Designing remote Parkinson’s disease (PD) management systems requires critical decision-making in two phases: developing technologies to address gaps in existing systems, and designing treatment protocols (e.g., medication dosage). This research proposes a decision-making framework for PD remote monitoring, combining hardware/software analysis, patient needs, and cost factors. It introduces an AI-based decision support system for dynamic treatment planning, leveraging prior clinical data and technical specifications.
Healthcare IT advancements, like wearable devices and remote monitoring, have improved patient care. However, securing electronic health records (EHRs) remains a challenge due to weak security policies. Blockchain technology enhances data privacy, reliability, and transparency. For movement disorder patients—who require continuous care—this research proposes a blockchain-based remote monitoring system to ensure real-time treatment management, data integrity, and reduced security risks while minimizing clinic visits and costs.
Spatial awareness is a key human ability that enables environmental evaluation and navigation by integrating sensory data and spatial memory. It enhances cognitive navigation in complex settings (e.g., cities), improves spatial recall, and aids route optimization. Crucially, it allows humans to adapt to dynamic environments and leverage tools like maps for efficient wayfinding. Motion capture systems quantify this by analyzing joint kinematics and movement patterns during navigation tasks. This study will: (1) collect clinical questionnaires and motion data, (2) analyze behavioral patterns, and (3) develop an algorithm to assess cognitive navigation performance. The resulting framework will bridge motion analysis with real-world spatial challenges, offering insights for rehabilitation and assistive technologies.
Attention is a fundamental cognitive process that enables humans to focus limited mental resources on relevant stimuli. It plays a vital role in perception, memory, and decision-making. Different attention types exist, including selective, sustained, divided, and executive attention - crucial for goal-directed tasks. Measuring attention has become essential across fields like education and healthcare, as attention deficits impair daily functioning. While traditional paper-based tests exist, technological advances now enable computerized assessments using eye-tracking and motion analysis. This study develops an AI-based algorithm to evaluate attention by: (1) designing cognitive tests, (2) collecting eye movement and hand motion data via camera, and (3) analyzing patterns to create an accessible, reliable assessment tool.
Human decision-making is a complex cognitive process influenced by multiple factors. Eye-tracking technology has emerged as a powerful tool to study decision-making by revealing visual attention patterns and unconscious biases. This research integrates eye movements with machine learning and deep learning techniques to: (1) understand how gaze behavior reflects decision processes, (2) identify hidden influences on choices, and (3) improve decision outcomes. Data will be collected via cameras during cognitive tasks and then analyzed to correlate eye-tracking parameters with decision components. The goal is to develop an AI framework that decodes decision-making from eye kinematics, offering applications in human-computer interaction.
Inhibitory control (attentional and response inhibition) is a core executive function enabling the suppression of inappropriate responses. This research develops AI algorithms using motion-pattern analysis (eye and body movements captured mainly via camera) to assess inhibition. Machine learning and signal processing will extract biomarkers from kinematic data to evaluate inhibitory attention and measure response inhibition. The approach uniquely captures naturalistic behavioral signatures that traditional lab-based methods often miss. The developed tool addresses environmental noise (lighting, camera angle) and aims to replace costly equipment (EEG/eye-trackers) with accessible video-based analysis for clinical/behavioral applications.
Biomechatronic Systems Research Group - March 2025
Atiye received her B.Sc. in electrical engineering - electronics from Ferdowsi University of Mashhad, Mashhad, Iran. Her project was to design a motor speed controller for a photoresist spinner. She received her M.Sc. degree in bioelectric engineering from K. N. Toosi University of Technology. During her master's studies, she focused on the prediction of ventricular fibrillation using morphological features of ECG signal. Her work includes biomedical engineering in hospital-based health care, electrical installations testing, and safety observer of buildings as a member of Iran Construction Engineering Organization (IRCEO), and referee of science and technology park in electronics and bioelectric fields. Currently, Atiye is a Ph.D. student in bioelectric engineering at K. N. Toosi University of Technology. She is a member of Biomechatronic Systems research group and working on the implementation of a decision support system to help patients with Parkinson's disease.
Behnaz received her B.Sc. in software engineering and her M.Sc. in biomedical engineering from Hakim Sabzevari University, Sabzevar, Iran. Currently, she is a Ph.D. student in bioelectric engineering at K. N. Toosi University of Technology, where she is a member of the Biomechatronic Systems research group. Her research focuses on blockchain-based solutions for securing electronic health records and improving remote patient monitoring, particularly for movement disorders, to enhance data integrity and healthcare efficiency.
Akram, a Biomedical Engineer, specializes in biomedical signal processing, machine learning, and health care systems. She earned her bachelor's degree in Electrical Engineering from the University of Zanjan and a master's in Biomedical Engineering from K.N. Toosi University of Technology. As a researcher at the Biomechatronics Lab, she has played a crucial role in developing a hybrid algorithm that utilizes vital signs to classify the severity of COPD.
Arash is a Mechatronics Engineer experienced in developing AI-based solutions, with a strong focus on Human-Computer Interaction (HCI) and data analysis. He holds a B.Sc. in Mechanical Engineering from Shahid Chamran University of Ahvaz, where his final project titled "Development and implementation of a fuzzy logic controller for the navigation of an obstacle-avoiding mobile robot". He earned his M.Sc. in Mechatronics Engineering from K.N. Toosi University of Technology, with his master's thesis titled "Cognitive Load Classification Based on Electrooculography (EOG) and using Machine Learning". As a researcher at the Biomechatronics Lab, he has made significant contributions through his work on electrooculography-based cognitive load classification and has co-authored multiple published papers in prestigious conferences and journals.
Mobina received her B.Sc. in electrical engineering—communications from the University of Zanjan, Zanjan, Iran. Her undergraduate project focused on designing and implementing a weather station and transmitting data using RF signals. She is currently a M.Sc. student in mechatronics engineering at K. N. Toosi University of Technology, Tehran, Iran. As a member of the Biomechatronics Laboratory, her work integrates pose estimation, eye-tracking, and behavioral data to investigate spatial navigation and memory processes. She is passionate about incorporating technologies into human-centered systems to bridge the gap between mechatronics engineering and cognitive science and provide deeper insights into human cognition.
Sobhan received his B.Sc. in mechanical engineering from K. N. Toosi University of Technology, Tehran, Iran, and he is currently an M.Sc. student in mechatronics engineering at K. N. Toosi University of Technology. Sobhan is all about artificial intelligence!
Sepideh received her B.Sc. in Mechanical Engineering from K. N. Toosi University of Technology, Tehran, Iran. She is currently a M.Sc. student in Mechatronics Engineering at the same university. Her research focuses on artificial intelligence and image processing. Sepideh's master's thesis focuses on developing an algorithm to evaluate human attention based on movement patterns. Her research aims to predict attention and mindfulness scores using machine learning techniques by analyzing eye-tracking and mouse movement data. Her work integrates artificial intelligence and image processing to enhance attention assessment methodologies.
Farbod is pursuing his Bachelor’s degree in Electrical Engineering at K. N. Toosi University of Technology. His B.Sc. thesis centers on predicting mind-wandering episodes in real-world settings using a custom-designed experimental framework. By combining signal processing and machine learning, he aims to enhance understanding of attentional dynamics in everyday life.
Amir Mohammad is pursuing his B.Sc. in Electrical Engineering at K. N. Toosi University of Technology, majoring in Control Systems. As an active member of the Biomechatronics Lab, he contributes to projects involving motion analysis for human spatial problem-solving assessment. His academic interests include reinforcement learning, AI applications in biomechatronics, and brain-computer interfaces.