Computer Sciences Commons^™

Looping Predictive Method To Improve Accuracy Of A Machine Learning Model, Subramanyam Reddy Pogili

Theses

The topic of this project is an analysis of drug-related tweets. The goal is to build a Machine Learning Model that can distinguish between tweets that indicate drug abuse and other tweets that also contain the name of a drug but do not describe abuse. Drugs can be illegal, such as heroin, or legal drugs with a potential of abuse, such as painkillers. However, building a good Machine Learning Model requires a large amount of training data. For each training tweet, a human expert has determined whether it indicates drug abuse or not. This is difficult work for humans. …

Business-It Alignment In Higher Education Institutions: United Arab Emirates University Case Study, Nayla Salem Al Khateri

Theses

This thesis addresses the importance of Business-IT alignment in higher education institutions. Business-IT alignment is defined as applying IT in a suitable and timely manner, in harmony with business strategies, goals and needs. Business- IT alignment is an ultimate goal of governmental and non-governmental organizations that requires close attention and continuous monitoring. UAE university has a well-defined business strategy augmented with a well-defined IT strategy. So, to get the most benefits of acquiring and using IT in the university, the IT need to be aligned with the core business and the supporting services. The main objective of this thesis is …

Matrix Completion Algorithms With Applications In Biomedicine, E-Commerce And Social Science, Yiran Wang

Theses

This thesis investigates matrix completion algorithms with applications in biomedicine, e-commerce and social science. In general, matrix completion algorithms work well for low rank matrices. Such matrices find many applications in recommender systems and social network analysis. On the other hand, biological networks often yield high rank matrices. For example, the adjacency matrix representing interactions between transcription factors and target genes in the cell is a highly sparse matrix, in which most entries correspond to absent interactions and only a few entries correspond to present interactions. This sparse matrix is a high rank or even full rank matrix. Matrix completion …

A Parallelized Method For Solving Large Scale Integer Linear Optimization Problems Using Cut-And-Solve With Applications To Cgwas, John Brandenburg

Theses

The commercial solver CPLEX has been one of the top solvers of mixed-integer and purely integer linear problems for some time. Its method of solving, Branch-and-Cut, has been shown to be highly effective, but has its limits in terms of input sizes which are tractable, and cannot be effectively parallelized beyond a small number. Here we present a different method of solution, Cut-and-Solve, which utilizes the power of CPLEX to effectively parallelize any mixed-integer or integer linear problem. We have utilized Cut-and-Solve in a novel way to offer optimal solution guarantees more quickly. We will show comparisons of Cut-and-Solve to …

Network Exploration Of Correlated Multivariate Protein Data For Alzheimer's Disease Association, Matthew J. Lane

Theses

Alzheimer Disease (AD) is difficult to diagnose by using genetic testing or other traditional methods. Unlike diseases with simple genetic risk components, there exists no single marker determining as to whether someone will develop AD. Furthermore, AD is highly heterogeneous and different subgroups of individuals develop the disease due to differing factors. Traditional diagnostic methods using perceivable cognitive deficiencies are often too little too late due to the brain having suffered damage from decades of disease progression. In order to observe AD at early stages prior to the observation of cognitive deficiencies, biomarkers with greater accuracy are required. By using …

Mobile Big Data Analytics In Healthcare, Alramzana Nujum Navaz

Theses

Mobile and ubiquitous devices are everywhere around us generating considerable amount of data. The concept of mobile computing and analytics is expanding due to the fact that we are using mobile devices day in and out without even realizing it. These mobile devices use Wi-Fi, Bluetooth or mobile data to be intermittently connected to the world, generating, sending and receiving data on the move. Latest mobile applications incorporating graphics, video and audio are main causes of loading the mobile devices by consuming battery, memory and processing power. Mobile Big data analytics includes for instance, big health data, big location data, …

Intelligent Profiling Of Blood Donors In Ireland, Joanna Kossakowska

Theses

The demand for blood products in Ireland is constantly rising due to population growth and population ageing. It is believed that within the next decade these two factors will present challenges to blood donor recruitment and the availability of blood supplies. Improving the retention of blood donors will have a positive impact on the availability of blood products. Identification of suitable donors with the potential for long-term donating can potentially enhance the predictability of blood supply levels.

This research proposes that the patterns of blood donation behaviours of donors can be isolated from blood donor databases held by blood collecting …

Novel Neuroevolution Techniques For The Life Science Domain, Timothy Manning

Theses

The life science domain is a high value research area, both in terms of the benefits in increased knowledge and in societal impact. Much of the research funding has focused on wet lab based approaches to increase visibility into biological processes and producing maximal relevant information on which to make decisions. Given the complexity of biological functions, in many cases this has led to an information overload. Researchers are now able to routinely generate and access petabytes of data as a result of high throughput experiments, and this capability is growing. This data can be difficult to interpret and intractable …

A Robust System For Local Reuse Detection Of Arabic Text On The Web, Leena Mahmoud Ahmed Lulu

Theses

We developed techniques for finding local text reuse on the Web, with an emphasis on the Arabic language. That is, our objective is to develop text reuse detection methods that can detect alternative versions of the same information and focus on exploring the feasibility of employing text reuse detection methods on the Web. The results of this research can be thought of as rich tools to information analysts for corporate and intelligence applications. Such tools will become essential parts in validating and assessing information coming from uncertain origins. These tools will prove useful for detecting reuse in scientific literature too. …

Sla Management In A Collaborative Network Of Federated Clouds: The Cloudland, Asma Obaid Subaih Ai Falasi

Theses

Cloud services have always promised to be available, flexible, and speedy. However, not a single Cloud provider can deliver such promises to their distinctly demanding customers. Cloud providers have a constrained geographical presence, and are willing to invest in infrastructure only when it is profitable to them. Cloud federation is a concept that collectively combines segregated Cloud services to create an extended pool of resources for Clouds to competently deliver their promised level of services. This dissertation is concerned with studying the governing aspects related to the federation of Clouds through collaborative networking. The main objective of this dissertation is …

Early Packet Rejection Using Dynamic Binary Decision Diagram, Vasiqullah Molvizadah

Theses

A firewall is a hardware or software device that performs inspection on a given incoming/outgoing packets and decide whether to allow/deny the packet from entering/leaving the system. Firewall filters the packets by using a set of rules called firewall policies. The policies define what type of packets should be allowed or discarded. These policies describe the field values that the packet header must contain in order to match a policy in the firewall. The decision for any given packet is made by finding the first matching firewall policy, if any.

In a traditional firewall, the packet filter goes through each …

Integration Of Lightweight & Energy Efficient Cipher In Wireless Body Area Network Fore-Health Monitoring, Azza Zayed Aishamsi

Theses

There is an increase in the diseases of the circulatory system in United Arab Emirates, which makes it the first leading cause of death. This led to a high demand for a continuous care that can be achieved by adopting an emerging technology of e- Health monitoring system using Wireless Body Area Network (WBAN) that can collect patient’s data. Since patient’s data is private, securing the communication within WBAN becomes highly essential. In this research thesis, we propose an architecture to secure the data transmission within the Wireless Body Area Network (WBAN) in e-Health monitoring. More specifically, our proposed architecture …

Towards Trustworthy Version Control Systems: Enhancing The Security Of Subversion, Ruchir Arya

Theses

Software development often relies on a Version Control System (VCS) to manage the source code, documentation and configuration of files. A VCS allows team development in which multiple developers can work simultaneously on source code updates. It also provides the ability to keep track of the historical changes made to the data over time, including the ability to retrieve previous versions of the source code in order to locate and fix bugs, and roll back to earlier versions in case the working version becomes buggy or unstable.

Apache Subversion (SVN) is a popular version control system that uses a client-server …

Semi Supervised Weighted Maximum Variance Dimensionality Reduction, Pranitha Surya Andalam

Theses

In the recent years, we have huge amounts of data which we want to classify with minimal human intervention. Only few features from the data that is available might be useful in some scenarios. In those scenarios, the dimensionality reduction methods play a major role for extracting useful features. The two parameter weighted maximum variance (2P-WMV) is a generalized dimensionality reduction method of which principal component analysis (PCA) and maximum margin criterion (MMC) are special cases.. In this paper, we have extended the 2P-WMV approach from our previous work to a semi-supervised version. The objective of this work is specially …

Data Analytics With Mapreduce In Apache Spark And Hadoop Systems, Zongxuan Du

Theses

MapReduce comes from a traditional problem solving method: separating a big problem and solving each small parts. With the target of computing larger dataset in more efficient and cheaper way, this is implement into a programming mode to deal with massive quantity of data. The users get a map function and use it to abstract dataset into key / value logical pair and then use a reduce function to group all value with the same key. With this mode, task can be automatic spread the job into clusters grouped by lots of normal computers. MapReduce program can be easily implemented …

Gene Network Understanding And Analysis, Maria E. Somoza

Theses

Gene regulatory network (GRN) is a collection of regulators that interact with each other in the cell to govern the gene expression levels of mRNA and proteins. These regulators can either be DNA, RNA, protein and their complex. Transcriptional gene regulation is an important mechanisms in which an in-depth study can lead to various practical applications, and a greater understanding of how organisms control their cellular behavior. One of the most widely studied organisms in gene regulatory networks are the Mycobacterium tuberculosis and Corynebacterium glutamicum ATCC 13032.

Gene co-expression networks are of biological interests due to co-expressed genes which are …

Uusing The Kdj As A Trading Strategy On Biotech Companies, Shijie Zha

Theses

Mean Reversion is the most commonly used model in quantitative trading. This model is associated with several factors, like ma5 and ma10 line. These factors are the most significant in stock markets. However, the disadvantages of this model are lag and inaccuracy.

In this research, we get the historical and current stock data by web crawler, analyze the quantitative data and build a new model involved with the KDJ. Taking biotech companies marketed in the United States and B-share marketed in China as the research subjects, the result shows increased profits compared with the Mean Reversion model. It also shows …

An Exploration Of The Effectiveness Of The Use Of Communication Apps Through Mobile Devices On Children With Autism Spectrum Disorders (Asd), Miriam O Sullivan

Theses

Autism Spectrum Disorder (ASD) is a complex neurological disorder which impacts on people in three primary areas: communication skills, social skills and behaviour skills. The diagnosis of ASD continues to rise with an estimated 1 in 100 receiving diagnoses of ASD in Ireland. There are many interventions promoted on a regular basis that claim positive effects on the basis of empirical research. However, the claims made by such studies are sometimes a little at odds with the level of methodological rigour and/or sample size employed. The research available is based on small scale international studies (America, Canada and Australia); however, …

Enhancing Snort Ids Performance Using Data Mining, Mohammed Ali Almaleki

Theses

Intrusion detection systems (IDSs) such as Snort apply deep packet inspection to detect intrusions. Usually, these are rule-based systems, where each incoming packet is matched with a set of rules. Each rule consists of two parts: the rule header and the rule options. The rule header is compared with the packet header. The rule options usually contain a signature string that is matched with packet content using an efficient string matching algorithm. The traditional approach to IDS packet inspection checks a packet against the detection rules by scanning from the first rule in the set and continuing to scan all …

Biometrics-Based Dynamic Authentication For Secure Services, Saif Mohammed Saeed Abdulla Al Aryani

Theses

This thesis proposes a secure authentication protocol against physical session hijacking attacks. In client/server technology, users establish sessions to access the services offered by the servers. However, using physical session hijacking attacks, malicious users may physically take control of ongoing sessions. Malicious users also can establish sessions with servers using stolen passwords. In both cases, the server will be communicating with the wrong user who pretends to be the real user. The goal of this authentication protocol is to continuously and dynamically ensure that during an ongoing session the current session’s user is himself the real person that is known …

Securing The Integrity Of The Power Distribution System For Smart Grid Applications, Hosam Yousef Hittini

Theses

The distribution system is one of the main components in a smart grid, readings are transferred from the distribution substations to the control center. Compromising transferred system data will result in drawing wrong conclusions about current operation status at the control center. Which leads to sending wrong operational commands that may result in very serious consequences.

Firstly, we propose a scalable communications architecture for future smart grid distribution systems (i.e. Security Aware Distribution System Architecture - SADSA). The architecture is adaptable to use Wi-Fi or other technologies to transfer smart grid information. The architecture is studied from various angles. Both …

Cloud Practical Exam Invigilation Control Systems With The Objective Of Enhancing Quality Control For Online Exams, Gordon O'Reilly

Theses

Online cloud computing courses are becoming more common place facilitating a student to study from home from anywhere in the world. Coupled with this trend is a need for educational institutions to facilitate students to take tests or exams online from home. It reduces the remote student’s time and cost of travel to an exam invigilation centre as well as reducing the educational institution’s test administration overhead. It does however introduce potential quality control concerns. A new industry called online proctoring has emerged that attempts to provide quality control in these online test scenarios.

This research provides an insight into …

Neural Networks For Autonomous Control Of Unmanned Helicopters, Padraig M. Moriarty

Theses

Landing a helicopter on a ship in high seas can be a dangerous endeavour. This thesis proposes to examine the possible uses of Artificial Neural Networks (A.N.N.) in the aiding and/or the landing of an Unmanned Aerial Vehicle (U.A.V.). It proposes that this procedure can be segregated into three distinct phases. The data for the A.N.N. training and testing sets is generated through simulation in the Unity cross-platform game engine. Phase 1 is intended to convert video images from an on-board camera to a set of numeric outputs suitable for use in Phase 2. Phase 2 estimates the current relative …

Exact Genome Alignment, Nandini Ghosh

Theses

The increase in the volume of genomic data due to the decrease in the cost of whole genome sequencing techniques has opened up new avenues of research in the field of Bioinformatics, like comparative genomics and evolutionary dynamics. The fundamental task in these studies is to align the genome sequences accurately. Sequence alignment helps to identify regions of similarity between the sequences to establish their functional, evolutionary and structural relationship. The thesis investigates the performance of two sequence alignment programs LASTZ, a hash table based faster method and SSEARCH, a slower but more rigorous Smith-Waterman based approach, on whole genome …

Unsupervised Gene Regulatory Network Inference On Microarray Data, Nidhi Radia

Theses

Obtaining gene regulatory networks (GRNs) from expression data is a challenging and crucial task. Many computational methods and algorithms have been developed to infer gene networks for gene expression data, which are usually obtained from microarray experiments. A gene network is a method to depict the relation among clusters of genes. To infer gene networks, the unsupervised method is used in this study. The two types of data used are time-series data and steady-state data. The data is analyzed using various tools containing different algorithms and concepts. GRNs from time-series data tools are obtained using the Time-delayed Algorithm for the …

Identifying Modifier Genes In Sma Model Mice, Weiting Xu

Theses

Spinal Muscular Atrophy (SMA) involves the loss of nerve cells called motor neurons in the spinal cord and is classified as a motor neuron disease, it affects 1 in 5000-10000 newborns, one of the leading genetic causes of infant death in USA. Mutations in the SMN1, UBA1, DYNC1H1 and VAPB genes cause spinal muscular atrophy. Extra copies of the SMN2 gene modify the severity of spinal muscular atrophy. Mutations in SMN1 (Motor Neuron 1) mainly causes SMA (Autosomal recessive inheritance). SMN1 gene mutations lead to a shortage of the SMN protein and SMN protein forms SMN complex …

Formal Specification And Refinement Of The Navigation Tasks Of Autonomous Robots, Eman Rabiah

Theses

Autonomous robots are hybrid systems whose role in our daily life is becoming increasingly critical. They are tasked with various activities requiring reliability, safety, and correctness of their software-controlled behavior. Formal methods have been proved effective in addressing development issues associated with these software qualities. However, even though autonomous robot navigation is a primordial function, there is no research dealing with enhancing reliability of the navigation algorithms. Thus, our focus is to investigate this type of algorithms, and specifically path planning, a fundamental and critical functionality supporting autonomy. We formally address the issue of enhancing reliability of the widely-used A* …

Uav-Cloud: A Platform For Uav Resources And Services On The Cloud, Sara Yousif Mohamed Mahmoud

Theses

UAVs - Unmanned Aerial Vehicles – have gained significant attention recently, due to the increasingly growing range of applications. However, developing collaborative UAV applications using traditional technologies in a tightly coupled design requires a great deal of development effort, time, and budget especially for heterogeneous UAVs. Moreover, monitoring and accessing UAV resources using traditional communication media suffer from several restrictions and limitations. This research aims to simplify the efforts, reduce the time, and lower the costs of developing collaborative applications for distributed heterogeneous UAVs. In addition, the research aims to provide ubiquitous UAV resources access. A platform is proposed for …

Rice And Mouse Quantitative Phenotype Prediction In Genome-Wide Association Studies With Support Vector Regression, Abdulrhman Fahad M. Aljouie

Theses

Quantitative phenotypes prediction from genotype data is significant for pathogenesis, crop yields, and immunity tests. The scientific community conducted many studies to find unobserved quantitative phenotype high predictive ability models. Early genome-wide association studies (GWAS) focused on genetic variants that are associated with disease or phenotype, however, these variants manly covers small portion of the whole genetic variance, and therefore, the effectiveness of predictions obtained using this information may possibly be circumscribed [ 1 ].

Instead, this study shows prediction ability from whole genome single nucleotide polymorphisms (SNPs) data of 1940 genotyped stoke mouse with - 12k SNPs, and 413 …

Cancer Risk Prediction With Next Generation Sequencing Data Using Machine Learning, Nihir Patel

Theses

The use of computational biology for next generation sequencing (NGS) analysis is rapidly increasing in genomics research. However, the effectiveness of NGS data to predict disease abundance is yet unclear. This research investigates the problem in the whole exome NGS data of the chronic lymphocytic leukemia (CLL) available at dbGaP. Initially, raw reads from samples are aligned to the human reference genome using burrows wheeler aligner. From the samples, structural variants, namely, Single Nucleotide Polymorphism (SNP) and Insertion Deletion (INDEL) are identified and are filtered using SAMtools as well as with Genome Analyzer Tool Kit (GATK). Subsequently, the variants are …