Computer Sciences Commons^™

Privacy-Enhanced And Outsourced Power Usage Control In Smart Grids, Hemadri Patel

Theses, Dissertations and Culminating Projects

Due to the numerous advantages of smart grids like reliability, availability, and efficiency, it has been emerging as an extraordinary contribution to the economic and environmental health. This project mainly focuses on the power outage issue in a smart grid environment. Power outages occur when electricity demand exceeds the supply, more specifically, consider a utility company which sets a threshold on the total power usage of households from a neighborhood. Whenever the total power usage from a neighborhood exceeds the threshold, some of the households needs to reduce their energy consumption; to avoid the power outage. This problem is referred …

Integrating The Spatial Pyramid Pooling Into 3d Convolutional Neural Networks For Cerebral Microbleeds Detection, Andre Accioly Veira

CCAC Theses and Dissertations

Cerebral microbleeds (CMB) are small foci of chronic blood products in brain tissues that are critical markers for cerebral amyloid angiopathy. CMB increases the risk of symptomatic intracerebral hemorrhage and ischemic stroke. CMB can also cause structural damage to brain tissues resulting in neurologic dysfunction, cognitive impairment, and dementia. Due to the paramagnetic properties of blood degradation products, CMB can be better visualized via susceptibility-weighted imaging (SWI) than magnetic resonance imaging (MRI).CMB identification and classification have been based mainly on human visual identification of SWI features via shape, size, and intensity information. However, manual interpretation can be biased. Visual screening …

Sequential User Modeling And Recommendation Under Partially Observable Environment, Chunpai Wang

Legacy Theses & Dissertations (2009 - 2024)

A tremendous amount of user data is collected daily due to technological progress that enables us to understand users better. The availability of this data also advances machine learning-based technologies, which aim to learn generic global patterns of user behavior from large volumes of data. User modeling is the process of building user profiles and finding the inherent representation of the user. Precise user modeling is critical for predicting users' future behavior and providing personalized services or products to individuals. Many machine learning models have been explored for user modeling to meet the increasing demand for user-centric technologies. Machine learning …

Learning From Hierarchical And Noisy Labels, Wenting Qi

Legacy Theses & Dissertations (2009 - 2024)

One branch of machine learning algorithms is supervised learning, where the label is crucial for the learning model. Numerous algorithms have been proposed for supervised learning with different classification tasks. However, fewer works question the quality of the training labels. Training a learning model with noisy labels leads to decreased or untruthful performance. On the other hand, hierarchical multi-label classification (HMC) is one of the most challenging problems in machine learning because the classes in HMC tasks are hierarchically structured, and data instances are associated with multiple labels residing in a path of the hierarchy. Treating hierarchical tasks as flat …

Utilizing Machine Learning In Healthcare In An Ethical Fashion, Nishka Ayyar

CMC Senior Theses

This thesis paper explores the ethical considerations surrounding the use of machine learning (ML) solutions in healthcare. The background section discusses the basics of machine learning techniques and algorithms, and the increasing interest in their utilization in the healthcare sector. The paper then reviews and critically analyzes four studies that highlight concerns related to using ML in healthcare, including issues of bias, privacy, accountability, and transparency. Based on the analysis of these studies, the paper presents several recommendations for addressing these concerns. The paper concludes with a discussion on the potential benefits of using machine learning technology in healthcare. Ultimately, …

Credit Worthiness Tool For Credit Unions, Rylee Christoffersen, Mario Ramalho

ICT

The core objectives for the Capstone project were to mine data in order to create a tool for Credit Unions (and banks) that will evaluate customers credit worthiness based on an ethical standardised criteria that is transparent to all. We explored why this was necessary and explored how important it could be to the business. Our focus is on helping Credit Unions have a stronger online presence as the banking sector has been changing rapidly and moving online and Credit Unions are currently behind in the market in this regard .This tool would help automate the credit approval process, reducing …

Facial Recognition Using Neural Network, Georges Diego Hawile Pinheiro, Allison Alves De Moura

ICT

Face recognition technology using machine learning and neural networks has become increasingly prevalent in recent years, revolutionizing various fields such as security, law enforcement, and marketing. The development of an AI-based system that can perform face recognition using these technologies has become a significant focus for researchers and developers worldwide. This project aims to create such a system that can recognize and classify faces accurately using machine learning algorithms and neural networks. By leveraging these advanced technologies, the system can learn and improve over time, leading to higher accuracy rates and enhanced performance.

Menu Recommendation System Using Machine Learning, Kelly Crystine Ferreira Jesus, Leo Jaime Kayser Macieski

ICT

Developing a recommendation menu system for restaurants based on the restaurant data and/or city food purchase data to help and change the way restaurants build their menu. Using Data Analysis and Machine Learning to build a project that aims to solve the problem of restaurants and chefs when it comes to preparing menus, the latter with ingredients and dishes that encourage their customers to order more, come back and recommend the restaurant. Helping chefs to create dishes for their restaurants with more accuracy and higher probability to be ordered by their customers. The project will cover tools to build the …

Predicting The Effects Of Climate Change On Irish Agriculture, Rodrigo Matsumoto, Sarah Kuprian Carrinho

ICT

The impact of climate change on agriculture is a growing concern worldwide, and Ireland is no exception. The purpose of this project is to use machine learning techniques to predict the effects of climate change on Irish agriculture and identify strategies for adaptation and mitigation. The project uses the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology to guide the data analysis process, MoSCoW prioritization to identify the most critical needs, and SWOT analysis to evaluate the strengths, weaknesses, opportunities, and threats our project may encounter. Historical temperature data for Ireland and Dublin will be used as our data sources. …

Covert Computation In The Abstract Tile-Assembly Model, Robert M. Alaniz, Timothy Gomez, Andrew Rodriguez, Tim Wylie, David Caballero, Elize Grizzell, Robert Schweller

Computer Science Faculty Publications

There have been many advances in molecular computation that offer benefits such as targeted drug delivery, nanoscale mapping, and improved classification of nanoscale organisms. This power led to recent work exploring privacy in the computation, specifically, covert computation in self-assembling circuits. Here, we prove several important results related to the concept of a hidden computation in the most well-known model of self-assembly, the Abstract Tile-Assembly Model (aTAM). We show that in 2D, surprisingly, the model is capable of covert computation, but only with an exponentialsized assembly. We also show that the model is capable of covert computation with polynomial-sized assemblies …

Adaptive Multiple Distributed Bidirectional Spiral Path Planning For Foraging Robot Swarms, Qi Lu, Ryan Luna

Computer Science Faculty Publications

The Distributed Deterministic Spiral Algorithm (DDSA) has shown great foraging efficiency in robot swarms. However, when the number of robots in the swarm increases, scalability becomes a significant bottleneck due to increased collisions among robots, making it challenging to deploy them in the search space (e.g., 20 robots). To address this issue, we propose an adaptive Multiple-Distributed Bidirectional Spiral Algorithm (MDBSA) that enhances scalability. Our proposed algorithm partitions the squared search arena into multiple identical squared regions and assigns robots to regions dynamically based on the number of regions. In each region, a bidirectional spiral search path is planned, and …

The Relationship Between Organizational Knowledge Management Constructs And Organizational Flexibility, Marcus B. Williams

Walden Dissertations and Doctoral Studies

The role that the information technology (IT) department serves is governed by the corporate culture and how it values the use of knowledge, including IT, to achieve a strategic competitive advantage. The purpose of this quantitative study was to examine the potential relationships between information acquisition, knowledge dissemination, shared interpretation, organizational memory, and organizational flexibility. Two theories served as the theoretical foundation for this study: contingency theory and the resource-based view of the firm. To answer the question of possible correlation between organizational flexibility and components of knowledge management, a randomly selected sample of 193 IT professionals employed at small- …

A Sociotechnical Systems View Of Computer Self-Efficacy And Usability Determinants Of Technical Readiness, Stefani L. Tucker

Walden Dissertations and Doctoral Studies

The specific research problem was that it is unknown whether computer self-efficacy and usability determine technical readiness in hourly and exempt information technology support employees in the United States. The purpose of this correlational study was to examine the relationship between computer self-efficacy and technical readiness, usability and technical readiness, and computer self-efficacy, usability, and technical readiness in hourly and exempt information technology support employees in the United States. Sociotechnical system theory suggests that every transaction has a human and technical aspect; thus, the theoretical framework. The convenience sample included 136 information technology support employees aged 18-70. The regression results …

Mining Health Informatics Job Advertisements: Insights For Higher Education Programs And Job Seekers, Ahmed El Noshokaty, Mohammad A. Al-Ramahi, Omar El-Gayar, Abdullah Wahbeh, Tareq Nasralah

Computer Information Systems Faculty Publications (Archived)

This paper used web scraping and data mining to analyze 831 health informatics job advertisements on indeed.com. Results showed that 87% of jobs explicitly required a college degree in a related field, 41% of jobs preferred a graduate degree, while 29% preferred or required professional certification. The analysis showed that preferred skills were analytics problem solving, communication skills, oral communication, interpersonal skills, project management, statistics, and critical thinking. The analysis also showed that college degrees, certifications, and the above-mentioned skill set are in high demand for working in the field of health informatics, especially in states with large populations and …

Conversational Agents For Mental Health And Well-Being: Discovering Design Recommendations Using Text Mining, Abdullah Wahbeh, Mohammad A. Al-Ramahi, Omar El-Gayar, Ahmed El Noshokaty, Tareq Nasralah

Computer Information Systems Faculty Publications (Archived)

Conversational agents are increasingly being used by the general population due to shortages in healthcare providers and specialists, and limited access to treatments. They are also used by people to deal with loneliness and lack of companionship. As these apps are increasingly replacing real humans, there is a need to explore their design features and limitations for better design of conversational apps. Using text mining and topic modeling, this study analyzed a total of 126,610 reviews about Replika, a popular and well-established conversational agent mobile app. Our results emphasized current practices for designing conversational apps while at the same time …

Rage Against The Machine: Who Is Responsible For Regulating Generative Artificial Intelligence In Domestic And Cross-Border Litigation?, S. I. Strong

Faculty Articles

In 2023, ChatGPT—an early form of generative artificial intelligence (AI) capable of creating entirely new content—took the world by storm. The first shock came when ChatGPT demonstrated its ability to pass the U.S. bar exam. Soon thereafter, the world learned that ChatGPT was being used by both lawyers and judges in actual litigation.

Some within the legal community find the use of generative AI in civil and criminal litigation entirely unproblematic. Others find generative AI troubling as a matter of due process and procedural fairness due to its propensity not only to misinterpret legitimate legal authorities but to create fictitious …

Real-Time Polyp Analysis On Endoscopic Images Using Deep Learning Approach: Detection, Characterization And Size Estimation, Phanukorn Sunthornwetchapong

Chulalongkorn University Theses and Dissertations (Chula ETD)

As medical devices advance, doctors adopt endoscopes to perform endoscopes for gastrointestinal disease screenings. For colonoscopy, skills such as polyp detection, polyp characterisation, and polyp size estimation needed to be practised while screening patients. This work aims to develop a deep learning model for performing polyp detection, characterisation, and size estimation to assist fellow doctors in these tasks. To maximise usability in assisting fellow doctors, the model must be able to perform in a real-time fashion. The work utilises existing object detection models for performing size estimation tasks. With the problems of data imbalances, we use depth information but without …

Deep Reinforcement Learning For Electricity Energy Trading On Non-Sharing Information Scenario, Nat Uthayansuthi

Chulalongkorn University Theses and Dissertations (Chula ETD)

In this research, we explore an optimized model for peer-to-peer (P2P) energy trading within microgrids that addresses the gap in previous research, which often assumed mandatory sharing of private information among prosumers. Our model-based multi-agent deep reinforcement learning framework includes several key components: an LSTM for the policy model, ; the Temporal Fusion Transformer (TFT) for predicting 24h-ahead net load consumption, adept at handling multivariate time series data; the inclusion of the Global Horizontal Index (GHI) to account for solar irradiance to the model; and a clustering technique to segment the dataset of 300 households from the Ausgrid dataset in …

A Review Of Piezoelectric Footwear Energy Harvesters: Principles, Methods, And Applications, Bingqi Zhao, Feng Qian, Alexander Hatfield, Lei Zuo, Tian-Bing Xu

Mechanical & Aerospace Engineering Faculty Publications

Over the last couple of decades, numerous piezoelectric footwear energy harvesters (PFEHs) have been reported in the literature. This paper reviews the principles, methods, and applications of PFEH technologies. First, the popular piezoelectric materials used and their properties for PEEHs are summarized. Then, the force interaction with the ground and dynamic energy distribution on the footprint as well as accelerations are analyzed and summarized to provide the baseline, constraints, potential, and limitations for PFEH design. Furthermore, the energy flow from human walking to the usable energy by the PFEHs and the methods to improve the energy conversion efficiency are presented. …

Go Green With Ecosia: The Search Engine With A Sustainable Business Model, James Thibeault

Library Publications

Ecosia, a non-profit search engine, is not only a thriving business but is also directly responsible for planting over 185 million trees. Focusing on sustainability and social responsibility, Ecosia demonstrates how business models can positively impact the environment.

Decoherence And Preferred Tensor Product Structures For Systems Of Qubits, Marissa M. Singh

Pitzer Senior Theses

In recent decades, the program of Decoherence has helped clarify how features of the classical world emerge from Quantum Mechanics. According to Decoherence, the interaction between a system and its environment dynamically selects certain system states — the pointer states — that exhibit predictable, classical behavior while their superpositions rapidly decohere. However, most Decoherence studies to date pre-suppose a preferred division of the world into “system” and “environment”, corresponding to a preferred choice of Tensor Product Structure (TPS) on the Hilbert Space of states. A few previous works have suggested that the existence of a well-defined pointer observable may be …

The Effects Of Head-Centric Rest Frames On Egocentric Distance Perception In Virtual Reality, Yahya Hmaiti

Honors Undergraduate Theses

It has been shown through several research investigations that users tend to underestimate distances in virtual reality (VR). Virtual objects that appear close to users wearing a Head-mounted display (HMD) might be located at a farther distance in reality. This discrepancy between the actual distance and the distance observed by users in VR was found to hinder users from benefiting from the full in-VR immersive experience, and several efforts have been directed toward finding the causes and developing tools that mitigate this phenomenon. One hypothesis that stands out in the field of spatial perception is the rest frame hypothesis (RFH), …

Understanding, Modeling, And Simulating The Discrepancy Between Intended And Perceived Image Appearance On Optical See-Through Augmented Reality Displays, Austin Erickson

Electronic Theses and Dissertations, 2020-2023

Augmented reality (AR) displays are transitioning from being primarily used in research and development settings, to being used by the general public. With this transition, these displays will be used by more people, in many different environments, and in many different contexts. Like other displays, the user's perception of virtual imagery is influenced by the characteristics of the user's environment, creating a discrepancy between the intended appearance and the perceived appearance of virtual imagery shown on the display. However, this problem is much more apparent for optical see-through AR displays, such as the HoloLens. For these displays, imagery is superimposed …

Improved Intelligent Ledger Construction For Realistic Iot Blockchain Networks, Charles Rawlins, S. (Sarangapani) Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

Scalability is essential for next generation blockchain technology to integrate with large mobile networks like Internet of Things (IoT). The IOTA distributed ledger protocol has combined transaction generation and verification to address this, but at the expense of increased reliance on connectivity to resolve conflicts with a novel ledger data structure. Intelligent Ledger Construction (ILC) was proposed as an auditable lightweight reinforcement-learning scheme to address this constraint with proposal of local conflict resolution with machine-learning classification. This effort presents an improved reliability reward model to enhance training for ILC and further reduce adversarial gaming and resource usage. Testing this revision …

Continual Optimal Adaptive Tracking Of Uncertain Nonlinear Continuous-Time Systems Using Multilayer Neural Networks, Irfan Ganie, S. (Sarangapani) Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This study provides a lifelong integral reinforcement learning (LIRL)-based optimal tracking scheme for uncertain nonlinear continuous-time (CT) systems using multilayer neural network (MNN). In this LIRL framework, the optimal control policies are generated by using both the critic neural network (NN) weights and single-layer NN identifier. The critic MNN weight tuning is accomplished using an improved singular value decomposition (SVD) of its activation function gradient. The NN identifier, on the other hand, provides the control coefficient matrix for computing the control policies. An online weight velocity attenuation (WVA)-based consolidation scheme is proposed wherein the significance of weights is derived by …

Personalizing Student Graduation Paths Using Expressed Student Interests, Nicolas Dobbins, Ali R. Hurson, Sahra Sedigh

Electrical and Computer Engineering Faculty Research & Creative Works

This paper proposes an intelligent recommendation approach to facilitate personalized education and help students in planning their path to graduation. The goal is to identify a path that aligns with a student's interests and career goals and approaches optimality with respect to one or more criteria, such as time-to-graduation or credit hours taken. The approach is illustrated and verified through application to undergraduate curricula at the Missouri University of Science and Technology.

Optimal Adaptive Tracking Control Of Partially Uncertain Nonlinear Discrete-Time Systems Using Lifelong Hybrid Learning, Behzad Farzanegan, Rohollah Moghadam, Sarangapani Jagannathan, Pappa Natarajan

Electrical and Computer Engineering Faculty Research & Creative Works

This article addresses a multilayer neural network (MNN)-based optimal adaptive tracking of partially uncertain nonlinear discrete-time (DT) systems in affine form. By employing an actor–critic neural network (NN) to approximate the value function and optimal control policy, the critic NN is updated via a novel hybrid learning scheme, where its weights are adjusted once at a sampling instant and also in a finite iterative manner within the instants to enhance the convergence rate. Moreover, to deal with the persistency of excitation (PE) condition, a replay buffer is incorporated into the critic update law through concurrent learning. To address the vanishing …

Rafid: A Lightweight Approach To Radio Frequency Interference Detection In Time Domain Using Lstm And Statistical Analysis, Luke A. Smith, Vishesh Kumar Tanwar, Maciej Jan Zawodniok, Sanjay Kumar Madria

Electrical and Computer Engineering Faculty Research & Creative Works

Recently, the utilization of Radio Frequency (RF) devices has increased exponentially over numerous vertical platforms. This rise has led to an abundance of Radio Frequency Interference (RFI) continues to plague RF systems today. The continued crowding of the RF spectrum makes RFI efficient and lightweight mitigation critical. Detecting and localizing the interfering signals is the foremost step for mitigating RFI concerns. Addressing these challenges, we propose a novel and lightweight approach, namely RaFID, to detect and locate the RFI by incorporating deep neural networks (DNNs) and statistical analysis via batch-wise mean aggregation and standard deviation (SD) calculations. RaFID investigates the …

Lifelong Deep Learning-Based Control Of Robot Manipulators, Irfan Ganie, Jagannathan Sarangapani

Electrical and Computer Engineering Faculty Research & Creative Works

This study proposes a lifelong deep learning control scheme for robotic manipulators with bounded disturbances. This scheme involves the use of an online tunable deep neural network (DNN) to approximate the unknown nonlinear dynamics of the robot. The control scheme is developed by using a singular value decomposition-based direct tracking error-driven approach, which is utilized to derive the weight update laws for the DNN. To avoid catastrophic forgetting in multi-task scenarios and to ensure lifelong learning (LL), a novel online LL scheme based on elastic weight consolidation is included in the DNN weight-tuning laws. Our results demonstrate that the resulting …

Lifelong Learning Control Of Nonlinear Systems With Constraints Using Multilayer Neural Networks With Application To Mobile Robot Tracking, Irfan Ganie, S. (Sarangapani) Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This Paper Presents a Novel Lifelong Multilayer Neural Network (MNN) Tracking Approach for an Uncertain Nonlinear Continuous-Time Strict Feedback System that is Subject to Time-Varying State Constraints. the Proposed Method Uses a Time-Varying Barrier Function to Accommodate the Constraints Leading to the Development of an Efficient Control Scheme. the Unknown Dynamics Are Approximated using a MNN, with Weights Tuned using a Singular Value Decomposition (SVD)-Based Technique. an Online Lifelong Learning (LL) based Elastic Weight Consolidation (EWC) Scheme is Also Incorporated to Alleviate the Issue of Catastrophic Forgetting. the Stability of the overall Closed-Loop System is Analyzed using Lyapunov Analysis. the …