Date on Master's Thesis/Doctoral Dissertation


Document Type

Doctoral Dissertation

Degree Name

Ph. D.


Computer Engineering and Computer Science

Degree Program

Computer Science and Engineering, PhD

Committee Chair

Elmaghraby, Adel

Committee Co-Chair (if applicable)

Sierrasosa, Daniel

Committee Member

Sierrasosa, Daniel

Committee Member

Kumar, Anup

Committee Member

Imam, Ibrahim

Committee Member

Gentili, Monica

Author's Keywords

smart health; fall detection; direction and severity; internet of things; machine learning; deep learning


Internet of Things is a system that integrates different devices and technologies, removing the necessity of human intervention. This enables the capacity of having smart (or smarter) cities around the world. By hosting different technologies and allowing interactions between them, the internet of things has spearheaded the development of smart city systems for sustainable living, increased comfort and productivity for citizens. The Internet of Things (IoT) for Smart Cities has many different domains and draws upon various underlying systems for its operation, in this work, we provide a holistic coverage of the Internet of Things in Smart Cities by discussing the fundamental components that make up the IoT Smart City landscape, the technologies that enable these domains to exist, the most prevalent practices and techniques which are used in these domains as well as the challenges that deployment of IoT systems for smart cities encounter and which need to be addressed for ubiquitous use of smart city applications. It also presents a coverage of optimization methods and applications from a smart city perspective enabled by the Internet of Things. Towards this end, a mapping is provided for the most encountered applications of computational optimization within IoT smart cities for five popular optimization methods, ant colony optimization, genetic algorithm, particle swarm optimization, artificial bee colony optimization and differential evolution. For each application identified, the algorithms used, objectives considered, the nature of the formulation and constraints taken in to account have been specified and discussed. Lastly, the data setup used by each covered work is also mentioned and directions for future work have been identified. Within the smart health domain of IoT smart cities, human activity recognition has been a key study topic in the development of cyber physical systems and assisted living applications. In particular, inertial sensor based systems have become increasingly popular because they do not restrict users’ movement and are also relatively simple to implement compared to other approaches. Fall detection is one of the most important tasks in human activity recognition. With an increasingly aging world population and an inclination by the elderly to live alone, the need to incorporate dependable fall detection schemes in smart devices such as phones, watches has gained momentum. Therefore, differentiating between falls and activities of daily living (ADLs) has been the focus of researchers in recent years with very good results. However, one aspect within fall detection that has not been investigated much is direction and severity aware fall detection. Since a fall detection system aims to detect falls in people and notify medical personnel, it could be of added value to health professionals tending to a patient suffering from a fall to know the nature of the accident. In this regard, as a case study for smart health, four different experiments have been conducted for the task of fall detection with direction and severity consideration on two publicly available datasets. These four experiments not only tackle the problem on an increasingly complicated level (the first one considers a fall only scenario and the other two a combined activity of daily living and fall scenario) but also present methodologies which outperform the state of the art techniques as discussed. Lastly, future recommendations have also been provided for researchers.