyan employing state-of-the-art signal processing methods to accurately analyze and characterize pulmonary percussion signals.
  • Through extensive research and experimentation, he optimized the signal processing pipeline, achieving significant improvements in diagnostic accuracy and reliability.
  • Building on this foundation, Dr. Bhuiyan’s current research leverages machine learning (ML) and deep learning (DL) to further enhance the speed, precision, and robustness of Pneumothorax detection. By applying intelligent algorithms to pulmonary signal datasets, he aims to develop a highly accurate, AI-driven diagnostic framework that can be seamlessly incorporated into portable, real-time clinical devices.
  • This groundbreaking work has the potential to transform point-of-care lung diagnostics by uniting biomedical signal processing, wearable sensor technologies, and artificial intelligence, providing rapid, reliable, and non-invasive detection of critical pulmonary conditions.

Brain Tumor Detection and Classification Using Deep Learning

  • Early and accurate detection of brain tumors is crucial for effective treatment and improved patient outcomes.
  • This research presents a deep learning-based framework for automated brain tumor detection and classification using Magnetic Resonance Imaging (MRI).
  • The proposed model employs Convolutional Neural Networks (CNNs) and transfer learning to extract discriminative features and classify tumors into three primary types: glioma, meningioma, and pituitary tumors, along with healthy controls.

 

AI-Enabled Sensor System for Early Detection of Bed Sores/Pressure Ulcers

  • This project aims to develop a smart sensor system for the early detection of bed sores (pressure ulcers) in patients with limited mobility.
  • The system will integrate advanced sensors to monitor pressure, temperature, and moisture at key skin contact points.
  • Using artificial intelligence algorithms, the collected data will be analyzed in real-time to identify early signs of tissue damage, enabling timely intervention.
  • The proposed solution has the potential to improve patient care, reduce complications, and enhance overall healthcare outcomes.

AI-Driven Intelligent Prosthetic Hand: Design, Development, and Control for Enhanced Dexterity and User Adaptability

  • The integration of artificial intelligence (AI) with next-generation prosthetic hand systems promises to significantly enhance the functionality, adaptability, and usability of upper-limb prostheses.
  • This research focuses on the design and development of an AI-driven intelligent prosthetic hand capable of providing natural and precise control for amputees.
  • The system will utilize surface electromyography (sEMG) signals and potentially other biosignals to decode user intent through advanced machine learning and deep learning algorithms.
  • A multi-modal sensing framework will be implemented, combining force, position, and motion sensors to achieve smooth and adaptive grasping patterns. AI-based classification models will be trained to distinguish complex hand gestures, enabling real-time control and personalized adaptability to individual users.
  • The project also aims to develop an energy-efficient embedded system for on-board processing and wireless connectivity, ensuring portability and practical usability.
  • By integrating biomedical signal processing, AI-driven control strategies, and ergonomic hardware design, this research strives to create a highly functional prosthetic hand that closely mimics natural human hand movements, ultimately improving the quality of life for upper-limb amputees.