Background: The continuous growth of the older adult population will have implications for the organization of health and social care. Potentially, in-home monitoring unobtrusive sensing systems (USSs) can be used to support formal or informal caregivers of older adults, as they can monitor deviant physical and physiological behavior changes. Most existing USSs are not specific to older adult care. Hence, to facilitate the implementation of existing USSs in older adult care, it is important to know which USSs would be more suitable for older adults. Objective: This scoping review aims to examine the literature to identify current USSs for monitoring human activities and behaviors and assess their implementation readiness for older adult care. Methods: We conducted a structured search in the Scopus, Web of Science, and ACM Digital Library databases. Predefined inclusion criteria included studies on unobtrusive sensor-based technology; experimental in nature; aimed at monitoring human social, emotional, physical, and physiological behavior; having the potential to be scalable in in-home care; and having at least 5 adults as participants. Using these criteria, we screened studies by title, abstract, and full text. A deductive thematic analysis based on the Proctor implementation framework along with an additional outcome of external validity was applied to the included studies to identify the factors contributing to successful implementation. Finally, the identified factors were used to report the implementation readiness of the included studies for older adult care. Results: In this review, 52 studies were included. Deductive analysis using the implementation framework by Proctor resulted in six factors that can contribute to the successful implementation of USSs in older adult care: study settings, age of participants, activities monitored, sensor setup, sensing technology used, and usefulness of USSs. These factors were associated with the implementation outcomes as follows: study settings and age of participants contributed to external validity, sensor setup contributed to acceptability, usefulness of USSs contributed to adoption, activities monitored contributed to appropriateness, and sensing technology used contributed to implementation cost. Furthermore, the implementation assessment of the included 52 studies showed that none of the studies addressed all the identified factors. This assessment was useful in highlighting studies that have addressed multiple factors; thus, these studies represent a step ahead in the implementation process. Conclusions: This review is the first to scope state-of-the-art USSs suitable for older adult care. Although the included 52 USS studies fulfilled the basic criteria to be suitable for older adult care, systems leveraging radio frequency technology in a no-contact sensor setup for monitoring life risk or health wellness activities are more suitable for older adult care. Finally, this review has extended the discussion about unobtrusiveness as a property of systems that cannot be measured in binary because it varies greatly with user perception and context.

Agitation is a commonly found behavioral condition in persons with advanced dementia. It requires continuous monitoring to gain insights into agitation levels to assist caregivers in delivering adequate care. The available monitoring techniques use cameras and wearables which are distressful and intrusive and are thus often rejected by older adults. To enable continuous monitoring in older adult care, unobtrusive Wi-Fi channel state information (CSI) can be leveraged to monitor physical activities related to agitation. However, to the best of our knowledge, there are no realistic CSI datasets available for facilitating the classification of physical activities demonstrated during agitation scenarios such as disturbed walking, repetitive sitting–getting up, tapping on a surface, hand wringing, rubbing on a surface, flipping objects, and kicking. Therefore, in this paper, we present a public dataset named Wi-Gitation. For Wi-Gitation, the Wi-Fi CSI data were collected with twenty-three healthy participants depicting the aforementioned agitation-related physical activities at two different locations in a one-bedroom apartment with multiple receivers placed at different distances (0.5–8 m) from the participants. The validation results on the Wi-Gitation dataset indicate higher accuracies ($F_1$-Scores $\ge 0.95$) when employing mixed-data analysis, where the training and testing data share the same distribution. Conversely, in scenarios where the training and testing data differ in distribution (i.e., leave-one-out), the accuracies experienced a notable decline ($F_1$-Scores $\le 0.21$). This dataset can be used for fundamental research on CSI signals and in the evaluation of advanced algorithms developed for tackling domain invariance in CSI-based human activity recognition.

The demand for smart solutions to support people with dementia (PwD) is increasing. These solutions are expected to assist PwD with their emotional, physical, and social well-being. At the moment, state-of-the-art works allow for the monitoring of physical well-being; however, not much attention is delineated for monitoring the emotional and social well-being of PwD. Research on emotion monitoring can be combined with research on the effects of music on PwD given its promising effects. More specifically, knowledge of the emotional state allows for music intervention to alleviate negative emotions by eliciting positive emotions in PwD. In this direction, the paper conducts a state-of-the-art review on two aspects: (i) the effect of music on PwD and (ii) both wearable and non-wearable sensing systems for emotional state monitoring. After outlining the application of musical interventions for PwD, including emotion monitoring sensors and algorithms, multiple challenges are identified. The main findings include a need for rigorous research approaches for the development of adaptable solutions that can tackle dynamic changes caused by the diminishing cognitive abilities of PwD with a focus on privacy and adoption aspects. By addressing these requirements, advancements can be made in harnessing music and emotion monitoring for PwD, thereby facilitating the creation of more resilient and scalable solutions to aid caregivers and PwD.

This paper explores the use of federated learning in a realistic household employing existing infrastructure to add new devices and locations by rotating the role of the transmitter among smart devices in a multi-person scenario. Current solutions employ channel state information-based sensing for health care monitoring in various ways to propagate knowledge efficiently; however, these solutions often consider (i) ideally placed devices in (ii) single-participant scenarios and (iii) do not consider the different roles of these devices in a network. Data is collected from four smart devices in a household, assuming three participants, one of which is monitored and the other two function as noise, are assigned to perform activities to replicate a realistic household scenario. Insights are provided on using federated learning in realistic at-home health care when adding a new activity location and client devices, both transmitter-only and full communication devices. Results indicate new devices and locations can quickly be adopted with less data by the federated model without intensive retraining, even in multi-person environments, when doing extensive pre-training.