Computer Engineering Commons^™

Promise And Limitations Of Supervised Optimal Transport-Based Graph Summarization Via Information Theoretic Measures, Sepideh Neshatfar

Electronic Theses and Dissertations

Graph summarization is a fundamental problem in the field of data analysis, aiming to distill extensive graph datasets into more manageable, yet informative representations. The challenge lies in creating compressed graphs that faithfully retain crucial structural information for downstream tasks. A recent advancement in this domain introduces an optimal transport-based framework that enables the incorporation of a priori knowledge regarding the importance of nodes, edges, and attributes during the graph summarization process. However, the statistical properties of this innovative framework remain largely unexplored. This master's thesis embarks on a comprehensive exploration of the field of graph summarization, with a particular …

Controllable Language Generation Using Deep Learning, Rohola Zandie

Electronic Theses and Dissertations

The advent of deep neural networks has sparked a revolution in Artificial Intelligence (AI), notably with the creation of Transformer models like GPT-X and ChatGPT. These models have surpassed previous methods in various Natural Language Processing (NLP) tasks. As the NLP field evolves, there is a need to further understand and question the capabilities of these models. Text generation, a crucial part of NLP, remains an area where our comprehension is limited while being critical in research.

This dissertation focuses on the challenging problem of controlling the general behaviors of language models such as sentiment, topical focus, and logical reasoning. …

A Data-Driven Multi-Regime Approach For Predicting Real-Time Energy Consumption Of Industrial Machines., Abdulgani Kahraman

Electronic Theses and Dissertations

This thesis focuses on methods for improving energy consumption prediction performance in complex industrial machines. Working with real-world industrial machines brings several challenges, including data access, algorithmic bias, data privacy, and the interpretation of machine learning algorithms. To effectively manage energy consumption in the industrial sector, it is essential to develop a framework that enhances prediction performance, reduces energy costs, and mitigates air pollution in heavy industrial machine operations. This study aims to assist managers in making informed decisions and driving the transition towards green manufacturing. The energy consumption of industrial machinery is substantial, and the recent increase in CO2 …

Guided Data Augmentation For Improved Semi-Supervised Image Classification In Low Data Regime., Fadoua Khmaissia

Electronic Theses and Dissertations

Deep learning models have achieved state of the art performances, especially for computer vision applications. Much of the recent successes can be attributed to the existence of large, high quality, labeled datasets. However, in many real-world applications, collecting similar datasets is often cumbersome and time consuming. For instance, developing robust automatic target recognition models from infrared images still faces major challenges. This is mainly due to the difficulty of acquiring high resolution inputs, sensitivity to the thermal sensors' calibration, meteorological conditions, targets' scale and viewpoint invariance. Ideally, a good training set should contain enough variations within each class for the …

Dynamic Scene Understanding: Pedestrian Tracking From Aerial Devices., Abdelhamid Bouzid

Electronic Theses and Dissertations

Multiple Object Tracking (MOT) is the problem that involves following the trajectory of multiple objects in a sequence, generally a video. Pedestrians are among the most interesting subjects to track and recognize for many purposes such as surveillance, and safety. In the recent years, Unmanned Aerial Vehicles (UAV’s) have been viewed as a viable option for monitoring public areas, as they provide a low-cost method of data collection while covering large and difficult-to-reach areas. In this thesis, we present an online pedestrian tracking and re-identification from aerial devices framework. This framework is based on learning a compact directional statistic distribution …

Reference Frames In Human Sensory, Motor, And Cognitive Processing, Dongcheng He

Electronic Theses and Dissertations

Reference-frames, or coordinate systems, are used to express properties and relationships of objects in the environment. While the use of reference-frames is well understood in physical sciences, how the brain uses reference-frames remains a fundamental question. The goal of this dissertation is to reach a better understanding of reference-frames in human perceptual, motor, and cognitive processing. In the first project, we study reference-frames in perception and develop a model to explain the transition from egocentric (based on the observer) to exocentric (based outside the observer) reference-frames to account for the perception of relative motion. In a second project, we focus …

Iot In Smart Communities, Technologies And Applications., Muhammad Zaigham Abbas Shah Syed

Electronic Theses and Dissertations

Internet of Things is a system that integrates different devices and technologies, removing the necessity of human intervention. This enables the capacity of having smart (or smarter) cities around the world. By hosting different technologies and allowing interactions between them, the internet of things has spearheaded the development of smart city systems for sustainable living, increased comfort and productivity for citizens. The Internet of Things (IoT) for Smart Cities has many different domains and draws upon various underlying systems for its operation, in this work, we provide a holistic coverage of the Internet of Things in Smart Cities by discussing …

Lung Nodules Identification In Ct Scans Using Multiple Instance Learning., Wiem Safta

Electronic Theses and Dissertations

Computer Aided Diagnosis (CAD) systems for lung nodules diagnosis aim to classify nodules into benign or malignant based on images obtained from diverse imaging modalities such as Computer Tomography (CT). Automated CAD systems are important in medical domain applications as they assist radiologists in the time-consuming and labor-intensive diagnosis process. However, most available methods require a large collection of nodules that are segmented and annotated by radiologists. This process is labor-intensive and hard to scale to very large datasets. More recently, some CAD systems that are based on deep learning have emerged. These algorithms do not require the nodules to …

Cosine-Based Explainable Matrix Factorization For Collaborative Filtering Recommendation., Pegah Sagheb Haghighi

Electronic Theses and Dissertations

Recent years saw an explosive growth in the amount of digital information and the number of users who interact with this information through various platforms, ranging from web services to mobile applications and smart devices. This increase in information and users has naturally led to information overload which inherently limits the capacity of users to discover and find their needs among the staggering array of options available at any given time, the majority of which they may never become aware of. Online services have handled this information overload by using algorithmic filtering tools that can suggest relevant and personalized information …

Flight Trajectory Prediction For Aeronautical Communications., Nathan T Schimpf

Electronic Theses and Dissertations

The development of future technologies for the National Airspace System (NAS) will be reliant on a new communications infrastructure capable of managing a limited spectrum among aircraft and ground systems. Emerging approaches to this spectrum allocation task mostly consider machine learning techniques reliant on aircraft and Air Traffic Control (ATC) sector data. Much of this data, however, is not directly available. This thesis considers the development of two such data products: the 4D trajectory (latitude, longitude, altitude, and time) of aircraft, and the anticipated airspace utilization and communication demand within an ATC sector. Data predictions are treated as a time …

Multi-Style Explainable Matrix Factorization Techniques For Recommender Systems., Olurotimi Nugbepo Seton

Electronic Theses and Dissertations

Black-box recommender system models are machine learning models that generate personalized recommendations without explaining how the recommendations were generated to the user or giving them a way to correct wrong assumptions made about them by the model. However, compared to white-box models, which are transparent and scrutable, black-box models are generally more accurate. Recent research has shown that accuracy alone is not sufficient for user satisfaction. One such black-box model is Matrix Factorization, a State of the Art recommendation technique that is widely used due to its ability to deal with sparse data sets and to produce accurate recommendations. Recent …

Imparting 3d Representations To Artificial Intelligence For A Full Assessment Of Pressure Injuries., Sofia Zahia

Electronic Theses and Dissertations

During recent decades, researches have shown great interest to machine learning techniques in order to extract meaningful information from the large amount of data being collected each day. Especially in the medical field, images play a significant role in the detection of several health issues. Hence, medical image analysis remarkably participates in the diagnosis process and it is considered a suitable environment to interact with the technology of intelligent systems. Deep Learning (DL) has recently captured the interest of researchers as it has proven to be efficient in detecting underlying features in the data and outperformed the classical machine learning …

Automatic Target Recognition With Convolutional Neural Networks., Nada Baili

Electronic Theses and Dissertations

Automatic Target Recognition (ATR) characterizes the ability for an algorithm or device to identify targets or other objects based on data obtained from sensors, being commonly thermal. ATR is an important technology for both civilian and military computer vision applications. However, the current level of performance that is available is largely deficient compared to the requirements. This is mainly due to the difficulty of acquiring targets in realistic environments, and also to limitations of the distribution of classified data to the academic community for research purposes. This thesis proposes to solve the ATR task using Convolutional Neural Networks (CNN). We …

Computational Techniques In Medical Image Analysis Application For White Blood Cells Classification., Omar Dekhil

Electronic Theses and Dissertations

White blood cells play important rule in the human body immunity and any change in their count may cause serious diseases. In this study, a system is introduced for white blood cells localization and classification. The dataset used in this study is formed by two components, the first is the annotation dataset that will be used in the localization (364 images), and the second is labeled classes that will be used in the classification (12,444 images). For the localization, two approaches will be discussed, a classical approach and a deep learning based approach. For the classification, 5 different deep learning …

Instructor Activity Recognition Using Smartwatch And Smartphone Sensors, Zayed Uddin Chowdhury

Electronic Theses and Dissertations

During a classroom session, an instructor performs several activities, such as writing on the board, speaking to the students, gestures to explain a concept. A record of the time spent in each of these activities could be valuable information for the instructors to virtually observe their own style of instruction. It can help in identifying activities that engage the students more, thereby enhancing teaching effectiveness and efficiency. In this work, we present a preliminary study on profiling multiple activities of an instructor in the classroom using smartwatch and smartphone sensor data. We use 2 benchmark datasets to test out the …

Applying Artificial Intelligence To Medical Data, Shaikh Shiam Rahman

Electronic Theses and Dissertations

Machine learning, data mining, and deep learning has become the methodology of choice for analyzing medical data and images. In this study, we implemented three different machine learning techniques to medical data and image analysis. Our first study was to implement different log base entropy for a decision tree algorithm. Our results suggested that using a higher log base for the dataset with mostly categorical attributes with three or more categories for each attribute can obtain a higher accuracy. For the second study, we analyzed mental health data tuning the parameters of the decision tree (splitting method, depth and entropy). …

Formally Designing And Implementing Cyber Security Mechanisms In Industrial Control Networks., Mehdi Sabraoui

Electronic Theses and Dissertations

This dissertation describes progress in the state-of-the-art for developing and deploying formally verified cyber security devices in industrial control networks. It begins by detailing the unique struggles that are faced in industrial control networks and why concepts and technologies developed for securing traditional networks might not be appropriate. It uses these unique struggles and examples of contemporary cyber-attacks targeting control systems to argue that progress in securing control systems is best met with formal verification of systems, their specifications, and their security properties. This dissertation then presents a development process and identifies two technologies, TLA+ and seL4, that can be …

An Explainable Recommender System Based On Semantically-Aware Matrix Factorization., Mohammed Sanad Alshammari

Electronic Theses and Dissertations

Collaborative Filtering techniques provide the ability to handle big and sparse data to predict the ratings for unseen items with high accuracy. Matrix factorization is an accurate collaborative filtering method used to predict user preferences. However, it is a black box system that recommends items to users without being able to explain why. This is due to the type of information these systems use to build models. Although rich in information, user ratings do not adequately satisfy the need for explanation in certain domains. White box systems, in contrast, can, by nature, easily generate explanations. However, their predictions are less …

Eaglebot: A Chatbot Based Multi-Tier Question Answering System For Retrieving Answers From Heterogeneous Sources Using Bert, Muhammad Rana

Electronic Theses and Dissertations

This paper proposes to tackle Question Answering on a specific domain by developing a multi-tier system using three different types of data storage for storing answers. For testing our system on University domain we have used extracted data from Georgia Southern University website. For the task of faster retrieval we have divided our answer data sources into three distinct types and utilized Dialogflow's Natural Language Understanding engine for route selection. We compared different word and sentence embedding techniques for making a semantic question search engine and BERT sentence embedding gave us the best result and for extracting answer from a …

Building A Classification Model Using Affinity Propagation, Christopher R. Klecker

Electronic Theses and Dissertations

Regular classification of data includes a training set and test set. For example for Naïve Bayes, Artificial Neural Networks, and Support Vector Machines, each classifier employs the whole training set to train itself. This thesis will explore the possibility of using a condensed form of the training set in order to get a comparable classification accuracy. The technique explored in this thesis will use a clustering algorithm to explore with data records can be labeled as exemplar, or a quality of multiple records. For example, is it possible to compress say 50 records into one single record? Can a single …

Modeling And Simulation Methodologies For Spinal Cord Stimulation., Saliya Kumara Kirigeeganage

Electronic Theses and Dissertations

The use of neural prostheses to improve health of paraplegics has been a prime interest of neuroscientists over the last few decades. Scientists have performed experiments with spinal cord stimulation (SCS) to enable voluntary motor function of paralyzed patients. However, the experimentation on the human spinal cord is not a trivial task. Therefore, modeling and simulation techniques play a significant role in understanding the underlying concepts and mechanics of the spinal cord stimulation. In this work, simulation and modeling techniques related to spinal cord stimulation were investigated. The initial work was intended to visualize the electric field distribution patterns in …

A Transfer Learning Approach For Sentiment Classification., Omar Abdelwahab

Electronic Theses and Dissertations

The idea of developing machine learning systems or Artificial Intelligence agents that would learn from different tasks and be able to accumulate that knowledge with time so that it functions successfully on a new task that it has not seen before is an idea and a research area that is still being explored. In this work, we will lay out an algorithm that allows a machine learning system or an AI agent to learn from k different domains then uses some or no data from the new task for the system to perform strongly on that new task. In order …

Spam Elimination And Bias Correction : Ensuring Label Quality In Crowdsourced Tasks., Lingyu Lyu

Electronic Theses and Dissertations

Crowdsourcing is proposed as a powerful mechanism for accomplishing large scale tasks via anonymous workers online. It has been demonstrated as an effective and important approach for collecting labeled data in application domains which require human intelligence, such as image labeling, video annotation, natural language processing, etc. Despite the promises, one big challenge still exists in crowdsourcing systems: the difficulty of controlling the quality of crowds. The workers usually have diverse education levels, personal preferences, and motivations, leading to unknown work performance while completing a crowdsourced task. Among them, some are reliable, and some might provide noisy feedback. It is …

Maintainability Analysis Of Mining Trucks With Data Analytics., Abdulgani Kahraman

Electronic Theses and Dissertations

The mining industry is one of the biggest industries in need of a large budget, and current changes in global economic challenges force the industry to reduce its production expenses. One of the biggest expenditures is maintenance. Thanks to the data mining techniques, available historical records of machines’ alarms and signals might be used to predict machine failures. This is crucial because repairing machines after failures is not as efficient as utilizing predictive maintenance. In this case study, the reasons for failures seem to be related to the order of signals or alarms, called events, which come from trucks. The …

Detailed Power Measurement With Arm Embedded Boards, Yanxiang Mao

Electronic Theses and Dissertations

Power and energy are becoming important considerations in today's electronic equipment. The amount of power required to run a supercomputer for an hour could supply an ordinary household for many months. The need for low-power computing also extends to smaller devices, such as mobile phones, laptops and embedded devices.

In order to optimize power usage of electronic equipment, we need to collect information on the power consumption of these devices. Unfortunately it is not easy to do this on modern computing systems. Existing measuring equipment is often expensive, inaccurate, and difficult to operate. The main goal of this project is …

Integrated Environment And Proximity Sensing For Uav Applications, Shawn S. Brackett

Electronic Theses and Dissertations

As Unmanned Aerial Vehicle (UAV), or “drone” applications expand, new methods for sensing, navigating and avoiding obstacles need to be developed. The project applies an Extended Kalman Filter (EKF) to a simulated quadcopter vehicle though Matlab in order to estimate not only the vehicle state but the world state around the vehicle. The EKF integrates multiple sensor readings from range sensors, IMU sensors, and radiation sensors and combines this information to optimize state estimates. The result is an estimated world map to be used in vehicle navigation and obstacle avoidance.

The simulation handles the physics behind the vehicle flight. As …

Dynamic Adversarial Mining - Effectively Applying Machine Learning In Adversarial Non-Stationary Environments., Tegjyot Singh Sethi

Electronic Theses and Dissertations

While understanding of machine learning and data mining is still in its budding stages, the engineering applications of the same has found immense acceptance and success. Cybersecurity applications such as intrusion detection systems, spam filtering, and CAPTCHA authentication, have all begun adopting machine learning as a viable technique to deal with large scale adversarial activity. However, the naive usage of machine learning in an adversarial setting is prone to reverse engineering and evasion attacks, as most of these techniques were designed primarily for a static setting. The security domain is a dynamic landscape, with an ongoing never ending arms race …

Uncovering Exceptional Predictions Using Exploratory Analysis Of Second Stage Machine Learning., Aneseh Alvanpour

Electronic Theses and Dissertations

Nowadays, algorithmic systems for making decisions are widely used to facilitate decisions in a variety of fields such as medicine, banking, applying for universities or network security. However, many machine learning algorithms are well-known for their complex mathematical internal workings which turn them into black boxes and makes their decision-making process usually difficult to understand even for experts. In this thesis, we try to develop a methodology to explain why a certain exceptional machine learned decision was made incorrectly by using the interpretability of the decision tree classifier. Our approach can provide insights about potential flaws in feature definition or …

Data Driven Discovery Of Materials Properties., Fadoua Khmaissia

Electronic Theses and Dissertations

The high pace of nowadays industrial evolution is creating an urgent need to design new cost efficient materials that can satisfy both current and future demands. However, with the increase of structural and functional complexity of materials, the ability to rationally design new materials with a precise set of properties has become increasingly challenging. This basic observation has triggered the idea of applying machine learning techniques in the field, which was further encouraged by the launch of the Materials Genome Initiative (MGI) by the US government since 2011. In this work, we present a novel approach to apply machine learning …

Determining Unique Agents By Evaluating Web Form Interaction, Ben Cooley

Electronic Theses and Dissertations

Because of the inherent risks in today’s online activities, it becomes imperative to identify a malicious user masquerading as someone else. Incorporating biometric analysis enhances the confidence of authenticating valid users over the Internet while providing additional layers of security with no hindrance to the end user. Through the analysis of traffic patterns and HTTP Header analysis, the detection and early refusal of robot agents plays a great role in reducing fraudulent login attempts.