Computer Sciences Commons^™

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 …

Combination Of Facebook Prophet And Attention-Based Lstm With Multi- Source Data For Indian Stock Market Prediction, Pavan Nagesh

Dissertations

The stock market prediction has been the subject of interest to various researchers and analysts due to its highly unpredictable nature and serves as a perfect example for time series forecasting. Over the years deep learning models such as Long-Term Short-Term Memory and statistical models such as Autoregressive Integrated Moving Average have shown promising results in predicting future stock prices. But the results from these models cannot be generalized as they fail to incorporate the dynamics of the market and influence of several external factors such as political, social, investor's emotion, etc on stock markets. Recently Facebook’s creation of the …

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 …

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, …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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.

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 …

Coordination, Adaptation, And Complexity In Decision Fusion, Weiqiang Dong

Dissertations

A parallel decentralized binary decision fusion architecture employs a bank of local detectors (LDs) that access a commonly-observed phenomenon. The system makes a binary decision about the phenomenon, accepting one of two hypotheses (H0 (“absent”) or H1 (“present”)). The k 1 LD uses a local decision rule to compress its local observations yk into a binary local decision uk; uk = 0 if the k 1 LD accepts H0 and uk = 1 if it accepts H1. The k 1 LD sends its decision uk over a noiseless dedicated channel to a Data Fusion Center (DFC). The DFC combines the …

Drone-Assisted Emergency Communications, Di Wu

Dissertations

Drone-mounted base stations (DBSs) have been proposed to extend coverage and improve communications between mobile users (MUs) and their corresponding macro base stations (MBSs). Different from the base stations on the ground, DBSs can flexibly fly over and close to MUs to establish a better vantage for communications. Thus, the pathloss between a DBS and an MU can be much smaller than that between the MU and MBS. In addition, by hovering in the air, the DBS can likely establish a Line-of-Sight link to the MBS. DBSs can be leveraged to recover communications in a large natural disaster struck area …

A Deep Machine Learning Approach For Predicting Freeway Work Zone Delay Using Big Data, Abdullah Shabarek

Dissertations

The introduction of deep learning and big data analytics may significantly elevate the performance of traffic speed prediction. Work zones become one of the most critical factors causing congestion impact, which reduces the mobility as well as traffic safety. A comprehensive literature review on existing work zone delay prediction models (i.e., parametric, simulation and non-parametric models) is conducted in this research. The research shows the limitations of each model. Moreover, most previous modeling approaches did not consider user delay for connected freeways when predicting traffic speed under work zone conditions. This research proposes Deep Artificial Neural Network (Deep ANN) and …

Supporting User Interaction And Social Relationship Formation In A Collaborative Online Shopping Context, Yu Xu

Dissertations

The combination of online shopping and social media allow people with similar shopping interests and experiences to share, comment, and discuss about shopping from anywhere and at any time, which also leads to the emergence of online shopping communities. Today, more people turn to online platforms to share their opinions about products, solicit various opinions from their friends, family members, and other customers, and have fun through interactions with others with similar interests. This dissertation explores how collaborative online shopping presents itself as a context and platform for users' interpersonal interactions and social relationship formation through a series of studies. …

Performance Optimization Of Big Data Computing Workflows For Batch And Stream Data Processing In Multi-Clouds, Huiyan Cao

Dissertations

Workflow techniques have been widely used as a major computing solution in many science domains. With the rapid deployment of cloud infrastructures around the globe and the economic benefits of cloud-based computing and storage services, an increasing number of scientific workflows have migrated or are in active transition to clouds. As the scale of scientific applications continues to grow, it is now common to deploy various data- and network-intensive computing workflows such as serial computing workflows, MapReduce/Spark-based workflows, and Storm-based stream data processing workflows in multi-cloud environments, where inter-cloud data transfer oftentimes plays a significant role in both workflow performance …

Semantic, Integrated Keyword Search Over Structured And Loosely Structured Databases, Xinge Lu

Dissertations

Keyword search has been seen in recent years as an attractive way for querying data with some form of structure. Indeed, it allows simple users to extract information from databases without mastering a complex structured query language and without having knowledge of the schema of the data. It also allows for integrated search of heterogeneous data sources. However, as keyword queries are ambiguous and not expressive enough, keyword search cannot scale satisfactorily on big datasets and the answers are, in general, of low accuracy. Therefore, flat keyword search alone cannot efficiently return high quality results on large data with structure. …

Countering Internet Packet Classifiers To Improve User Online Privacy, Sina Fathi-Kazerooni

Dissertations

Internet traffic classification or packet classification is the act of classifying packets using the extracted statistical data from the transmitted packets on a computer network. Internet traffic classification is an essential tool for Internet service providers to manage network traffic, provide users with the intended quality of service (QoS), and perform surveillance. QoS measures prioritize a network's traffic type over other traffic based on preset criteria; for instance, it gives higher priority or bandwidth to video traffic over website browsing traffic. Internet packet classification methods are also used for automated intrusion detection. They analyze incoming traffic patterns and identify malicious …

Hierarchical Aggregation Of Multidimensional Data For Efficient Data Mining, Safaa Khalil Alwajidi

Dissertations

Big data analysis is essential for many smart applications in areas such as connected healthcare, intelligent transportation, human activity recognition, environment, and climate change monitoring. Traditional data mining algorithms do not scale well to big data due to the enormous number of data points and the velocity of their generation. Mining and learning from big data need time and memory efficiency techniques, albeit the cost of possible loss in accuracy. This research focuses on the mining of big data using aggregated data as input. We developed a data structure that is to be used to aggregate data at multiple resolutions. …

Hybrid Deep Neural Networks For Mining Heterogeneous Data, Xiurui Hou

Dissertations

In the era of big data, the rapidly growing flood of data represents an immense opportunity. New computational methods are desired to fully leverage the potential that exists within massive structured and unstructured data. However, decision-makers are often confronted with multiple diverse heterogeneous data sources. The heterogeneity includes different data types, different granularities, and different dimensions, posing a fundamental challenge in many applications. This dissertation focuses on designing hybrid deep neural networks for modeling various kinds of data heterogeneity.

The first part of this dissertation concerns modeling diverse data types, the first kind of data heterogeneity. Specifically, image data and …

Enrichment Of Ontologies Using Machine Learning And Summarization, Hao Liu

Dissertations

Biomedical ontologies are structured knowledge systems in biomedicine. They play a major role in enabling precise communications in support of healthcare applications, e.g., Electronic Healthcare Records (EHR) systems. Biomedical ontologies are used in many different contexts to facilitate information and knowledge management. The most widely used clinical ontology is the SNOMED CT. Placing a new concept into its proper position in an ontology is a fundamental task in its lifecycle of curation and enrichment.

A large biomedical ontology, which typically consists of many tens of thousands of concepts and relationships, can be viewed as a complex network with concepts as …

Crowdsourcing Atop Blockchains, Yuan Lu

Dissertations

Traditional crowdsourcing systems, such as Amazon's Mechanical Turk (MTurk), though once acquiring great economic successes, have to fully rely on third-party platforms to serve between the requesters and the workers for basic utilities. These third-parties have to be fully trusted to assist payments, resolve disputes, protect data privacy, manage user authentications, maintain service online, etc. Nevertheless, tremendous real-world incidents indicate how elusive it is to completely trust these platforms in reality, and the reduction of such over-reliance becomes desirable.

In contrast to the arguably vulnerable centralized approaches, a public blockchain is a distributed and transparent global "consensus computer" that is …

Machine Learning For Scientific Data Mining And Solar Eruption Prediction, Hao Liu

Dissertations

This dissertation explores new machine learning techniques and adapts them to mine scientific data, specifically data from solar physics and space weather studies. The dissertation tackles three important problems in heliophysics: solar flare prediction, coronal mass ejection (CME) prediction and Stokes inversion.

First, the dissertation presents a long short-term memory (LSTM) network for predicting whether an active region (AR) would produce a certain class of solar flare within the next 24 hours. The essence of this approach is to model data samples in an AR as time series and use LSTMs to capture temporal information of the data samples. The …

Energy And Performance-Optimized Scheduling Of Tasks In Distributed Cloud And Edge Computing Systems, Haitao Yuan

Dissertations

Infrastructure resources in distributed cloud data centers (CDCs) are shared by heterogeneous applications in a high-performance and cost-effective way. Edge computing has emerged as a new paradigm to provide access to computing capacities in end devices. Yet it suffers from such problems as load imbalance, long scheduling time, and limited power of its edge nodes. Therefore, intelligent task scheduling in CDCs and edge nodes is critically important to construct energy-efficient cloud and edge computing systems. Current approaches cannot smartly minimize the total cost of CDCs, maximize their profit and improve quality of service (QoS) of tasks because of aperiodic arrival …

Global Optimization Algorithms For Image Registration And Clustering, Cuicui Zheng

Dissertations

Global optimization is a classical problem of finding the minimum or maximum value of an objective function. It has applications in many areas, such as biological image analysis, chemistry, mechanical engineering, financial analysis, deep learning and image processing. For practical applications, it is important to understand the efficiency of global optimization algorithms. This dissertation develops and analyzes some new global optimization algorithms and applies them to practical problems, mainly for image registration and data clustering.

First, the dissertation presents a new global optimization algorithm which approximates the optimum using only function values. The basic idea is to use the points …

Changing The Focus: Worker-Centric Optimization In Human-In-The-Loop Computations, Mohammadreza Esfandiari

Dissertations

A myriad of emerging applications from simple to complex ones involve human cognizance in the computation loop. Using the wisdom of human workers, researchers have solved a variety of problems, termed as “micro-tasks” such as, captcha recognition, sentiment analysis, image categorization, query processing, as well as “complex tasks” that are often collaborative, such as, classifying craters on planetary surfaces, discovering new galaxies (Galaxyzoo), performing text translation. The current view of “humans-in-the-loop” tends to see humans as machines, robots, or low-level agents used or exploited in the service of broader computation goals. This dissertation is developed to shift the focus back …