Abdulnasir Hossen
Biography
Prof. Abdulnasir Hossen is a distinguished scholar in the fields of artificial intelligence and signal processing, currently serving as the UNESCO Chair on Artificial Intelligence at the Communication and Information Research Center, Sultan Qaboos University (SQU), Oman. He earned his Ph.D. from Ruhr-University, Bochum, Germany, in 1994 and has been a faculty member in the Department of Electrical and Computer Engineering at SQU since 1999, where he was promoted to full professor in 2013. Prof. Hossen has made significant contributions to the academic and research community, with nearly 100 publications in international journals and conferences, and he has been actively engaged in advancing AI education and innovation through his leadership in major events such as FOSSC 2019, the International Symposium on Telemedicine and AI in Medicine (2020), the International Symposium on FOSS for Intelligent Education and Digital Economy (2022), and the forthcoming International Conference on Artificial Intelligence: Applications, Innovation and Ethics (2025). A senior member of IEEE, Prof. Hossen continues to play a pivotal role in shaping the future of AI research, applications, and ethics in the region and beyond.
Research Interest
Artificial Intelligence (AI) - theory, applications, and ethical aspects, Signal Processing - algorithms, methods, and applications, Telemedicine & AI in Medicine - applying AI to healthcare and remote medical technologies
Abstract
Artificial Intelligence in Medicine: New Identification and Discrimination Results of Biomedical Signals:
To streamline the diagnostic process in daily routine and avoid misdiagnosis, artificial intelligence methods (especially computer aided diagnosis and artificial neural networks (ANN)) can be employed. These adaptive learning algorithms can handle diverse types of medical data and integrate them into categorized outputs. Different ANNs are to be used from simple perceptron to convolutional neural network (CNN) in diagnoses. Different Machine learning algorithms such as KNN and SVM are to be used also in the identification systems.
Sleep apnea which is defined as a complete or partial stop of breath during sleep, is one of the most common types of respiratory-related sleep disorders. Patients with sleep apnea (SA) suffer from snoring, but not all the people who snore have sleep apnea. Many researchers find a clear correlation between severe sleep apnea and cardiovascular diseases.
Heart failure is a common condition that usually develops slowly as the heart muscle weakens and needs to work harder to keep blood flowing through the body. Heart failure develops following injury to the heart such as the damage caused by heart attack, long-term high blood pressure, or an abnormality of one of the heart valves. Heart failure is often not recognized until a more advanced stage of heart failure, commonly referred to as congestive heart failure (CHF), in which fluid may leak into the lungs, feet, and in some cases the liver or abdominal cavity.
Essential tremor (ET) and the tremor in Parkinson' s disease (PD) are the two most common pathological tremors with a certain overlap in the clinical presentation. The main purpose is to use ANN to select the best features and to discriminate between the two types of tremors using spectral analysis of tremor time-series recorded by accelerometer and surface EMG signals.
AI and ML algorithms are to be applied on identification of OSA from normal subjects and CHF from normal subjects and to discriminate PD from ET.
