The measurement and detection of overnight wandering is a significant issue for dementia patients and their caregivers such as a spouse. The wandering places the patient at risk of injury or even death if they fall or leave their residence without being detected. While it also causes stress and reduced sleep for the caregiver as they try to remain alert to the actions of their partner. This paper presents initial data for the first participant from an ongoing study of dementia patients where a wander detection and diversion system based on low-cost commercial sensors has been deployed into the residence. The paper shows that over a 3-week period, the analysis and classification of the sensor data is able to measure the behavior of the patient. In this period, the patient only used the washroom overnight and did not wander into other parts of the residence. These early results show that an off the shelf system targeted for residential security and home automation applications based on low-cost sensors supported with automated analysis and classification has the potential to be used to assist caregivers and dementia patients.
2018 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2018
Department of Systems and Computer Engineering

Wallace, B. (Bruce), Harake, T.N.E. (Tarek Nasser El), Goubran, R, Valech, N. (Natalia), & Knoefel, F. (2018). Preliminary results for measurement and classification of overnight wandering by dementia patient using multi-sensors. In I2MTC 2018 - 2018 IEEE International Instrumentation and Measurement Technology Conference: Discovering New Horizons in Instrumentation and Measurement, Proceedings (pp. 1–6). doi:10.1109/I2MTC.2018.8409727