Biography:

Dr. Xiaohui Tao is an elected Senior Member of IEEE and ACM, an active researcher in AI, and Associate Professor (Computing) in School of Sciences, University of Southern Queensland (USQ), Australia. His research interests include data analytics, machine learning, knowledge engineering, information retrieval, and health informatics. During his research career, Tao gained a wealth of knowledge and experience in dealing with massive data sets and delivering solutions to complex research problems. He developed many innovative models, methods and systems, such as a multi-disease recommender system, a clinic decision support system for personalized and evidence-based medicine, a heterogeneous information graph model for health risk prediction, an algorithm to detect potential mental issues using sentiment analysis and natural language processing techniques, and an ontology learning and mining model for personalized information gathering, and made contributions to the areas such as Knowledge Engineering, Text Mining and Information Retrieval and Health informatics. The research outcomes have been published on many top-tier journals (e.g., TKDE, KBS, ESWA, IP&M, and PRL) and conferences (e.g., ICDE, CIKM, PAKDD and WISE). A/Prof. Tao is an Endeavour Research Fellow in 2015-16 and was awarded with Research Award by Department of Mathematics and Computing, USQ in 2012 and the Dean's Award for Academic Excellence by Faculty of Science and Technology at QUT in 2009. A/Prof. Tao has been active in professional services. He has served PC Chair in WI '17, '18, WI-IAT '21 and BESC '18 and '21. He has been an editor or guest editor in many journals including INFFUS and WWWJ, and also been a regular reviewer in many top-ranking journals such as TKDE, TPDS, Neural Networks, and Knowledge Based Systems. Dr. Tao has also been actively participating in tertiary education ever since 2005 and taught a variety of IT/IS subjects. Currently, he is leading the Data Mining and Analytics (DMA) Group in School of Sciences, USQ and is the Principal Supervisor of a number of PhD and Research Master students.

Speech title: Graph-based Multi-label Classification on Health Datasets

Abstract: In recent years, the means of disease diagnosis and treatment have been improved remarkably, along with the continuous development of technology and science. Researchers have spent tremendous time and effort to build models that aim to assist medical practitioners in decision-making support. However, one of the greatest challenges remains how to identify the connection between different diseases. This talk will report a recent study on a new multi-disease prediction model learning from NHANES, an extensive health related dataset, and MEDLINE, a corpus with medical domain knowledge. This study contributes to the medical community with a novel model for multi-disease prediction and represents a new endeavour on multi-label classification using knowledge graphs.