Digital Commons Network^™

Comparative Study Of Generative Models For Text-To-Image Generation, Nazia Siddiqui

Electronic Theses and Dissertations

The development of deep learning algorithms has tremendously helped computer vision applications, image processing methods, Artificial Intelligence, and Natural Language Processing. One such application is image synthesis, which is the creation of new images from text. Recent techniques for text-to-image synthesis offer an intriguing yet straight forward conversion capability from text to image and have become a popular research topic. Synthesis of images from text descriptors has practical and creative applications in computer-aided design, multimodal learning, digital art creation, etc. Non-Fungible Tokens (NFTs) are a form of digital art that is being used as tokens for trading across the globe. …

Online Sexual Predator Detection, Muhammad Khalid

Electronic Theses and Dissertations

Online sexual abuse is a concerning yet severely overlooked vice of modern society. With more children being on the Internet and with the ever-increasing advent of web-applications such as online chatrooms and multiplayer games, preying on vulnerable users has become more accessible for predators. In recent years, there has been work on detecting online sexual predators using Machine Learning and deep learning techniques. Such work has trained on severely imbalanced datasets, and imbalance is handled via manual trimming of over-represented labels. In this work, we propose an approach that first tackles the problem of imbalance and then improves the effectiveness …

Practical Secure Aggregation In Federated Learning Using Additive Secret Sharing, Hamid Fazli Khojir

Electronic Theses and Dissertations

Federated learning is a machine learning technique where multiple clients with local data collaborate in training a machine learning model. In FedAvg, the main federated learning algorithm, clients train machine learning models locally and share the trained model with the server. While the sensitive data will never be sent to the server, a malicious server can construct the original training data by having access to the clients’ models in each training round. Secure aggregation techniques such as cryptography, trusted execution environment, or differential privacy are used to solve this problem. However, these techniques incur computation and communication overhead or affect …

Robot Learning From Human Observation Using Deep Neural Networks, Michael Elachkar

Electronic Theses and Dissertations

Industrial robots have gained traction in the last twenty years and have become an integral component in any sector empowering automation. Specifically, the automotive industry implements a wide range of industrial robots in a multitude of assembly lines worldwide. These robots perform tasks with the utmost level of repeatability and incomparable speed. It is that speed and consistency that has always made the robotic task an upgrade over the same task completed by a human. The cost savings is a great return on investment causing corporations to automate and deploy robotic solutions wherever feasible.

The cost to commission and set …

Human-Machine Collaboration In Healthcare Innovation, Breeze Fenton

Electronic Theses and Dissertations

Almost every individual has visited a healthcare institute, whether for an annual checkup, surgery, or a nursing home. Ensuring healthcare institutes are using human-machine collaboration systems correctly can improve daily operations. A maturity assessment and an implementation plan have been developed to help healthcare institutes monitor the human-machine collaboration systems. A maturity model, the Smart Maturity Model for Health Care (SMMHC), is a tool designed for maturity assessment. A four-step implementation plan was also created in this research. The implementation plan views the maturity of the institute and develops a strategy on how to improve it. The research utilized Integrated …

Hardware Implementations Of Spiking Neural Networks And Artificially Intelligent Systems, Alexander J. Leigh

Electronic Theses and Dissertations

Artificial spiking neural networks are gaining increasing prominence due to their potential advantages over traditional, time-static artificial neural networks. Custom hardware implementations of spiking neural networks present many advantages over other implementation mediums. Two main topics are the focus of this work. Firstly, digital hardware implementations of spiking neurons and neuromorphic hardware are explored and presented. These implementations include novel implementations for lowered digital hardware requirements and reduced power consumption.

The second section of this work proposes a novel method for selectively adding sparsity to a spiking neural network based on training set images for pattern recognition applications, thereby greatly …

Identifying Network Biomarkers For Each Breast Cancer Subtypes Along With Their Effective Single And Paired Repurposed Drugs Using Network-Based Machine Learning Techniques, Forough Firoozbakht

Electronic Theses and Dissertations

Breast cancer is a complex disease that can be classified into at least 10 different molecular subtypes. Appropriate diagnosis of specific subtypes is critical for ensuring the best possible patient treatment and response to therapy. Current computational methods for determining the subtypes are based on identifying differentially expressed genes (i.e., biomarkers) that can best discriminate the subtypes. Such approaches, however, are known to be unreliable since they yield different biomarker sets when applied to data sets from different studies. Gathering knowledge about the functional relationship among genes will identify “network biomarkers” that will enrich the criteria for biomarker selection. Cancer …

Emergency Evaluation In Connected And Automated Vehicles, Elvin Eziama

Electronic Theses and Dissertations

An intelligent transportation system (ITS) provides improved transport efficiency and safety based on vehicle communication. Connected and automated vehicles (CAVs) as part of an ITS are projected to revolutionize the transportation industry, primarily by allowing real-time and seamless information exchange between vehicles and roadside infrastructure. Although these CAVs are expected to offer vast benefits, new problems in terms of safety, security, and privacy will also emerge. Since CAVs continue to rely heavily on vehicle sensors and information obtained from other vehicles and roadside units, abnormal sensors and malicious cyber attacks can lead to destructive results and fatal crashes. Therefore, ensuring …

Active Community Opinion Network Mining And Maximization Through Social Networks Posts, Mayank Semwal

Electronic Theses and Dissertations

Existing OM systems like CONE take a partial historical rating of users on multiple products and perform opinion estimation to maximizes overall positive opinions using OM. However, CONE does not consider actual user opinions from social posts where users provide opinions through comments, likes and sharing about a product. OBIN mines users' low-frequency features from comments to create a community preference influence network utilizing user response on posts and relationships between them. However, OBIN only performs feature-level opinion mining and does not consider a joint approach that combines sentence-level and feature-level to remove subjective reviews and includes slang words and …

Deep Learning Applications In Medical Bioinformatics, Ziad Omar

Electronic Theses and Dissertations

After a patient’s breast cancer diagnosis, identifying breast cancer lymph node metastases is one of the most important and critical factor that is directly related to the patient’s survival. The traditional way to examine the existence of cancer cells in the breast lymph nodes is through a lymph node procedure, biopsy. The procedure process is time-consuming for the patient and the provider, costly, and lacks accuracy as not every lymph node is examined. The intent of this study is to develop an artificial neural network (ANNs) that would map genetic biomarkers to breast lymph node classes using ANNs. The neural …

Reaction Wheels Fault Isolation Onboard 3-Axis Controlled Satellite Using Enhanced Random Forest With Multidomain Features, Mofiyinoluwa Oluwatobi Folami

Electronic Theses and Dissertations

With the increasing number of satellite launches throughout the years, it is only natural that an interest in the safety and monitoring of these systems would increase as well. However, as a system becomes more complex it becomes difficult to generate a high-fidelity model that accurately describes all the system components. With such constraints using data-driven approaches becomes a more feasible option. One of the most commonly used actuators in spacecraft is known as the reaction wheel. If these reaction wheels are not maintained or monitored, it could result in mission failure and unwarranted costs. That is why fault detection …

Meta-Heuristic Approach For Course Scheduling Problem, Amanta Sunny

Electronic Theses and Dissertations

Nowadays, much research is being carried out to find efficient algorithms for optimal automated university course timetable problems (UCTP). UCTP allocates the university's events like lectures, exams to the various resources, including instructors, students, lecture time and classrooms. Class scheduling is one of the biggest challenging problems of educational institutions. In this thesis, the aim is to improve the state-of-art for a class scheduling problem considering some hard and soft constraints. Hard constraints must be satisfied. Soft constraints need not be satisfied, but there is a penalty for each soft constraint violation. We also have a timing penalty for scheduling …

Mining Twitter Sequences Of Product Opinions With Multi-Word Aspect Terms, Vinay Kiran Manjunath

Electronic Theses and Dissertations

Social media platforms have opened doors to users' opinions and perceptions. The text remains the most popular means of contact on social media, despite different means of communication (audio/video and images). Twitter is one such microblogging platform that allows people to express their thoughts within 280 characters per message. The freedom of expression has made it difficult to understand the polarity (Positive, Negative, or Neutral) of the tweets/posts. Given a corpus of microblog texts (e.g., "the new iPhone battery life is good, but camera quality is bad"), mining aspects (e.g., battery life, camera quality) and opinions (e.g., good, bad) of …

Transferability Of Intrusion Detection Systems Using Machine Learning Between Networks, William Peter Mati

Electronic Theses and Dissertations

Intrusion detection systems (IDS) using machine learning is a next generation tool to strengthen the cyber security of networks. Such systems possess the potential to detect zero-day attacks, attacks that are unknown to researchers and are occurring for the first time in history. This thesis tackles novel ideas in this research domain and solves foreseeable issues of a practical deployment of such tool.

The main issue addressed in this thesis are situations where an entity intends to implement an IDS using machine learning onto their network, but do not have attack data available from their own network to train the …

A Framework To Study The Impact Of Interventions On Social Isolation During Pandemics Using Multi-Agent Simulation, Simranpreet Kaur

Electronic Theses and Dissertations

The spread of Coronavirus, widely known as COVID-19, has posed detrimental effects worldwide, affecting almost every primary sector. Due to its asymptomatic behavior and non-early diagnosis, government and health organizations implemented interventions such as physical distancing, lockdown, and quarantine, to mitigate the spread of the virus. Studies have shown that a connection exists between social isolation and health risks experienced by individuals. Thus, this research proposes an agent-based model to address the impact of varying interventions in our society. For simulation purposes, the SEIR model is followed, and agents are categorized into two classes based on their pace of movement, …

An Enhancement To Cnn Approach With Synthesized Image Data For Disease Subtype Classification, Narider Pal Singh

Electronic Theses and Dissertations

The introduction of genetic testing has profoundly enhanced the prospects of early detection of diseases and techniques to suggest precision medicines. The subtyping of critical diseases has proven to be an essential part of the development of individualized therapies and has led to deeper insights into the heterogeneity of the disease. Studies suggest that variants in particular genes have significant effects on certain types of immune system cells and are also involved in the risk of certain critical illnesses like cancer. By analyzing the genetic sequence of a patient, disease types and subtypes can be predicted. Recent research work has …

Experimental Study Of Evolving Communities In Online Social Networks, Pallavi Kaul

Electronic Theses and Dissertations

In the past few decades, the advancement in technology and the internet has leveraged the application of social networks in the world. Millions of people connect through social networks irrespective of their geographical boundaries. These users tend to form communities on common ground, such as similar hobbies, school, work, and much more. Deep level mining and analysis of these communities, connections within these communities, and the connections within the users of these communities divulge abundant data about the underlying features of these complex networks. This thesis focuses on detecting communities at specific times to track the change in memberships. Doing …

Neural Network Based Approach For Detecting Location Spoofing In Vehicular Communication, Smarth Kukreja

Electronic Theses and Dissertations

Vehicular Ad hoc Network (VANET) is an evolving subset of MANET. It's deployed on the roads, where vehicles act as mobile nodes. Active security and Intelligent Transportation System (ITS) are integral applications of VANET, which require stable and uninterrupted vehicle-to-vehicle communication technology. VANET, is a type of wireless network, due to which it is quite prone to security attacks. Extremely dynamic connections, sensitive data sharing and time-sensitivity of this network make it a vulnerable to security attacks. The messages shared between the vehicles are the basic safety message (BSM), these messages are broadcasted by each vehicle in the network to …

Deep Learning Applications In Medical Bioinformatics, Ziad Omar

Electronic Theses and Dissertations

After a patient’s breast cancer diagnosis, identifying breast cancer lymph node metastases is one of the most important and critical factor that is directly related to the patient’s survival. The traditional way to examine the existence of cancer cells in the breast lymph nodes is through a lymph node procedure, biopsy. The procedure process is time-consuming for the patient and the provider, costly, and lacks accuracy as not every lymph node is examined. The intent of this study is to develop an artificial neural network (ANNs) that would map genetic biomarkers to breast lymph node classes using ANNs. The neural …

A Framework To Study The Impact Of Interventions On Social Isolation During Pandemics Using Multi-Agent Simulation, Simranpreet Kaur

Electronic Theses and Dissertations

The spread of Coronavirus, widely known as COVID-19, has posed detrimental effects worldwide, affecting almost every primary sector. Due to its asymptomatic behavior and non-early diagnosis, government and health organizations implemented interventions such as physical distancing, lockdown, and quarantine, to mitigate the spread of the virus. Studies have shown that a connection exists between social isolation and health risks experienced by individuals. Thus, this research proposes an agent-based model to address the impact of varying interventions in our society. For simulation purposes, the SEIR model is followed, and agents are categorized into two classes based on their pace of movement, …

Bridging The Simulation-To-Reality Gap: Adapting Simulation Environment For Object Recognition, Hardik Yogesh Sonetta

Electronic Theses and Dissertations

Rapid advancements in object recognition have created a huge demand for labeled datasets for the task of training, testing, and validation of different techniques. Due to the wide range of applications, object models in the datasets need to cover both variations in geometric features and diverse conditions in which sensory inputs are obtained. Also, the need to manually label the object models is cumbersome. As a result, it becomes difficult for researchers to gain access to adequate datasets for the development of new methods or algorithms. In comparison, computer simulation has been considered a cost-effective solution to generate simulated data …