2026
GIAFormer: A Gradient-Infused Attention and Transformer for Pain Assessment with EDA-fNIRS Fusion
Information Fusion, Vol. 131, Article 104173, 2026.
Researcher | Engineer | Educator
Muhammad Umar Khan
Signal Processing | AI in Healthcare | Multimodal Learning | Machine Learning | Neurophysiological Signal Analysis | Computer Vision
University of Canberra, Australia
I am a researcher and engineer with more than 10 years of experience in signal processing and artificial intelligence. My research focuses on machine and deep learning, multimodal learning, sensor fusion, physiological sensing, and intelligent system design. My work spans healthcare, biomedical engineering, human sensing, condition monitoring, and broader signal, image, and data-driven intelligent systems.
Biomedical Signals
Multimodal AI
Real-Time Systems
111
Publications
2086
Citations
26
h-index
59
i10-index
Google Scholar metrics · Updated October 2026
Research Areas
My research focuses on signal processing, artificial intelligence and multimodal learning for analysing complex biomedical, physiological, acoustic, vibration and visual data.
Signal Processing
Processing, analysis and intelligent modelling of physiological, neurophysiological, acoustic and vibration signals, including EEG, fNIRS, EDA, PPG/BVP, ECG, EMG, PCG, speech and vibration data, for healthcare, engineering and intelligent sensing applications.
Multimodal Learning
Multimodal learning, sensor and information fusion, and representation learning for integrating heterogeneous data sources, including time-series signals, images and videos.
Machine Learning
Feature engineering, representation learning, and predictive modelling, spanning classical machine learning to advanced deep learning methods for time-series signals, images and videos.
Image & Computer Vision
Machine and deep learning for image and video analysis, including medical imaging, object detection, visual recognition, and AI applications in healthcare, agriculture and other domains.
Selected Publications
Selected recent research contributions in signal processing, multimodal learning, neurophysiological sensing.
2026
Pain Intensity Estimation via Multimodal Fusion: Leveraging Ternary Textures of Derivatives in EDA and PPG Signals
Biomedical Signal Processing and Control, Vol. 112, Article 108532, 2026.
2025
A Systematic Review of Multimodal Signal Fusion for Acute Pain Assessment Systems
ACM Computing Surveys, Vol. 58, No. 2, pp. 1-35, 2025.
2025
Empirically Transformed Energy Patterns: A Novel Approach for Capturing fNIRS Signal Dynamics in Pain Assessment
Computers in Biology and Medicine, Vol. 192, Article 110300, 2025.
2025
DeriModNet: A Derivative-Aware Modulation Network for fNIRS-Based Pain Assessment
2025 12th International IEEE/EMBS Conference on Neural Engineering (NER), pp. 1152–1157, 2025.