A Real-Time Detection of Patient's Aggressive Behaviors on a Smart Sensor

Patient aggression in older people with dementia is one of the most challenging problems of medical care in today's nursing homes. Existing wireless autography-based technologies help caregivers to collect data related to behavioral and psychological symptoms of dementia. However, their inability to process the data in real-time reduces the efficiency of patient assessment and affects the quality of care. In this paper we present a computationally inexpensive technique that identifies aggressive behaviors on a sensor that measures the wrist acceleration of the dominant patient hand. Experiments show that the technique effectively detects aggressive behaviors in real-time and significantly reduces the wireless data transmissions.