Many applications, such as smart buildings, crowd flow, action recognition, and assisted living, rely on occupancy information. Although the use of smart cameras and computer vision can assist with these tasks and provide accurate occupancy information, it can be cost prohibitive, invasive, and difficult to scale or generalise to different environments. An alternative solution should bring similar accuracy while minimising the listed problems. This work demonstrates that a scalable wireless sensor network with CO₂-based estimation is a viable alternative. To support many applications, a solution must be transferable and must handle not knowing the physical system model; instead, it must learn to model CO₂ dynamics. This work presents a viable prototype and uses the captured data to train machine learning-based occupancy estimation systems. Models are trained under varying conditions to assess the consequences of design decisions on performance. Four different learning models were compared: gradient boosting, k-nearest neighbours (KNN), linear discriminant analysis, and random forests. With sufficient labelled data, the KNN model produced peak results with a root-mean-square error value of 1.021.

With the rapid implementation and expansion of the Internet of things (IoT) technologies in smart cities, network congestion control and energy-efficient routing in wireless sensor and actuator networks (WSANs) for virtualising IoT have emerged as a crucial area of research in recent years. This study implements the particle swarm optimisation (PSO) algorithm to realise network congestion control and energy-efficient routing in the transport layer of WSANs. This algorithm is based on the flocking behaviour of birds. The simulation results show that the proposed PSO-based approach provides better performance in terms of network lifetime and packet drop ratio compared with the ant colony optimisation and the artificial bee colony algorithm.

The growing trend of ageing has created many challenges. One of these challenges is the rehabilitation of individuals who take time, resources and manpower. The motivation for this study is to propose an ontology-based automatic design methodology for use in intelligent rehabilitation systems in the Internet of things (IoTs). For interconnection, all health system resources in a network use IoT technology. In order to provide fast and effective rehabilitation for different patients, IoT is combined with ontology. The experimental results obtained from rehabilitation of the lower limbs show that the IoT-based rehabilitation system works properly and an ontology-based approach can help create an effective rehabilitation strategy, configure and quickly deploy all available resources with the requirements given. In this study, three types of biosensors have been selected. These biosensors are used for blood, saliva and breathing tests. The expansion of the growth and maturity of technology based on the Fisher-Pry model is based on patent and bibliometrics analysis. The analysis of intellectual property rights according to their number indicates that blood vital sensors reached their turning point in 2009, but the vital sensors of saliva and respiration will reach their turning point and maturity with a delay of 8–14 years.

Today, mobile phones have become smarter than ever before and people are always carrying them. Mobile phones are not only references for computing and communications, but also a great option for gathering information about individuals and their surroundings. This study investigates the problem of mapping air pollution by leveraging a crowd of people that are equipped with smartphones. The proposed system uses mobile cloud computing as well, in order to collect and aggregate air pollution data. At the layer of mobile devices, air pollution is measured by local portable sensors through the exposure of users to the surrounding environment. Afterwards, these pieces of local information generated by the crowd of users are aggregated in the cloud layer. The proposed system is implemented in two components for mobile device and cloud. Furthermore, the scenario-based approach is used to evaluate the functionality of the system.