Prof. Dr. Xu Huang, University of Canberra, Australia
Professor (Dr) Xu Huang, Engineering of Electronics and Electrical and Network Professor, currently is working at Faculty of Education Science Technology & Mathematics, University Canberra, Australia Capital City. He has received the B.E. and M.E. degrees and first Ph.D. in Electrical Engineering and Optical Engineering prior to 1989 and his second Ph.D. in Experimental Physics in the University of New South Wales, Australia in 1992. He has earned the Graduate Certificate in Higher Education in 2004 at the University of Canberra, Australia. He was working at the Australia National University from 1988 to 1990 and University of New South Wales from 1990 to 1995, also University of New England from 1995 to 2001. He has been working on the areas of cybersecurity, network security, the telecommunications, networking engineering, Internet of Things (IoT), Clouding computing, software engineering, wireless communications, optical communications, digital signal processing, bio-signal processing, brain computer interface (BCI), intelligent system, smart networks, and nuclear physics more than 30 years. He has been a senior member of IEEE in Electronics and in Computer Society since 1989 and a Fellow of Institution of Engineering Australian (FIEAust), Chartered Professional Engineering (CPEng), a Member of Australian Institute of Physics. He was a member of the Executive Committee of the Australian and New Zealand Association for Engineering Education, he has been a member of Committee of the Institution of Engineering Australia at Canberra Branch for last 10 years. Prof Xu Huang has been the Chair, Co-Chair, and TCM at various high quality International Conferences, and Editor for various high quality Journals. Professor Huang has edited ten books, nine Book Chapters, more than 45 Journal Articles, and more than two hundred papers in high level of the IEEE and other international conferences (within ERA ranking); he has been awarded 17 patents in Australia in 2010 and 2013. Professor Xu Huang has more than ten PhD candidates obtained their PhDs under his primary supervisions. He has also more than 10 PhD candidates with his and his cosupervision.
More Information, including publication please refer to website:
Speech Title: Neuroimaging Conjunction with Machine Learning for Applications of fNIRS for Human Pain
Abstract: Pain diagnosis for nonverbal patients represents a big challenge in clinical settings. However, neuroimaging methods such as functional magnetic resonance imaging and functional near-infrared spectroscopy (fNIRS), have shown some promising results to assess neuronal function in response to nociception and pain. Recent studies strongly suggest that neuroimaging in conjunction with machine learning models can be used to not only facilitate but also predict different cognitive tasks on this challenge. The aim of this research is to expand our previous studies by exploring the classification of fNIRS signals (oxyhaemoglobin) according to temperature level (cold and hot) and corresponding pain intensity (low and high) using machine learning models. In our research, we defined and used the quantitative sensory testing to determine pain threshold and pain tolerance to cold and heat in 18 healthy subjects (three females), with, mean age _ standard deviation, being 31.9 _ 5.5. The classification model is based on the bag-of-words approach, a histogram representation used in document classification based on the frequencies of extracted words and adapted for time series; two learning algorithms were used separately, K-nearest neighbor (K-NN) and support vector machines (SVM). A comparison between two sets of fNIRS channels was also made in the classification task, all 24 channels and 8 channels from the somatosensory region defined as our region of interest. The results showed that K-NN obtained slightly better results (92.08%) than SVM (91.25%) using the 24 channels; however, the performance slightly dropped using only channels from the region of interest with K-NN (91.53%) and SVM (90.83%). These research results indicate potential applications of fNIRS in the development of a physiologically based diagnosis of human pain that would benefit vulnerable patients who cannot self-report pain including in clinical settings.