IoT-Based Home Monitoring: Supporting Practitioners’ Assessment by Behavioral Analysis

Abstract

This paper introduces technical solutions devised to support the Deployment Site - Regione Emilia Romagna (DS-RER) of the ACTIVAGE project. The ACTIVAGE project aims at promoting IoT (Internet of Things)-based solutions for Active and Healthy ageing. DS-RER focuses on improving continuity of care for older adults (65+) suffering from aftereffects of a stroke event. A Wireless Sensor Kit based on Wi-Fi connectivity was suitably engineered and realized to monitor behavioral aspects, possibly relevant to health and wellbeing assessment. This includes bed/rests patterns, toilet usage, room presence and many others. Besides hardware design and validation, cloud-based analytics services are introduced, suitable for automatic extraction of relevant information (trends and anomalies) from raw sensor data streams. The approach is general and applicable to a wider range of use cases; however, for readability’s sake, two simple cases are analyzed, related to bed and toilet usage patterns. In particular, a regression framework is introduced, suitable for detecting trends (long and short-term) and labeling anomalies. A methodology for assessing multi-modal daily behavioral profiles is introduced, based on unsupervised clustering techniques. The proposed framework has been successfully deployed at several real-users’ homes, allowing for its functional validation. Clinical effectiveness will be assessed instead through a Randomized Control Trial study, currently being carried out.

Pilot Site Deployment of an IoT Solution for Older Adults’ Early Behavior Change Detection

“…The systems proposed in these cases are dedicated to some specific scenarios and use-cases and are not for generic use by elderly people. There exist some works that have investigated behavior change and anomaly detection over the time [19][20][21]; however, these works have not carried health and medical correlation with the detected changes and anomalies in order to take appropriate interventions.Regarding research works that have investigated medical and health related behavior change, we can distinguish four main categories: The first category targets "Short-term Health Change Detection" occurring in specific time periods, such as falls and wandering during sleep [22,23]. The second category retrospectively investigates possible changes after change occurrence [24,25].…”

“…The systems proposed in these cases are dedicated to some specific scenarios and use-cases and are not for generic use by elderly people. There exist some works that have investigated behavior change and anomaly detection over the time [19][20][21]; however, these works have not carried health and medical correlation with the detected changes and anomalies in order to take appropriate interventions.…”

The Future of Emerging IoT Paradigms: Architectures and Technologies

“…A different approach would be appropriate if a different type of behavior is being monitored. In [99], the behavior being analyzed is to be used for health purposes so that changes may be made to a patient's care or action may be taken in case of an emergency. Sensors that monitored behavior regarding the subjects is drastically more specialized.…”

“…End-to-end protection is provided by Transport Layer Security (TLS) over TCP/IP protocol and Message Queue Telemetry Transport (MQTT) sends periodic measurements by using the publish/subscribe mechanism. The MQTT is a protocol that, according to [99], relies on a broker to send and receive data between subscribers and publishers. With this configuration, Wi-Fi enabled sensors can send measurements and receive commands over SSH sessions.…”

“…The figure also depicts the protocol stack through which the traffic has been configured to flow. Figure 11 below shows the architecture deployed in [99] used to sense, collect, and process health behaviors throughout a home and present that information to caregivers. It interfaces with IBM Watson for data processing in the cloud.…”