Browsing Open Theses & Dissertations by Thesis Supervisor "Narayanan, Ajit"
Now showing items 1-20 of 26
-
Bioinformatics-inspired analysis for watermarked images with multiple print and scan
(Auckland University of Technology, 2018)Image identification and grouping through pattern analysis are the core problems in image analysis. In this thesis, the gap between bioinformatics and image analysis is bridged by using biologically-encoding and ... -
The Caravan Trader Problem (CTP) and a Tournament-based Lamarckian Genetic Algorithm Solution
(Auckland University of Technology, 2019)This research introduces the Caravan Trading Problem (CTP) which is a routing problem with an additional economic model, and attempts to optimize two different objectives, namely profit and distance, using Genetic Algorithm ... -
A Component Based Knowledge Transfer Model for Deep Neural Networks
(Auckland University of Technology, 2020)This thesis explores the idea that features extracted from deep neural networks (DNNs) through layered weight analysis are knowledge components and are transferable. Among the components extracted from the various layers, ... -
Deep Transfer Learning for Intelligent Autonomous Vehicles
(Auckland University of Technology, 2020)Autonomous driving has become a very interesting research problem for the deep learning domain. While Intelligent Autonomous Vehicles (IAVs) have developed significantly over the last 10 years, there are still unresolved ... -
Developing a Digital Forensic Capability for Critical Infrastructures: An Investigation Framework
(Auckland University of Technology, 2020)Digital forensic science in critical infrastructures is a booming study area of research. It combines cybersecurity practices of industrial control systems in critical infrastructures, with the problems of big data quantities ... -
Disaster e-Health Scope and the Role of RFID for Healthcare Purposes
(Auckland University of Technology, 2019)Disasters, either natural or manmade, are sudden and mostly unpredictable. They are of such enormous scale that it is necessary for societies to embark upon special planning and preparedness before disasters strike to ... -
Discovery of High Quality Knowledge for Clinical Decision Support Systems by Applying Semantic Web Technology
(Auckland University of Technology, 2017)While the discovery of new clinical knowledge is always a good thing, it can lead to difficulties. Health experts are required to actively ensure they are informed about the latest accurate knowledge in their field. Many ... -
Ensemble Classifier Modelling for Dealing with Missing Values
(Auckland University of Technology, 2020)An ensemble classifier method for life critical data classification is considered one of the most capable classifiers where data suffers from missing values. The execution of a decision tree classifier can be expanded by ... -
Epidemiological cellular automata: a case study involving AIDS
(Auckland University of Technology, 2013)The spread of disease is a major health concern in many parts of the world. In the absence of vaccines and treatments, the only method to stop the spread of disease is to control population movements. Human mobility is ... -
Evidence-based Stratification Methodology for Non-probabilistic Sampling Surveys
(Auckland University of Technology, 2018)There is increasing use of non-probability sampling methods in large-scale surveys due to the costs involved in ensuring that the sample chosen is representative of the population, as is the case with probability sampling. ... -
Hydrological Cycle Algorithm for Solving Optimisation Problems
(Auckland University of Technology, 2018)This research proposes a new nature-inspired algorithm called the Hydrological Cycle Algorithm (HCA), which simulates the movement of water drops in the hydrological water cycle. In the HCA, a collection of artificial water ... -
Identifying Polymorphic Malware Variants Using Biosequence Analysis Techniques
(Auckland University of Technology, 2018)Modern antivirus systems (AVSs) are not able to detect new polymorphic malware variants until they emerge, even when signatures of one or more variants belonging to a specific polymorphic malware family are known. Polymorphic ... -
Image Authentication and Rightful Ownership Watermarking Method for the Cloud Environment
(Auckland University of Technology, 2017)Cloud computing has evolved in the last five years from being an abstract idea and proposal, and into services that people use every day. In particular services that relate to mobile phone technologies have expanded in ... -
Intelligent collision detection and avoidance techniques for autonomous agents
(Auckland University of Technology, 2014)Collision is one of the main problems in distributed task cooperation involving multiple moving agents or robots. The collision avoidance problem arises when the environment is dynamic and to reach their destination agents ... -
Locating and extracting digital evidence from hosted virtual desktop infrastructures: cloud context
(Auckland University of Technology, 2012)The development of virtualization started in 1960, when VMware introduced partitioning of large mainframes for better hardware utilization. (Virtualization History, 2010) Since then virtualization has matured and been ... -
Malware motif identification using Bio-inspired Data Mining
(Auckland University of Technology, 2013)The application of data mining techniques into biological data is well established. The aim of this thesis is to explore the effects of giving amino acid representation to problematic machine learning data and to evaluate ... -
Measuring Mindfulness and Health-related Outcomes: Applying Rasch Analysis and Generalisability Theory to Improve Reliability and Validity of Scales
(Auckland University of Technology, 2017)There is growing evidence for mindfulness-based interventions in alleviating the symptoms and enhancing the coping abilities of people suffering from psychological and physical health conditions and improving overall ... -
Mobile Cloud Computing: implications to smartphone forensic procedures and methodologies
(Auckland University of Technology, 2011)There is a growing understanding of how to conduct digital forensic analysis on mobile devices. However, there is little understanding of how to apply digital forensic methodologies in Cloud computing, and even less ... -
Natural immune systems for developing novel Machine Learning algorithms
(Auckland University of Technology, 2012)This thesis presents novel multi-layered natural immune system (NIS) inspired algorithms in the domain of machine learning. The exploration of biological metaphors for developing novel learning algorithms for computation ... -
Power and Network Integration: Structural and Algorithmic Analysis of Organizational Networks
(Auckland University of Technology, 2016)This thesis constitutes the results of our research towards structural and algorithmic analysis of organizational networks. We study how interpersonal ties become crucial empowerment channels that shape organizational ...