Behavioral and Environmental Sensing and Intervention for Dementia Caregiver Empowerment (BESI) is a system of body-worn and in-home sensors developed to provide continuous, non-invasive agitation assessment and environmental context monitoring to detect early signals of agitation and environmental triggers. The goal to detect early stages of agitation in persons with dementia (PWD) opens up new and promising technological development of cyber-human systems to enable early caregiver intervention. Caregivers shoulder most of the burden of dementia caregiving, and the BESI project seeks to reduce burden and improve caregiver self-efficacy. This mixed methods, remote ethnographic study is explored in a 3-phase, multi-year plan. In Phase 1 we developed the BESI system, completed usability studies in Alzheimer's Disease support groups using the Systems Usability Scale (SUS), and refined the system. Dyads (caregivers + PWD) who live at home are studied for 30 days in Phase 2 with continuous data collection during the deployment period. A tablet application for caregivers is used to log PWD activities, agitation events, and input markers of caregiver self-efficacy. Using wearable wrist technology (e.g. Pebble®), agitation severity level, physical, behavioral, and social activities of the PWD are captured. Post-deployment surveys of all ten dyads provided data on the system usability from questions posed with Likert-type scaling response ratings between 1 and 6 plus qualitative feedback. Between phases 1 & 2, the tablet application was updated to enhance interface usability for caregivers. Scores for the ten questions (rated 1-6) on ease of use of the tablet were in the very easy range (5.11 - 5.90). Agreement on use of the table device yielded SUS scores (rated 1-5) with range of 2.67 - 4.56. Preliminary analysis of the subjective feedback indicates overall positive impressions in working with the technologies. Phase 2 results facilitated targeted changes in BESI, improving overall usability for the final phase of the study. Caregivers consistently demonstrated willingness to help – including working with technologies previously unfamiliar. These subject-oriented design decisions influenced the team in understanding caregiver and PWD dyad interactions with technologies. The full qualitative report will be available in June 2019.

Dementia caregiver burden associated with patient agitation is one of the most common reasons for the institutionalization of a person with dementia. We developed an integrative sensing, analytics, modeling, and intervention system that detects early signs of agitation and notifies the caregiver to intervene before escalation.

Sensing driven behavior modeling is vital in health applications. Recent advances in machine learning and sensing technologies accelerate such efforts. While wearables facilitate continuous sensing, they lack the computational resources for on-board heavy-weight signal processing and model-based prediction. Moreover, continuous transmission to a remote server drains much energy to achieve reasonable battery life for practical use. The BESI (Behavioral and Environmental Sensing and Intervention) system addresses these challenges to achieve continuous and real-time prediction-based tracking of human behavior. It employs a network of embedded nodes to ensure continuous connection with the wearables, and distributes the feature extraction and the model prediction tasks among these nodes and a local server to achieve real-time performance. In a dementia case-study, the BESI system is used for tracking agitated behavior in patients. It has been deployed in 12 residences of dementia patients, each for 30 days; and is planned for 10 more 60-day deployments. The system operation, behavior modeling method, and some preliminary result on tracking performance are presented here along with a discussion on future plan for platform optimization and model performance improvement.

In-home monitoring applications often need strong and reliable contextual information to be of value. Indoor location tracking can play an important role in providing this context. However, most current indoor tracking solutions require extensive, application-specific knowledge and pre-deployment preparation, often including detailed information about floorplans and RF signal strength calibration, which is not practical in many deployments. This paper introduces an edge-based location monitoring technique that uses doorway sensors to detect doorway crossing events with walking directions. The approach is designed to provides room-level tracking. Users movement from a wearable device is used in conjunction with the edge-monitored approach to track multiple people. This method also enables the tracked location and doorway crossing events to be transformed into states and state transitions, respectively. This provides an opportunity to implement stochastic models to the edge-based location tracking to correct tracking errors and improve its accuracy, as demonstrated in simulation. This location tracking method has been implemented and deployed in a health monitoring study on dementia-related agitation.