Wandering Detection and Activity Recognition for Dementia Patients Using Wireless Sensor Networks

摘要: A central goal of information technology is to improve human life. In terms useful in the area sensor networks, activity recognition (AR) has become a key feature. Using AR technology, it now possible understand behavior, including what, how and when people perform an activity. recent years, there been increase accident reports involving aged dementia patients, resulting higher social costs treat care for patients. can be utilized take monitor these this paper, we present efficient method that converts raw data readable patterns order classify individual's current activities then compare with previously stored detect any abnormal patterns, such as wandering, which one early symptoms dementia. We used digitize applied Levy-walk model wandering patterns. developed inference symptom based on digitized article, also illustrate implementation system configured tri-axis acceleration ultrasonic well estimation algorithm overcome limitations existing models detect/infer