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.

Cloud computing has been a game changer for internet-based applications such as content delivery networks, social networking and multi-tier enterprise applications. However, the requirements for low-latency data access, security, bandwidth, mobility, and cost have challenged centralized data center-based cloud computing models, which is driving the need for the novel computing paradigms of edge and fog computing. The internet of things (IoT) focuses on discovery, aggregation, management, and acting on data originating from internet-connected devices via programmable sensors, actuators, mobile phones, surveillance cameras, routers, gateways and switches. But the aggregation of this data is expensive and can be time consuming.

Traditional cloud-centric resource management models need to move towards more distributed and decentralized models so that they can cope with the challenges posed by the evolution of IoT smart devices and network solutions. However, supporting IoT data processing across cloud and edge data centers is not a trivial challenge. IoT sensing devices must be configured as a collection of data-analytics driven workflows where each node in the process can essentially run on multiple heterogeneous cloud and edge data centers.

This book presents state-of-the-art interdisciplinary computing research in the application lifecycle management for internet of things in edge and cloud computing. The book addresses challenges from a distributed system perspective that includes both cyber and physical aspects. The authors aim to bring together the four paradigms of cloud and edge computing, cyber physical systems, internet of things and big data for future ICT systems.

Written and edited by an international team of experts in the field, this book offers key insights to researchers, engineers, IT professionals, advanced students, postgraduate students and lecturers working in the fields of parallel and distributed computing, data mining, information retrieval, cloud, edge and fog computing, and the IoT.

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.

A Service Level Agreement (SLA) establishes the trustworthiness of service providers and consumers in several domains; including the Internet of Things (IoT). Given the proliferation of Blockchain technology, we find it compelling to reconsider the assumption of trust and centralised governance typically practised in SLA management including monitoring, compliance assessment, and penalty enforcement. Therefore, we argue that, such critical tasks should be operated by blockchain-based smart contracts in a non-repudiable manner beyond the influence of any SLA party. This paper envisions an IoT scenario wherein a firefighting station outsources end-to-end IoT operations to a specialised service provider. The contractual relationship between them is governed by an SLA which stipulates a set of quality requirements and violation consequences. The main contribution of this paper lies in designing, deploying and empirically experimenting a novel blockchain-based SLA monitoring and compliance assessment framework in the context of IoT. This is done by utilising Hyperledger Fabric (HLF), an enterprise-grade blockchain technology. Our work highlights a set of considerations and best practice at two sides, the IoT application monitoring-side and the blockchain-side. Moreover, it experimentally validates the reliability of the proposed monitoring approach, which collects relevant metrics from each IoT component and examines them against the quality requirements stated in the SLA. Finally, we propose a novel design for smart contracts at the blockchain-side, analyse and benchmark the performance, and demonstrate that the new design proves to successfully handle Multiversion Concurrency Control (MVCC) conflicts typically encountered in blockchain applications, while maintaining sound throughput and latency.