mHealth Application for Fall Detection
This research activity is aiming to realize an innovative approach to discriminate in real time falls from normal daily activities on the basis of the automatic extraction of knowledge expressed as a set of IF-THEN rules.
Several methods already exist to perform this task, but approaches able to provide explicit formalized knowledge and high classification accuracy have not yet been developed and would be highly desirable.
The realized approach is based on the automatic extraction of knowledge expressed as a set of IF-THEN rules from a database of fall recordings. This set of rules, generated offline through the DEREx tool, could then be exploited in a real-time mobile monitoring system.
The approach has been compared against four other classifiers on a database of falls simulated by volunteers, and its discrimination ability has been shown to be higher with an average accuracy of 91.88%.
- G.Sannino, I. De Falco and G. De Pietro, "Automatic Extraction of an Effective Rule Set for Fall Detection for a Real-Time Mobile Monitoring System", In Proceedings of the 6th International Conference on Developments in eSystems Engineering (DeSE2013), Abu Dhabi.
- G. Sannino, I. De Falco and G. De Pietro, "Effective supervised knowledge extraction for an mHealth system for fall detection", in Proceedings of the XIII Mediterranean Conference on Medical and Biological Engineering and Computing (MEDICON2013), Sevilla, Spain.