Signal processing based psychophysiological data analysis and ailment prediction for sport training

点击翻译按钮获取中文摘要

A variety of mobile applications have been introduced to market for health and fitness management. These applications allow users to record their health related data. However, they do not currently possess advanced technology and analytical tools to elaborate the hidden relationship in the data, let alone to forecast the possible illness, injury, and burnout risk in athletes (collectively known as "ailment" risks).****This research is a collaborative effort between Ryerson University and RightBlue Labs to utilize advanced statistical analysis, signal processing, and machine learning to: (i) investigate relationships between psychophysiological data, including measured psychological, activity, and physiological data, and various known health/performance indicators; and (ii) develop a set of analytical algorithms to predict/monitor health status and assess illness, injury, and burnout risks in athletes (ailment risks), with the potential to extend these findings to the general population.****Theory and application development from this research will build a strong technology foundation for mobile health monitoring and consultation systems with a strong commercial application focus, and provide a solid framework, useful guidelines, and tested algorithms for future research. This collaborated project will help Ryerson University to train highly qualified personnel and develop advanced expertise in health management research and big data analytics, and help RightBlue Labs and related Canadian industries to build and sustain market advantages.****