Computer Engineering Commons^™

A Computational Model Of Trust Based On Dynamic Interaction In The Stack Overflow Community, Patrick O’Neill

Dissertations

A member’s reputation in an online community is a quantified representation of their trustworthiness within the community. Reputation is calculated using rules-based algorithms which are primarily tied to the upvotes or downvotes a member receives on posts. The main drawback of this form of reputation calculation is the inability to consider dynamic factors such as a member’s activity (or inactivity) within the community. The research involves the construction of dynamic mathematical models to calculate reputation and then determine to what extent these results compare with rules-based models. This research begins with exploratory research of the existing corpus of knowledge. Constructive …

Exploring Gender Bias In Semantic Representations For Occupational Classification In Nlp: Techniques And Mitigation Strategies, Joseph Michael O'Carroll

Dissertations

Gender bias in Natural Language Processing (NLP) models is a non-trivial problem that can perpetuate and amplify existing societal biases. This thesis investigates gender bias in occupation classification and explores the effectiveness of different debiasing methods for language models to reduce the impact of bias in the model’s representations. The study employs a data-driven empirical methodology focusing heavily on experimentation and result investigation. The study uses five distinct semantic representations and models with varying levels of complexity to classify the occupation of individuals based on their biographies.

Evaluating The Performance Of Vulkan Glsl Compute Shaders In Real-Time Ray-Traced Audio Propagation Through 3d Virtual Environments, James Buggy

Dissertations

Real time ray tracing is a growing area of interest with applications in audio processing. However, real time audio processing comes with strict performance requirements, which parallel computing is often used to overcome. As graphics processing units (GPUs) have become more powerful and programmable, general-purpose computing on graphics processing units (GPGPU) has allowed GPUs to become extremely powerful parallel processors, leading them to become more prevalent in the domain of audio processing through platforms such as CUDA. The aim of this research was to investigate the potential of GLSL compute shaders in the domain of real time audio processing. Specifically …

Evaluation Of Text Transformers For Classifying Sentiment Of Reviews By Using Tf-Idf, Bert (Word Embedding), Sbert (Sentence Embedding) With Support Vector Machine Evaluation, Mina Jamshidian

Dissertations

As the online world evolves and new media emerge, consumers are sharing their reviews and opinions online. This has been studied in various academic fields, including marketing and computer science. Sentiment analysis, a technique used to identify the sentiment of a piece of text, has been researched in different domains such as movie reviews and mobile app ratings. However, the video game industry has received relatively little research on experiential products. The purpose of this study is to apply sentiment analysis to user reviews of games on Steam, a popular gaming platform, in order to produce actionable results. The video …

Application Of Shallow Neural Networks To Retail Intermittent Demand Time Series, Urko Allende

Dissertations

Accurate sales predictions are essential for businesses in the fast-moving consumer goods (FMCG) industry. However, their demand forecasts are often unreliable, leading to imprecisions that affect downstream decisions. This dissertation proposes using an artificial neural network to improve intermittent demand forecasting in the retail sector. The research investigates the validity of using unprocessed historical information, eluding hand-crafted features, to learn patterns in intermittent demand data. The experiment tests a selection of shallow neural network architectures that can expedite the time-to-market in comparison to conventional demand forecasting methods. The results demonstrate that organisations that still rely on manual and direct forecasting …

Explaining Deep Q-Learning Experience Replay With Shapley Additive Explanations, Robert S. Sullivan

Dissertations

Reinforcement Learning (RL) has shown promise in optimizing complex control and decision-making processes but Deep Reinforcement Learning (DRL) lacks interpretability, limiting its adoption in regulated sectors like manufacturing, finance, and healthcare. Difficulties arise from DRL’s opaque decision-making, hindering efficiency and resource use, this issue is amplified with every advancement. While many seek to move from Experience Replay to A3C, the latter demands more resources. Despite efforts to improve Experience Replay selection strategies, there is a tendency to keep capacity high. This dissertation investigates training a Deep Convolutional Q-learning agent across 20 Atari games, in solving a control task, physics task, …

The Use Of Data Balancing Algorithms To Correct For The Under-Representation Of Female Patients In A Cardiovascular Dataset, Sian Miller

Dissertations

Given that women are under-represented in medical datasets, and that machine learning classification algorithms are known to exhibit bias towards the majority class, the growing application of machine learning in the medical field risks resulting in worse medical outcomes for female patients. The Heart Failure Prediction (HFP) dataset is a historical dataset used for the training of models for the prediction of heart disease. This dataset contains significantly fewer female patients than male patients, and as such it is expected that models trained using this data will inherit a gender bias to favour male patients. This dissertation explores the use …

Probability Expressions In Ai Decision Support: Impacts On Human+Ai Team Performance, Elias Spinn

Dissertations

AI decision support systems aim to assist people in highly complex and consequential domains to make efficient, effective, and high-quality decisions. AI alone cannot be guaranteed to be correct in these complex decision tasks, and a human is often needed to ensure decision accuracy. The ambition is for these human+ AI teams to perform better together than either would individually. To realise this, decision makers must trust their AI partners appropriately, knowing when to rely on their recommendations and when to be sceptical. However, research has shown that decision makers often either mistrust and underutilise these systems, or trust them …

Modelling And Mitigating Interlocutor Confusion In Situated Human-Avatar And Human-Robot Interaction, Na Li

Dissertations

Human-Robot Interaction (HRI) is an important but challenging field focused on improving the interaction between humans and robots, to make the interaction more intelligent and effective. However, building a natural conversational HRI is an interdisciplinary challenge for scholars, engineers, and designers. Achieving successful conversational interaction with a social robot necessitates not only observing a user’s active participation in the interaction but also being aware of their emotional and attitudinal states as the interaction progresses. On the topic of attitudinal states, one field that has received little attention to date is monitoring the user for possible confusion states. Confusion is a …

Integrating Kano Model With Data Mining Techniques To Enhance Customer Satisfaction, Khaled Abdulla Ali Al Rabaiei

Dissertations

The business world is becoming more competitive from time to time; therefore, businesses are forced to improve their strategies in every single aspect. So, determining the elements that contribute to the clients' contentment is one of the critical needs of businesses to develop successful products in the market. The Kano model is one of the models that help determine which features must be included in a product or service to improve customer satisfaction. The model focuses on highlighting the most relevant attributes of a product or service along with customers’ estimation of how these attributes can be used to predict …

Software Protection And Secure Authentication For Autonomous Vehicular Cloud Computing, Muhammad Hataba

Dissertations

Artificial Intelligence (AI) is changing every technology we deal with. Autonomy has been a sought-after goal in vehicles, and now more than ever we are very close to that goal. Vehicles before were dumb mechanical devices, now they are becoming smart, computerized, and connected coined as Autonomous Vehicles (AVs). Moreover, researchers found a way to make more use of these enormous capabilities and introduced Autonomous Vehicles Cloud Computing (AVCC). In these platforms, vehicles can lend their unused resources and sensory data to join AVCC.

In this dissertation, we investigate security and privacy issues in AVCC. As background, we built our …

Performance Analysis Of The Dominant Mode Rejection Beamformer, Enlong Hu

Dissertations

In array signal processing over challenging environments, due to the non-stationarity nature of data, it is difficult to obtain enough number of data snapshots to construct an adaptive beamformer (ABF) for detecting weak signal embedded in strong interferences. One type of adaptive method targeting for such applications is the dominant mode rejection (DMR) method, which uses a reshaped eigen-decomposition of sample covariance matrix (SCM) to define a subspace containing the dominant interferers to be rejected, thereby allowing it to detect weak signal in the presence of strong interferences. The DMR weight vector takes a form similar to the adaptive minimum …

Artificial Neural Networks And Their Applications To Intelligent Fault Diagnosis Of Power Transmission Lines, Fatemeh Mohammadi Shakiba

Dissertations

Over the past thirty years, the idea of computing based on models inspired by human brains and biological neural networks emerged. Artificial neural networks play an important role in the field of machine learning and hold the key to the success of performing many intelligent tasks by machines. They are used in various applications such as pattern recognition, data classification, stock market prediction, aerospace, weather forecasting, control systems, intelligent automation, robotics, and healthcare. Their architectures generally consist of an input layer, multiple hidden layers, and one output layer. They can be implemented on software or hardware. Nowadays, various structures with …

Development And Evaluation Of A Hand Exoskeleton For Neurorehabilitation Post Stroke, Ashley Joyce Mont

Dissertations

Stroke affects approximately 800,000 people in the United States each year, and due to its chronic effects, it is one of the leading causes of disability. Many individuals with stroke suffer the loss of motor function in their paretic upper extremity, and longitudinal studies show that 30 — 66% of individuals with hemiplegia fail to regain arm function six months post stroke. After a stroke, the brain undergoes neuroplasticity which will promote recovery of function. Investigators and clinicians are trying to develop rehabilitation interventions that can be designed to promote neuroplasticity, enhancing the recovery outcomes of therapy.

For individuals with …

Towards Ensuring Integrity And Authenticity Of Software Repositories, Sangat Vaidya

Dissertations

The software development process comprises a series of steps known as a software supply chain. These steps include managing the source code, testing, building and packaging it into a final product, and distributing the product to end users. Along this chain, software repositories are used for different purposes such as source code management (Git, SVN, mercurial), software distribution (PyPI, RubyGems, NPM) or for deploying software based on container images (Harbor, DockerHub, Artifact Hub). In the recent past, different types of repositories have increasingly been the target of attacks. As such, there is a need for mechanisms to ensure integrity and …

Application Of Deep Learning For Medical Sciences And Epidemiology Data Analysis And Diagnostic Modeling, Somenath Chakraborty

Dissertations

Machine Learning and Artificial Intelligence have made significant progress concurrent with new advancements in hardware and software technologies. Deep learning methods heavily utilize parallel computing and Graphical Processing Units(GPU). It is already used in many applications ranging from image classification, object detection, segmentation, cyber security problems and others. Deep Learning is emerging as a viable choice in dealing with today’s real-time medical problems. We need new methods and technologies in the field of Medical Science and Epidemiology for detecting and diagnosing emerging threats from new viruses such as COVID-19. The use of Artificial Intelligence in these domains is becoming more …

Local Learning Algorithms For Stochastic Spiking Neural Networks, Bleema Rosenfeld

Dissertations

This dissertation focuses on the development of machine learning algorithms for spiking neural networks, with an emphasis on local three-factor learning rules that are in keeping with the constraints imposed by current neuromorphic hardware. Spiking neural networks (SNNs) are an alternative to artificial neural networks (ANNs) that follow a similar graphical structure but use a processing paradigm more closely modeled after the biological brain in an effort to harness its low power processing capability. SNNs use an event based processing scheme which leads to significant power savings when implemented in dedicated neuromorphic hardware such as Intel’s Loihi chip.

This work …

Outdoor Operations Of Multiple Quadrotors In Windy Environment, Deepan Lobo

Dissertations

Coordinated multiple small unmanned aerial vehicles (sUAVs) offer several advantages over a single sUAV platform. These advantages include improved task efficiency, reduced task completion time, improved fault tolerance, and higher task flexibility. However, their deployment in an outdoor environment is challenging due to the presence of wind gusts. The coordinated motion of a multi-sUAV system in the presence of wind disturbances is a challenging problem when considering collision avoidance (safety), scalability, and communication connectivity. Performing wind-agnostic motion planning for sUAVs may produce a sizeable cross-track error if the wind on the planned route leads to actuator saturation. In a multi-sUAV …

Design And Control Of Next-Generation Uavs For Effectively Interacting With Environments, Caiwu Ding

Dissertations

In this dissertation, the design and control of a novel multirotor for aerial manipulation is studied, with the aim of endowing the aerial vehicle with more degrees of freedom of motion and stability when interacting with the environments. Firstly, it presents an energy-efficient adaptive robust tracking control method for a class of fully actuated, thrust vectoring unmanned aerial vehicles (UAVs) with parametric uncertainties including unknown moment of inertia, mass and center of mass, which would occur in aerial maneuvering and manipulation. The effectiveness of this method is demonstrated through simulation. Secondly, a humanoid robot arm is adopted to serve as …

Towards A Cross-Layer Coupled Design Framework For Big Data Workflows, Qianwen Ye

Dissertations

The processing and analysis of big data increasingly rely on workflow technologies for knowledge discovery and scientific innovation. The execution of such workflows goes far beyond the capability and capacity of single computers and is now commonly supported on reliable and scalable data storage and analysis platforms in distributed environments, such as the Hadoop ecosystem. Workflow performance largely depends on how big data systems are configured and used. For example, the makespan of a big data workflow is affected by multiple layers of big data systems, including the parallel computing engine it runs on, the resource manager that orchestrates various …

Improving Dysarthric Speech Recognition By Enriching Training Datasets, Sophie Cullen

Dissertations

Dysarthria is a motor speech disorder that results from disruptions in the neuro-motor interface and is characterised by poor articulation of phonemes and hyper-nasality and is characteristically different from normal speech. Many modern automatic speech recognition systems focus on a narrow range of speech diversity therefore as a consequence of this they exclude a groups of speakers who deviate in aspects of gender, race, age and speech impairment when building training datasets. This study attempts to develop an automatic speech recognition system that deals with dysarthric speech with limited dysarthric speech data. Speech utterances collected from the TORGO database are …

Real-Time Stock Market Recommendation & Prediction Using Multi Source Data, Kalpana Konety

Dissertations

Stock investors must be cognizant of both the current price of their stock and the price at which they want to sell it in the future. This does not stop investors to monitor past price patterns and apply their knowledge to the present. ’Past performance is not an indicator of future success’, as the saying goes. To put it another way, historical stock data alone isn’t enough to forecast future stock prices. Another key factor to consider in a trading strategy is the impact of market psychology. Financial data, which is a type of multimedia data, provides a wealth of …

Measuring And Comparing Social Bias In Static And Contextual Word Embeddings, Alan Cueva Mora

Dissertations

Word embeddings have been considered one of the biggest breakthroughs of deep learning for natural language processing. They are learned numerical vector representations of words where similar words have similar representations. Contextual word embeddings are the promising second-generation of word embeddings assigning a representation to a word based on its context. This can result in different representations for the same word depending on the context (e.g. river bank and commercial bank). There is evidence of social bias (human-like implicit biases based on gender, race, and other social constructs) in word embeddings. While detecting bias in static (classical or non-contextual) word …

Hybridization Of Biologically Inspired Algorithms For Discrete Optimisation Problems, Elihu Essian-Thompson

Dissertations

In the field of Optimization Algorithms, despite the popularity of hybrid designs, not enough consideration has been given to hybridization strategies. This paper aims to raise awareness of the benefits that such a study can bring. It does this by conducting a systematic review of popular algorithms used for optimization, within the context of Combinatorial Optimization Problems. Then, a comparative analysis is performed between Hybrid and Base versions of the algorithms to demonstrate an increase in optimization performance when hybridization is employed.

Development Of An Explainability Scale To Evaluate Explainable Artificial Intelligence (Xai) Methods, Stephen Mccarthy

Dissertations

Explainable Artificial Intelligence (XAI) is an area of research that develops methods and techniques to make the results of artificial intelligence understood by humans. In recent years, there has been an increased demand for XAI methods to be developed due to model architectures getting more complicated and government regulations requiring transparency in machine learning models. With this increased demand has come an increased need for instruments to evaluate XAI methods. However, there are few, if none, valid and reliable instruments that take into account human opinion and cover all aspects of explainability. Therefore, this study developed an objective, human-centred questionnaire …

Evaluation Of Automated Eye Blink Artefact Removal Using Stacked Dense Autoencoder, Matthew Rigney

Dissertations

The presence of artefacts in Electroencephalograph (EEG) signals can have a considerable impact on the information they portray. In this comparative study, the automated removal of eye blink artefacts using the constrained latent representation of a stacked dense autoencoders (SDAE) and comparing its ability to that of the manual independent component analysis (ICA) approach was evaluated. A comparative evaluation of 5 stacked dense autoencoder architectures lead to a chosen architecture for which the ability to automatically detect and remove eye blink artefacts were both statistically and humanistically evaluated. The ability of the stacked dense autoencoder was statistically evaluated with the …

Scrolling Vs Paging: Reading Performance And Preference Of Reading Modes In Long-Form Online News, Richard Herlihy

Dissertations

This study explores the impact of scrolling and dynamic pagination in long-form online documents on reader performance and reader experience. Previous research has produced mixed results, indicating no difference between modes, or a positive effect favouring scrolling. Recent advances in web standards have enabled simpler, dynamic, performant methods of pagination to tailor content responsively to any screen, meriting renewed study in this area. This paper uses one such method to load subsequent online news pages instantly without buffering. In an online browser experiment with 38 participants, an increase in reading speed in the scrolling mode was found at a level …

Ensemble Approach To The Semantic Segmentation Of Satellite Images, Brendan Kent

Dissertations

Automatic classification and segmentation of land use land cover(LULC) is extremely important for understanding the relationship between humans and nature. Human pressures on the environment have drastically accelerated in the last decades, risking biodiversity and ecosystem services. Remote sensing via satellite imagery is an excellent tool to study LULC. Research has shown that deep learning encoder-decoder architectures have achieved worthy results in the area of LULC, however the application of an ensemble approach has not been well quantified. Studies have shown it to be useful in the area of medical imaging. Ensembling by pooling together predictions to produce better predictions …

An Analysis On Network Flow-Based Iot Botnet Detection Using Weka, Cian Porteous

Dissertations

Botnets pose a significant and growing risk to modern networks. Detection of botnets remains an important area of open research in order to prevent the proliferation of botnets and to mitigate the damage that can be caused by botnets that have already been established. Botnet detection can be broadly categorised into two main categories: signature-based detection and anomaly-based detection. This paper sets out to measure the accuracy, false-positive rate, and false-negative rate of four algorithms that are available in Weka for anomaly-based detection of a dataset of HTTP and IRC botnet data. The algorithms that were selected to detect botnets …

Dark Patterns: Effect On Overall User Experience And Site Revisitation, Deon Soul Calawen

Dissertations

Dark patterns are user interfaces purposefully designed to manipulate users into doing something they might not otherwise do for the benefit of an online service. This study investigates the impact of dark patterns on overall user experience and site revisitation in the context of airline websites. In order to assess potential dark pattern effects, two versions of the same airline website were compared: a dark version containing dark pattern elements and a bright version free of manipulative interfaces. User experience for both websites were assessed quantitatively through a survey containing a User Experience Questionnaire (UEQ) and a System Usability Scale …