Computer Engineering Commons^™

Poly-Gan: Regularizing Polygons With Generative Adversarial Networks, Lasith Niroshan, James Carswell

Conference Papers

Regularizing polygons involves simplifying irregular and noisy shapes of built environment objects (e.g. buildings) to ensure that they are accurately represented using a minimum number of vertices. It is a vital processing step when creating/transmitting online digital maps so that they occupy minimal storage space and bandwidth. This paper presents a data-driven and Deep Learning (DL) based approach for regularizing OpenStreetMap building polygon edges. The study introduces a building footprint regularization technique (Poly-GAN) that utilises a Generative Adversarial Network model trained on irregular building footprints and OSM vector data. The proposed method is particularly relevant for map features …

Co-Design Of An Interactive Wellness Park: Exploring Design Requirements For A Multimodal Outdoor Physical Web Installation With Older Adults, Fatima Badmos

Academic Posters Collection

The global demographic landscape is experiencing a notable shift, characterised by a growing proportion of adults over 60. According to projections, the proportion of individuals aged 60 and above is expected to reach one-sixth of the global population by 2030. Furthermore, by 2050, this demographic is projected to exceed a staggering two billion people. Amidst this shift, there is an urgent need to develop interactive and innovative solutions to address older adults' unique challenges, particularly in outdoor physical activity.

A co-design methodology involving older adults’ participation from the idea generation to the application development process will be adopted to address …

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 …

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 …

Evaluating The Performance Of Vision Transformer Architecture For Deepfake Image Classification, Devesan Govindasamy

Dissertations

Deepfake classification has seen some impressive results lately, with the experimentation of various deep learning methodologies, researchers were able to design some state-of-the art techniques. This study attempts to use an existing technology “Transformers” in the field of Natural Language Processing (NLP) which has been a de-facto standard in text processing for the purposes of Computer Vision. Transformers use a mechanism called “self-attention”, which is different from CNN and LSTM. This study uses a novel technique that considers images as 16x16 words (Dosovitskiy et al., 2021) to train a deep neural network with “self-attention” blocks to detect deepfakes. It creates …

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 …

Human Age And Gender Classification Using Convolutional Neural Networks, Eamon Kelliher

Dissertations

In a world relying ever more on human classification, this papers aims to improve on age and gender image classification through the use of Convolutional Neural Networks (CNN). Age and gender classification has become a popular area of study in the past number of years however there are still improvements to be made, particularly in the area of age classification. This research paper aims to test the currently accepted fact that CNN models are the superior model type for image classification by comparing CNN performance against Support Vector Machine performance on the same dataset. Using the Adience image classification dataset, …

Identifying Roles Of Software Developers From Their Answers On Stack Overflow, Dean Power

Dissertations

Stack Overflow is the world’s largest community of software developers. Users ask and answer questions on various tagged topics of software development. The set of questions a site user answers is representative of their knowledge base, or “wheelhouse”. It is proposed that clustering users by their wheelhouse yields communities of similar software developers by skill-set. These communities represent the different roles within software development and could be used as the basis to define roles at any point in time in an ever-evolving landscape of software development. A network graph of site users, linked if they answered questions on the same …

A Comparison Of Instructional Efficiency Models In Third Level Education, Murali Rajendran

Dissertations

This study investigates the validity and sensitivity of a novel model of instructional efficiency: the parabolic model. The novel model is compared against state-of-the-art models present in instructional design today; Likelihood model, Deviational model and Multidimensional model. This models is based on the assumption that optimal mental workload and high performance leads to high efficiency, while other models assume that low mental workload and high performance leads to high efficiency. The investigation makes use of two instructional design conditions: a direct instructions approach to learning and its extension with a collaborative activity. A control group received the former instructional design …

Feature Augmentation For Improved Topic Modeling Of Youtube Lecture Videos Using Latent Dirichlet Allocation, Nakul Srikumar

Dissertations

Application of Topic Models in text mining of educational data and more specifically, the text data obtained from lecture videos, is an area of research which is largely unexplored yet holds great potential. This work seeks to find empirical evidence for an improvement in Topic Modeling by pre- extracting bigram tokens and adding them as additional features in the Latent Dirichlet Allocation (LDA) algorithm, a widely-recognized topic modeling technique. The dataset considered for analysis is a collection of transcripts of video lectures on Machine Learning scraped from YouTube. Using the cosine similarity distance measure as a metric, the experiment showed …

Can Generative Adversarial Networks Help Us Fight Financial Fraud?, Sean Mciver

Dissertations

Transactional fraud datasets exhibit extreme class imbalance. Learners cannot make accurate generalizations without sufficient data. Researchers can account for imbalance at the data level, algorithmic level or both. This paper focuses on techniques at the data level. We evaluate the evidence of the optimal technique and potential enhancements. Global fraud losses totalled more than 80 % of the UK’s GDP in 2019. The improvement of preprocessing is inherently valuable in fighting these losses. Synthetic minority oversampling technique (SMOTE) and extensions of SMOTE are currently the most common preprocessing strategies. SMOTE oversamples the minority classes by randomly generating a point between …

Exploiting Bert And Roberta To Improve Performance For Aspect Based Sentiment Analysis, Gagan Reddy Narayanaswamy

Dissertations

Sentiment Analysis also known as opinion mining is a type of text research that analyses people’s opinions expressed in written language. Sentiment analysis brings together various research areas such as Natural Language Processing (NLP), Data Mining, and Text Mining, and is fast becoming of major importance to companies and organizations as it is started to incorporate online commerce data for analysis. Often the data on which sentiment analysis is performed will be reviews. The data can range from reviews of a small product to a big multinational corporation. The goal of performing sentiment analysis is to extract information from those …

Performance Comparison Between A Distributed Particle Swarm Algorithm And A Centralised Algorithm, Ciarán O’Loughlin

Dissertations

Particle Swarm optimisation (PSO) is a particular form of swarm intelligence, which itself is an innovative intelligent paradigm for solving optimization problems. PSO is generally used to find a global optimum in a single optimisation function. This typically occurs on one node(machine) but there has been a significant body of research into creating distributed implementations of the PSO algorithm. Such research has often focused on the creation and performance of the distributed implementation in an isolated manner or compared to different distributed algorithms.

This research piece aims to bridge a gap in the existing literature, by testing a distributed implementation …

Stellar Classification Of Folded Spectra Using The Mk Classification Scheme And Convolutional Neural Networks, John Magee

Dissertations

The year 1943 saw the introduction of the Morgan-Keenan (MK) classification scheme and this replaced the existing Harvard Classification scheme. Both stellar classification scheme are fundamentally grounded in the field of spectroscopy. The Harvard Classification scheme classified stars based on stellar surface temperature. The MK Classification scheme introduced the concept of a luminosity class that is intrinsically linked to the surface gravity of a star. Temperature and luminosity class values are estimated directly from the stellar spectrum.

Machine learning is a well-established technique in astronomy. Traditionally, a spectrum is treated as a one-dimensional sequence of data. Techniques such as artificial …

Event-Driven Servers Using Asynchronous, Non-Blocking Network I/O: Performance Evaluation Of Kqueue And Epoll, Lorcan Leonard

Dissertations

This research project evaluates the performance of kqueue and epoll in the context of event-driven servers. The evaluation is done through benchmarking and tracing which are used to measure throughput and execution time respectively. The experiment is repeated for both a virtualised and native server environment. The results from the experiment are statistically analysed and compared. These results show significant differences between kqueue and epoll, and a profound impact of virtualisation as a variable.

Improving A Network Intrusion Detection System’S Efficiency Using Model-Based Data Augmentation, Vinicius Waterkemper Lodetti

Dissertations

A network intrusion detection system (NIDS) is one important element to mitigate cybersecurity risks, the NIDS allow for detecting anomalies in a network which may be a cyberattack to a corporate network environment. A NIDS can be seen as a classification problem where the ultimate goal is to distinguish between malicious traffic among a majority of benign traffic. Researches on NIDS are often performed using outdated datasets that don’t represent the actual cyberspace. Datasets such as the CICIDS2018 address this gap by being generated from attacks and an infrastructure that reflects an up-to-date scenario.

A problem may arise when machine …

A Hybrid Neural Network For Stock Price Direction Forecasting, Daniel Devine

Dissertations

The volatility of stock markets makes them notoriously difficult to predict and is the reason that many investors sell out at the wrong time. Contrary to the efficient market hypothesis (EMH) and the random walk theory, contribution to the study of machine learning models for stock price forecasting has shown evidence of stock markets predictability with varying degrees of success. Contemporary approaches have sought to use a hybrid of convolutional neural network (CNN) for its feature extraction capabilities and long short-term memory (LSTM) neural network for its time series prediction. This comparative study aims to determine the predictability of stock …

Identifying Significant Features For Player Evaluation In Nfl Comparing Anns And Traditional Models, Ronan Walsh

Dissertations

The evaluation of player performance in sports is popular and important in modern sports, enabling teams to use real data in the construction of their rosters. This dissertation proposes to apply machine learning algorithms to predicting the player evaluations from a leading NFL analytics company who use a combination of statistics and expert evaluation. In addition, it will investigate what features are significant in the evaluation of a position. Data for the dissertation is obtained from multiple online sources - Pro Football Reference and Pro Football Focus (the the NFL analytics company). These data sets are combined and analysed before …

Evaluating The Performance Of Transformer Architecture Over Attention Architecture On Image Captioning, Deepti Balasubramaniam

Dissertations

Over the last few decades computer vision and Natural Language processing has shown tremendous improvement in different tasks such as image captioning, video captioning, machine translation etc using deep learning models. However, there were not much researches related to image captioning based on transformers and how it outperforms other models that were implemented for image captioning. In this study will be designing a simple encoder-decoder model, attention model and transformer model for image captioning using Flickr8K dataset where will be discussing about the hyperparameters of the model, type of pre-trained model used and how long the model has been trained. …

Finetuning Bert And Xlnet For Sentiment Analysis Of Stock Market Tweets Using Mixout And Dropout Regularization, Shubham Jangir

Dissertations

Sentiment analysis is also known as Opinion mining or emotional mining which aims to identify the way in which sentiments are expressed in text and written data. Sentiment analysis combines different study areas such as Natural Language Processing (NLP), Data Mining, and Text Mining, and is quickly becoming a key concern for businesses and organizations, especially as online commerce data is being used for analysis. Twitter is also becoming a popular microblogging and social networking platform today for information among people as they contribute their opinions, thoughts, and attitudes on social media platforms over the years. Because of the large …

An Evaluation On The Performance Of Code Generated With Webassembly Compilers, Raymond Phelan

Dissertations

WebAssembly is a new technology that is revolutionizing the web. Essentially it is a low-level binary instruction set that can be run on browsers, servers or stand-alone environments. Many programming languages either currently have, or are working on, compilers that will compile the language into WebAssembly. This means that applications written in languages like C++ or Rust can now be run on the web, directly in a browser or other environment. However, as we will highlight in this research, the quality of code generated by the different WebAssembly compilers varies and causes performance issues. This research paper aims to evaluate …

Image Instance Segmentation: Using The Cirsy System To Identify Small Objects In Low Resolution Images, Orghomisan William Omatsone

Dissertations

The CIRSY system (or Chick Instance Recognition System) is am image processing system developed as part of this research to detect images of chicks in highly-populated images that uses the leading algorithm in instance segmentation tasks, called the Mask R-CNN. It extends on the Faster R-CNN framework used in object detection tasks, and this extension adds a branch to predict the mask of an object along with the bounding box prediction. Mask R-CNN has proven to be effective ininstance segmentation and object de-tection tasks after outperforming all existing models on evaluation of the Microsoft Common Objects in Context (MS COCO) …

Brain Disease Detection From Eegs: Comparing Spiking And Recurrent Neural Networks For Non-Stationary Time Series Classification, Hristo Stoev

Dissertations

Modeling non-stationary time series data is a difficult problem area in AI, due to the fact that the statistical properties of the data change as the time series progresses. This complicates the classification of non-stationary time series, which is a method used in the detection of brain diseases from EEGs. Various techniques have been developed in the field of deep learning for tackling this problem, with recurrent neural networks (RNN) approaches utilising Long short-term memory (LSTM) architectures achieving a high degree of success. This study implements a new, spiking neural network-based approach to time series classification for the purpose of …

An Evaluation Of Text Representation Techniques For Fake News Detection Using: Tf-Idf, Word Embeddings, Sentence Embeddings With Linear Support Vector Machine., Sangita Sriram

Dissertations

In a world where anybody can share their views, opinions and make it sound like these are facts about the current situation of the world, Fake News poses a huge threat especially to the reputation of people with high stature and to organizations. In the political world, this could lead to opposition parties making use of this opportunity to gain popularity in their elections. In the medical world, a fake scandalous message about a medicine giving side effects, hospital treatment gone wrong or even a false message against a practicing doctor could become a big menace to everyone involved in …

Drug Reviews: Cross-Condition And Cross-Source Analysis By Review Quantification Using Regional Cnn-Lstm Models, Ajith Mathew Thoomkuzhy

Dissertations

Pharmaceutical drugs are usually rated by customers or patients (i.e. in a scale from 1 to 10). Often, they also give reviews or comments on the drug and its side effects. It is desirable to quantify the reviews to help analyze drug favorability in the market, in the absence of ratings. Since these reviews are in the form of text, we should use lexical methods for the analysis. The intent of this study was two-fold: First, to understand how better the efficiency will be if CNN-LSTM models are used to predict ratings or sentiment from reviews. These models are known …

Classification Of Animal Sound Using Convolutional Neural Network, Neha Singh

Dissertations

Recently, labeling of acoustic events has emerged as an active topic covering a wide range of applications. High-level semantic inference can be conducted based on main audioeffects to facilitate various content-based applications for analysis, efficient recovery and content management. This paper proposes a flexible Convolutional neural network-based framework for animal audio classification. The work takes inspiration from various deep neural network developed for multimedia classification recently. The model is driven by the ideology of identifying the animal sound in the audio file by forcing the network to pay attention to core audio effect present in the audio to generate Mel-spectrogram. …

A Comparative Study Of Text Summarization On E-Mail Data Using Unsupervised Learning Approaches, Tijo Thomas

Dissertations

Over the last few years, email has met with enormous popularity. People send and receive a lot of messages every day, connect with colleagues and friends, share files and information. Unfortunately, the email overload outbreak has developed into a personal trouble for users as well as a financial concerns for businesses. Accessing an ever-increasing number of lengthy emails in the present generation has become a major concern for many users. Email text summarization is a promising approach to resolve this challenge. Email messages are general domain text, unstructured and not always well developed syntactically. Such elements introduce challenges for study …

Content-Based Filtering Recommendation Approach To Label Irish Legal Judgements, Sandesh Gangadhar

Dissertations

Machine learning approaches are applied across several domains to either simplify or automate tasks which directly result in saved time or cost. Text document labelling is one such task that requires immense human knowledge about the domain and efforts to review, understand and label the documents. The company Stare Decisis summarises legal judgements and labels them as they are made available on Irish public legal source www.courts.ie. This research presents a recommendation-based approach to reduce the time for solicitors at Stare Decisis by reducing many numbers of available labels to pick from to a concentrated few that potentially contains the …

Customer Churn Prediction, Deepshikha Wadikar

Dissertations

Churned customers identification plays an essential role for the functioning and growth of any business. Identification of churned customers can help the business to know the reasons for the churn and they can plan their market strategies accordingly to enhance the growth of a business. This research is aimed at developing a machine learning model that can precisely predict the churned customers from the total customers of a Credit Union financial institution. A quantitative and deductive research strategies are employed to build a supervised machine learning model that addresses the class imbalance problem handled feature selection and efficiently predict the …

An Examination Of The Smote And Other Smote-Based Techniques That Use Synthetic Data To Oversample The Minority Class In The Context Of Credit-Card Fraud Classification, Eduardo Parkinson De Castro

Dissertations

This research project seeks to investigate some of the different sampling techniques that generate and use synthetic data to oversample the minority class as a means of handling the imbalanced distribution between non-fraudulent (majority class) and fraudulent (minority class) classes in a credit-card fraud dataset. The purpose of the research project is to assess the effectiveness of these techniques in the context of fraud detection which is a highly imbalanced and cost-sensitive dataset. Machine learning tasks that require learning from datasets that are highly unbalanced have difficulty learning since many of the traditional learning algorithms are not designed to cope …