Degree Name

Doctor of Philosophy


School of Computing and Information Technology


The thesis work majorly focuses on the development methodologies of the Internet of Things (IoT). A detailed literature survey is presented for the discussion of various challenges in the development of software and design and deployment of hardware. The thesis work deals with the efficient development methodologies for the deployment of IoT system. Efficient hardware and software development reduces the risk of the system bugs and faults. The optimal placement of the IoT devices is the major challenge for the monitoring application. A Qualitative Spatial Reasoning (QSR) and Qualitative Temporal Reasoning (QTR) methodologies are proposed to build software systems. The proposed hybrid methodology includes the features of QSR, QTR, and traditional databased methodologies. The hybrid methodology is proposed to build the software systems and direct them to the specific goal of obtaining outputs inherent to the process. The hybrid methodology includes the support of tools and is detailed, integrated, and fits the general proposal. This methodology repeats the structure of Spatio-temporal reasoning goals. The object-oriented IoT device placement is the major goal of the proposed work. Segmentation and object detection is used for the division of the region into sub-regions. The coverage and connectivity are maintained by the optimal placement of the IoT devices using RCC8 and TPCC algorithms.

Over the years, IoT has offered different solutions in all kinds of areas and contexts. The diversity of these challenges makes it hard to grasp the underlying principles of the different solutions and to design an appropriate custom implementation on the IoT space. One of the major objective of the proposed thesis work is to study numerous production-ready IoT offerings, extract recurring proven solution principles, and classify them into spatial patterns. The method of refinement of the goals is employed so that complex challenges are solved by breaking them down into simple and achievable sub-goals. The work deals with the major sub-goals e.g. efficient coverage of the field, connectivity of the IoT devices, Spatio-temporal aggregation of the data, and estimation of spatially connected regions of event detection. We have proposed methods to achieve each sub-goal for all different types of spatial patterns. The spatial patterns developed can be used in ongoing and future research on the IoT to understand the principles of the IoT, which will, in turn, promote the better development of existing and new IoT devices.

The next objective is to utilize the IoT network for enterprise architecture (EA) based IoT application. EA defines the structure and operation of an organization to determine the most effective way for it to achieve its objectives. Digital transformation of EA is achieved through analysis, planning, design, and implementation, which interprets enterprise goals into an IoT-enabled enterprise design. A blueprint is necessary for the readying of IT resources that support business services and processes. A systematic approach is proposed for the planning and development of EA for IoT-Applications. The Enterprise Interface (EI) layer is proposed to efficiently categorize the data. The data is categorized based on local and global factors. The clustered data is then utilized by the end-users. A novel four-tier structure is proposed for Enterprise Applications. We analyzed the challenges, contextualized them, and offered solutions and recommendations.

The last objective of the thesis work is to develop energy-efficient data consistency method. The data consistency is a challenge for designing energy-efficient medium access control protocol used in IoT. The energy-efficient data consistency method makes the protocol suitable for low, medium, and high data rate applications. The idea of energyefficient data consistency protocol is proposed with data aggregation. The proposed protocol efficiently utilizes the data rate as well as saves energy. The optimal sampling rate selection method is introduced for maintaining the data consistency of continuous and periodic monitoring node in an energy-efficient manner. In the starting phase, the nodes will be classified into event and continuous monitoring nodes. The machine learning based logistic classification method is used for the classification of nodes. The sampling rate of continuous monitoring nodes is optimized during the setup phase by using optimized sampling rate data aggregation algorithm. Furthermore, an energy-efficient time division multiple access (EETDMA) protocol is used for the continuous monitoring on IoT devices, and an energy-efficient bit map assisted (EEBMA) protocol is proposed for the event driven nodes.

FoR codes (2020)

4606 Distributed computing and systems software



Unless otherwise indicated, the views expressed in this thesis are those of the author and do not necessarily represent the views of the University of Wollongong.