No abstract

The Internet of Things (IoT)

The Internet of Things (IoT) incorporates multiple long-range, short-range, and personal area wireless networks and technologies into the designs of IoT applications. This enables numerous business opportunities in fields as diverse as e-health, smart cities, smart homes, among many others. This research analyses some of the major evolving and enabling wireless technologies in the IoT. Particularly, it focuses on ZigBee, 6LoWPAN, Bluetooth Low Energy, LoRa, and the different versions of Wi-Fi including the recent IEEE 802.11ah protocol. The studies evaluate the capabilities and behaviours of these technologies regarding various metrics including the data range and rate, network size, RF Channels and Bandwidth, and power consumption. It is concluded that there is a need to develop a multifaceted technology approach to enable interoperable and secure communications in the IoT.

The Internet of Things (IoT) was of a vision in which all physical objects are tagged and uniquely identified using RFID transponders or readers. Nowadays, research into the IoT has extended this vision to the connectivity of Things to anything, anyone, anywhere and at anytime. The IoT has grown into multiple dimensions, which encompasses various networks of applications, computers, devices, as well as physical and virtual objects, referred to as things or objects, that are interconnected together using communication technologies such as, wireless, wired and mobile networks, RFID, Bluetooth, GPS systems, and other evolving technologies. This paradigm is a major shift from an essentially computer-based network model to a fully distributed network of smart objects. This change poses serious challenges in terms of architecture, connectivity, efficiency, security and provision of services among many others. This paper studies the state-of-the art of the IoT. In addition, some major security and privacy issues are described and a new attack vector is introduced, referred to as the "automated invasion attack".

Identifying the symptoms of the early stages of dementia is a difficult task, particularly for older adults living in residential care. Internet of Things (IoT) and smart environments can assist with the early detection of dementia, by nonintrusive monitoring of the daily activities of the older adults. In this work, we focus on the daily life activities of adults in a smart home setting to discover their potential cognitive anomalies using a public dataset. After analysing the dataset, extracting the features, and selecting distinctive features based on dynamic ranking, a classification model is built. We compare and contrast several machine learning approaches for developing a reliable and efficient model to identify the cognitive status of monitored adults. Using our predictive model and our approach of distinctive feature selection, we have achieved 90.74% accuracy in detecting the onset of dementia.