The revolution in information technologies, and the spread of the Internet of Things (IoT) and smart city industrial systems, have fostered widespread use of smart systems. As a complex, 24/7 service, healthcare requires efficient and reliable follow-up on daily operations, service and resources. Cloud and edge computing are essential for smart and efficient healthcare systems in smart cities. Emergency departments (ED) are real-time systems with complex dynamic behavior, and they require tailored techniques to model, simulate and optimize system resources and service flow. ED issues are mainly due to resource shortage and resource assignment efficiency. In this paper, we propose a resource preservation net (RPN) framework using Petri net, integrated with custom cloud and edge computing suitable for ED systems. The proposed framework is designed to model non-consumable resources and is theoretically described and validated. RPN is applicable to a real-life scenario where key performance indicators such as patient length of stay (LoS), resource utilization rate and average patient waiting time are modeled and optimized. As the system must be reliable, efficient and secure, the use of cloud and edge computing is critical. The proposed framework is simulated, which highlights significant improvements in LoS, resource utilization and patient waiting time.

Content delivery through cloud networks has gained popularity due to the cloud's ability to provide on-demand services. However, composite services, such as customized multimedia content, introduce both delays and resource limitations if traditional cloud solutions are used. With recent advances in mobile edge computing, customized media delivery can be achieved through compositions of service specific overlays (SSOs). This paper presents a workflow-net-based mechanism for mobile edge node cooperation in fog-cloud networks to form guaranteed SSOs. The proposed solution uses a mathematical cooperation operator to turn the SSO composition problem expressed as workflow nets into algebraic representations. In turn, the minimal cost cooperative path from the workflow net is determined such that it guarantees the delivery of the requested composite media services to clients. Experimental results show that the composition process can be adequately established and carried out in a timely manner.

This research addresses the accuracy issues in IoT-based human activity recognition (HAR) applications, essential for health monitoring, elderly care, gait analysis, security, and Industry 5.0. This study uses 12 machine learning approaches, split equally between support vector machine (SVM) and k-nearest neighbor (k-NN) models. Data from 102 individuals, aged 18–43, were used to train and test these models. The researchers aimed to detect twelve daily activities, such as sitting, walking, and cycling. Results showed k-NN models achieved slightly higher accuracy (97.08%) compared to SVM models (95.88%), though SVM had faster processing times. The improved machine learning approaches proved effective in accurately classifying daily activities, with k-NN models outperforming SVM models marginally. The paper provides significant contributions to the field of HAR by enhancing the performance of SVM and k-NN classifiers, optimizing them for higher accuracy and faster processing. Through robust testing with samples of real-world data, the study provides a detailed comparative analysis that highlights strengths and weaknesses of each classifier model, specifically within IoT-based systems. This work not only advances the theoretical understanding and practical applications of HAR systems in areas, such as healthcare and industrial automation, but also sets the stage for future research that could explore hybrid models or further enhancements, consequently improving the efficiency and functionality of IoT devices based on activity recognition.