Sound classification for event detection: Application into medical telemonitoring

This paper presents results of our study in order to build an automatic alarm system using sound analysis which can be used for medical telemonitoring. The system will raise the alarm if it detects abnormal sounds coming from abnormal situations in a patient/aged person´s room. Our work consists of building three sound corpora and developing a sound analysis algorithm consisting of three sound discriminators. The obtained results of above 95% events correct recognition rate are promising for the first studies.