One of the main concerns regarding the facilitation of the elderly well-being monitoring system is to preserve the participants’ privacy, enable the older adults to live longer independently, and support caregivers. Human Activity Recognition (HAR) in smart homes allows us to foresee the residents’ needs by identifying changes in behaviour that might link to possible health conditions. We propose a Federated learning (FL) model within the health monitoring application to generalize for diverse participant populations and to achieve comparable performance without disclosing the raw data to the traditional centralized approach, which raises privacy issues. In this study, we evaluate an unsupervised variational autoencoder (VAE) in centralized, individualized, compared to federated learning settings to learn the features of normal patterns of daily activities and build an anomaly detector based on reconstructed error resulting as outcomes by the trained model. Further, we validated our proposed approach on real-world datasets collected over three years from six single-resident elderly households. The individual and centralized-based learning models were used as a baseline to compare with FL. Our results show that the personalized FedAvg models achieve RMSE of about 1%, while the Global FL models achieve RMSE of approximately. 4%. The centralized model achieves RMSE of about 0.5%, and the RMSE of individual models based on local training ranges between 1% to 6%. The FL models are relatively comparable to the centralized baseline model.

Sleep is an essential activity that affects an individual’s health and ability to perform Activities of Daily Living (ADL). Inadequate sleep reduces cognitive capacity and leads to health-related issues such as cardiovascular diseases. Sleep disorders are more prevalent in older adults. Therefore, it is essential to recognize sleep patterns and support older adults and their caregivers. In our study, we collect data in real-world unconstrained and non-intrusive environments. This paper presents a novel sleep activity recognition method using motion sensors for recognizing nighttime and daytime sleep, which can further enable the development of insightful healthcare applications. The research objectives are to evaluate the application of using Multi-Armed Bandit methods to (i) learn normal sleep patterns, (ii) evaluate sleep quality, and (iii) detect anomalies in sleep activity for 11 elderly participants living in single-resident smart homes. We evaluate the performance of Thompson Sampling, Random Selection, and Upper Confidence Bound MAB methods. Thompson Sampling outperformed the other two methods. Our findings show most elderly participants slept between 6 and 8 hours with 85% sleep efficiency and up to 3 awakenings per night.

Virtual reality cloud-based gaming (VRCG) services are becoming widely available on virtual reality (VR) devices delivered over computer networks.VRCG brings users worldwide an extensive catalog of games to play anywhere and anytime. Delivering these gaming services in existing broadband mobile networks is challenging due to their stochastic nature and the user perceived Quality of Experience (QoE)' sensitivity towards them. More research is needed regarding developing effective methods to measure the impact of network QoS factors on users' QoE in the VRCG context. Therefore, this paper proposes, develops, and validates three novel regression models trained on a real dataset collected via subjective tests (N=30); the dataset contains subjective users' QoE ratings regarding VR shooters affected by network conditions (N=28), such as round-trip time (RTT), random jitter (RJ), and packet loss (PL). Our findings reveal that due to the nonlinear relationship of (RTT and RJ) tested together, nonlinear(mean absolute error (MAE)=0.14) and polynomial (MAE=0.15) regression models have the best performance; yet, simple linear regression model(MAE=0.19) is also suitable to predict QoE for VRCG. Further, we found that the model's most important feature is RTT, followed by (RTT, RJ). Finally, our models' prediction of QoE for real-world traffic measurements suggests that mobile network traffic (4G, 5G non-standalone, 5G standalone) provides a 2.5 \(\leq MOS\_{QoE} \leq\) 3.0 experience for VRCG, while 4.2 \(\leqMOS\_{QoE} \leq\) 4.4  for wired connections, suggesting the need for improvements in the current commercial 5G network deployments to deliverVRCG.

As the impact of global warming on climate change becomes noticeable, the importance of energy efficiency for reducing greenhouse gas emissions grows immense. To this end, a platform, solution, and mobile apps are developed as part of the European Union’s Horizon 2020 research and innovation program to support energy optimization in residences. However, to ensure long-term energy optimization, it is crucial to keep users engaged with the apps. Since augmented reality (AR) and a virtual animal companion positively influenced user engagement, we designed an AR companion that represented the user’s residence states; thereby making the user aware of indoor information. We conducted user evaluations to determine the effect of the AR companion on user engagement and perceived usability in the context of energy management. We identified that the user interface (UI) with AR (ARUI) barely affected user engagement and perceived usability compared to the traditional UI without AR (TUI); however, we found that the ARUI positively affected one of the user engagement aspects. Our results show AR companion integration’s potential benefits and effects on energy management mobile apps. Furthermore, our findings provide insights into UI design elements for developers considering multiple interaction modalities with AR.