Computer Engineering Commons^™

Modeling Multiple Tasks In Recommendation Systems, Dinh Hieu Do

Dissertations and Theses Collection (Open Access)

Traditional research in recommendation systems has largely centered on the static offline supervised learning setting. In this paradigm, all available user-item interaction data is collected and partitioned into fixed training, validation, and test sets. Models are developed and evaluated in this controlled environment, where the underlying data distribution is assumed to remain unchanged. This approach offers clear advantages: it simplifies experimentation, enables reproducible benchmarking, and allows for straightforward comparisons between algorithms.

However, this static offline setting does not reflect the realities faced by modern recommendation systems. In real-world applications, data is dynamic and ever-evolving, where new users and items are …

From Sparse Feedback To Sequential Decision-Making: Learning Safety Constraints With Weak Supervision, Siow Meng Low

Dissertations and Theses Collection (Open Access)

Real-world decision-making often involves safety constraints that are implicit, non-Markovian, or difficult to specify directly. Standard reinforcement learning (RL) approaches typically assume access to fully specified cost functions and constraint budgets—assumptions that limit their applicability in domains where such structure must instead be inferred from data. This dissertation develops a sequence of methods for learning safety-relevant structure from weak supervision, such as sparse binary feedback on trajectory segments, and using these signals to guide planning and policy optimization.

The first part of the dissertation introduces a sample-efficient method for planning in continuous Markov Decision Processes (MDPs) using deep reactive policies. …

Hardware Accelerated Simulation Of Buck Converters Using Physics-Informed Neural Networks, James Clayton Crews

Theses and Dissertations

Physics-informed neural networks (PINNs) are an emerging machine learning method for learning the behavior of physical systems described by governing differential equations. Dc-dc power-electronic converters are used in a variety of industry applications such as motor drives or power supplies where real-time simulation is critical for control and safety. This thesis investigates physics-informed machine learning as an approach to develop a real-time digital twin for dc-dc power converters. Traditional numerical integration methods are used to approximate discretized behavior, and the results are compared with a trained PINN model. Modern ML frameworks (such as PyTorch and TensorFlow/Keras) are used to quickly …

Advancing Food Nutrition Estimation Via Visual-Ingredient Feature Fusion, Huiyan Qi, Bin Zhu, Chong-Wah Ngo, Jingjing Chen, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Nutrition estimation is an important component of promoting healthy eating and mitigating diet-related health risks. Despite advances in tasks such as food classification and ingredient recognition, progress in nutrition estimation is limited due to the lack of datasets with nutritional annotations. To address this issue, we introduce FastFood, a dataset with 84,446 images across 908 fast food categories, featuring ingredient and nutritional annotations. In addition, we propose a new model-agnostic Visual-Ingredient Feature Fusion (VIF2 ) method to enhance nutrition estimation by integrating visual and ingredient features. Ingredient robustness is improved through synonym replacement and resampling strategies during training. The ingredient-aware …

Performance Enhancement In Rewound Industrial Retrofit Solutions For Five- And Six-Phase Permanent Magnet Assisted Synchronous Reluctance Machines, Kotb B. Tawfiq, Ayman M. El-Refaie, Peter Sergeant, Hatem Zeineldin, Ahmed Al-Durra, Ehab F. El-Sadaany

Electrical and Computer Engineering Faculty Research and Publications

This paper investigates upgrading aging three-phase Permanent Magnet Assisted Synchronous Reluctance Machines (PMaSynRMs) into multiphase configurations—specifically six- and five-phase windings—without modifying the existing stator or rotor laminations. This retrofit supports circular economic principles by extending machine life and reducing material waste and cost. Four configurations are examined: the original three-phase winding, asymmetrical six-phase winding, symmetrical six-phase winding, and five-phase winding. The feasibility of rewinding existing three-phase stators is explored for different slot/pole combinations. Balanced rewound five-phase windings are feasible only when the stator's slot/pole ratio is greater than or equal to 9. Both symmetrical and asymmetrical rewound six-phase windings are …

The Importance Of The Analog-To-Digital Converter In The Measurement System, Aliev Ravshan, Anvar Djalilov

Chemical Technology, Control and Management

At the moment, many scientific researches are being conducted all over the world on the economical use of water and energy resources. Most of the scientific research works are aimed at improving measurement techniques and technologies, that is, increasing their accuracy. With this in mind, a high-precision analog-to-digital converter due to its unique metrological and technical characteristics was studied in this research paper. As a result of the study, it became clear that the use of a small-sized, high-precision sigma-delta analog-to-digital converter in modern measuring technology has a positive effect on its accurate and efficient operation.

Multi-Modal Covid-19 Detection Using Cough Sounds And Medical Information With Attention-Enhanced Deep Learning, Mohamed Talaat Saidahmed, Reda Elbasiony, Marwa Reda Bastwesy, Asmaa Aly Hagar

Journal of Engineering Research

The COVID-19 pandemic has highlighted the need for fast, non-invasive, and cost-effective diagnostic tools. Cough sounds, as a prominent symptom of respiratory diseases, present a promising modality for automated COVID-19 detection. In this study, we propose a novel multi-modal deep learning framework for COVID-19 detection that leverages cough sounds and patient-specific medical information. Our approach extracts two types of acoustic features—Mel-Frequency Cepstral Coefficients (MFCCs) and Mel spectrograms—and integrates them with clinical metadata to improve diagnostic ac-curacy. The MFCC branch employs 1D convolutional layers followed by Efficient Channel Attention mechanism. The Mel spectrogram branch utilizes ResNet-50 combined with ECA to capture …

A Hybrid Binary Grey Wolf Optimizer Based On De Algorithm For Feature Selection, Amany Saad Abdelrazek, Basma Ghareeb Elkilany, M. Arafa

Journal of Engineering Research

Feature selection is one kind of optimization problem that has bio-objective functions, where it is necessary to get the minimum number of features that achieve high classification accuracy. According to literature studies, several kinds of meta-heuristic algorithms have been utilized to solve feature selection problems. One of these meta-heuristic algorithms is the Grey Wolf Optimization (GWO) algorithm and its modified variants, including the binary versions. They have yielded competitive results compared to other algorithms. Despite the simplicity and effectiveness of GWO and its modified versions, they face challenges related to the exploitation ability of the local search. To avoid premature …

Evaluation Of Machine And Deep Learning Models For Predicting Water Distillate Rate, Ghada Hamisa

Journal of Engineering Research

Freshwater scarcity has become a critical global challenge due to rapid population growth and environmental pollution caused by industrial and urban expansion. Solar stills offer a sustainable solution by desalinating impure water using solar energy, making them valuable for domestic, industrial, and academic applications. However, traditional methods for optimizing solar still performance face significant limitations, including time-consuming experimental data collection, computational inaccuracies, and high development costs. To address these challenges, this study leverages machine learning (ML) and deep learning (DL) techniques to predict the distilled water production rate of solar stills before physical construction or modification. A heat pump solar …

Dynamic Resource Allocation For Wireless Networks And Radar Systems Via Deep Reinforcement Learning, Ziyang Lu

Dissertations - ALL

The rapid advancement of wireless communication technologies and the proliferation of smart devices have led to increasingly complex and dynamic network environments. These developments have posed significant challenges to traditional radio resource management (RRM) techniques, which often struggle with scalability, adaptability, and real-time decision-making. In response to these limitations, this dissertation explores the application of advanced machine learning, particularly deep reinforcement learning (DRL), to develop intelligent, adaptive, and data-efficient solutions for resource management in wireless networks and radar systems. We begin by addressing joint channel access and power control in wireless interference networks using centralized, distributed, and federated multi-agent DRL …

Efficient Methods And Algorithms For Analyzing Stochastic Systems, Mohammad Ahmadi

USF Tampa Graduate Theses and Dissertations

This dissertation addresses the challenges of stochastic analysis of safety-critical systems with biological components, where unexpected behavior can lead to catastrophic events. Two fundamental challenges hinder the analysis of such systems: their typically large or infinite state spaces, and the extreme rarity of error states of interest. While Monte Carlo simulation can analyze biochemical systems without storing the state space, accurately estimating rare event probabilities becomes computationally prohibitive. Conversely, probabilistic model checking excels at analyzing extremely low probability events but becomes impractical for systems with large or infinite state spaces due to memory constraints.This work proposes two main contributions to …

From Assembly Lines To The Open Road: Predicting Rare Events In Autonomous Systems, Ruwan Wickramarachchi

Publications

In the age of embodied AI and smart automation, autonomous agents are increasingly deployed in high-stakes, real-world environments. Ensuring the robustness and resilience of these systems in the face of rare but critical failure events is essential for their safe and reliable operation. Accurate forecasting of such rare events is particularly crucial, as a single overlooked anomaly can lead to catastrophic consequences. In manufacturing, for instance, unplanned downtime due to rare failures costs industries over \$50 billion annually, with sectors like automotive losing more than \$2 million per hour—even with preventive maintenance systems in place.

However, the extreme rarity and …

Director, Military Cyber Institute, Joseph Schafer

Military Cyber Affairs

No abstract provided.

Throughput Of Ascon Compared With Popular Iot Encryption Algorithms, Mitchel R. Harvey (Ryan), Andrew M. Kaiser, Garrett W. Hoiness

Military Cyber Affairs

No abstract provided.

Anomaly Detection Of Network Layer Attacks Against Cyber Physical Systems Using Machine Learning And Deep Learning Techniques, James Alger, Michael Tu

Military Cyber Affairs

This research paper presents the analysis of using machine learning and deep learning algorithms on detecting anomalous network traffic in Cyber-Physical Systems (CPS). Using a real PLC CPS-based system, normal and anomalous network traffic will be captured using Wireshark. The research analyzes a DDoS attack. The focus of the research is to identify the most effective feature combinations and evaluate them on ML and DL models. The emphasis is on enhancing detection strategies rather than exploiting device vulnerabilities. The detection of network attacks often involves handling a vast array of high-level features. Previous studies (Li & Chasaki, 2022) apply machine …

Characterizing Caldera’S Cyber Attack Emulation Capabilities, Caleb Chang, Matthew Cao, Kenyou Teoh, Ekzhin Ear, Shouhuai Xu

Military Cyber Affairs

Autonomous cyber attack emulation can aid cyber defenders to identify and remediate cyber risks. MITRE’s Caldera software is the state-of-the-practice for automated attack emulation. Yet, it has not been systematically analyzed, putting its performance and effectiveness into question. This paper systematically characterizes Caldera’s architecture, abilities and use cases, and assesses its strengths and weaknesses. It draws useful insights, such as: Caldera excels in stealthy access and execution tactics to pilfer data against Windows operating systems. It also discusses two directions for Caldera improvement: module-level automation and end-to-end attack emulation.

The Digital Battlefield: Safeguarding Military Drones Against Cyberattacks, Jason Ashong, Arun Venkitanarayanan, Benjamin Yankson

Military Cyber Affairs

The Internet of Battlefield Things (IoBT) is an advanced network of interconnected devices that significantly enhance military operations through real-time data exchange and situational awareness. While IoBT offers tactical advantages like improved surveillance, reconnaissance, and operational effectiveness, it also introduces substantial cybersecurity risks. Adversaries can exploit vulnerabilities within these networks, potentially compromising mission integrity and national security. This research examines the cybersecurity measures of commercial drone controllers and their correlation with military devices. It aims to enhance future vulnerability assessments with advanced tools and approaches to better secure critical military operations. The study highlights the need for robust security architectures …

Using Blockchain Technology To Help Secure America's Defense Critical Infrastructure, Vimal Buck, Aerin Krebs, Brynn Hillard, Jakob Gerha, Joseph Lutma, Srikar Maduposu, Ted Allen

Military Cyber Affairs

Critical water infrastructure in the United States faces increasing cybersecurity threats from state-sponsored actors, with potentially devastating consequences for national security, economic stability, and public health. (Cybersecurity and Infrastructure Security Agency, 2025). This infrastructure supports defense critical assets and is actively being targeted by various state-sponsored hacking groups, which poses a major concern for civilians and military alike. K. Herath (personal communication, February 24, 2025) reported being aware of two attacks on Ohio water systems during his tenure as Cybersecurity Strategic Advisor to Ohio Governor Mike DeWine.

Water is essential to everyday life and defense and presents as a high-value …

Network And Multipath Traceroute Visualization, Cameron Makowski

Military Cyber Affairs

TraceCam introduces a new paradigm in network path analysis, leveraging GPU-accelerated WebGL visualization, advanced traceroute integrations, and AI-driven insights to transform complex routing data into actionable intelligence. Early prototypes have demonstrated significant improvements in performance, clarity, and multi-path discovery, overcoming traditional limitations in traceroute analysis. By incorporating retrieval-augmented language models and enriched metadata sources like IPinfo.io, TraceCam enables automated anomaly detection, contextual explanations, and rapid root-cause analysis, enhancing operational efficiency. The platform’s architecture ensures scalability and adaptability, supporting deeper investigations and real-time situational awareness. Future development will focus on clustering-based anomaly detection, expanded geographic visualizations, and enhanced AI-generated analysis to …

Quantifying Adversary Military Forces’ Susceptibility To Cognitive Attacks, Bonnie Rushing, Cole Nelson, Shouhuai Xu, Christofer “Raven” O’Keefe, Olga Karpoyan

Military Cyber Affairs

This paper introduces a method to quantify international populations’ susceptibility to cyber cognitive attacks using press freedom and media trust metrics. We present the Cognitive Influence Calculator, a tool that estimates susceptibility (𝑆) based on Press Freedom Scores (PFS) and media trust levels. Findings show that while authoritarian regimes are harder to reach, successful cognitive attacks have greater impacts due to higher trust in state-controlled narratives. Using U.S. wargaming data and international trust metrics, we compute susceptibility scores for the U.S., Russia, China, Iran, and North Korea. Results show an inverse relationship between PFS and media susceptibility, with local/allied …

Forward, Amy Hamilton

Military Cyber Affairs

No abstract provided.

Understanding Russia’S Cyber Policies, Strategies, And Doctrines, Bryan Hancock, Hanh Nguyen, Olga Karpoyan, Ekzhin Ear, Shouhuai Xu

Military Cyber Affairs

This study analyzes the strengths and weaknesses of Russia’s cyber policies, strategies, and doctrines through a systematic set of attributes, leading to key insights: (i) Russia has proactively adapted its cyber policies, strategies, and doctrines to its evolving environment; (ii) Russia actively conducts cognitive warfare, but remains equally vulnerable to it; and (iii) Russia’s cyber posture faces significant challenges, including a limited technological base, shortage of skilled personnel, and restrictive approach to information control, all of which undermine the effectiveness of its strategies. These insights offer valuable implications for US Cyber Command and the Department of Defense.

Characterizing Cyberattacks Against Operational Technology Infrastructures Through The Lens Of Attack Flows, Sherman Kettner, Caleb Chang, Ekzhin Ear, Shouhuai Xu

Military Cyber Affairs

Operational Technology (OT) infrastructures play a critical role in modern society and economy. However, their increasing connectivity with public networks such as the Internet has made them vulnerable to cyberattacks, much like traditional Information Technology (IT) systems. In particular, cyberattacks against OT infrastructures remain relatively underexplored and little understood. In this paper, we aim to deepen our understanding of cyberattacks against OT infrastructures. For this purpose, we propose a methodology, including novel cybersecurity metrics to analyze the attack flows of these attacks in an end-to-end fashion, which allows us to draw useful insights. We demonstrate the utility of the methodology …

Tweaking Ml-Kem (Kyber) And Ml-Dsa (Dilithium), Kumar Rahul

Master’s Dissertations

Lattice-based cryptography is the use of conjectured hard problems on point lattices in Rn as the foundation for secure cryptographic systems. Attractive features of lattice cryptography include apparent resistance to quantum attacks (in contrast with most number-theoretic cryptography), high asymptotic efficiency and parallelism, security under worst-case intractability assumptions, and solutions to long-standing open problems in cryptography. This work surveys the structure, security, and optimization potential of two leading lattice-based cryptographic schemes: ML-KEM (Kyber) and ML-DSA (Dilithium). Special attention is given to their applicability in government-oriented post-quantum cryptographic systems, focusing on performance, implementation considerations, and resilience against known quantum threats. In …

Limb Light - Interactive Lighting Control, Joseph Pandit, Matthew Tran

Computer Science and Engineering Senior Theses

The progression of stage lighting in the modern age has significantly influenced the immersive experience of the audience. Through events like Daft Punk’s 2006 Cochella performance, lighting has become more pivotal to performances in every genre. However, interactive, customized lighting remains inaccessible to small and mediumscale performers. The cost of hiring a lighting director or pre-programing each song is simply too much. Current cost effective solutions, like sound-activated effects, lack in both quality and real-time emotional responsiveness.

This thesis presents an interactive lighting control system designed to bridge this gap and create a novel creative tool. Our approach integrates MIDI-triggered …

Harnessing Generative Ai And Large Language Models For Revolutionizing Cybersecurity In The Internet Of Things: Ethical And Privacy Implications, Harsha Sammangi, Aditya Jagatha, Jun Liu

Research & Publications

Generative artificial intelligence (AI) and large language models (LLMs) have in- troduced transformative capabilities in cybersecurity, particularly in securing Internet of Things (IoT) environments. These technologies can synthesize vast datasets, support real-time anomaly detection, and generate predictive insights through simple prompts. However, their deployment also presents ethical and privacy-related concerns, including algorithmic bias, data leakage, and misuse for malicious content creation. This paper conducts a systematic literature review to evaluate how LLMs and generative AI contribute to IoT cybersecurity. We propose an ethical AI-IoT security framework, examine key challenges, and offer recommendations for integrating responsible AI governance. We aim to …

Cst110.1 Analysing Everyday Interfaces Example 1, Sae University College

Exemplars

A Case Study on MyTime Interface analysing the usability of it.

Cst110.1 Analysing Everyday Interfaces Example 2, Sae University College

Exemplars

A Case Study on usability analysis of the Apple iOS fitness app.

Context-Switch Attacks: Understanding And Mitigating The Threat To Llm Applications, Sydney Holder, Bivin Sadler

SMU Data Science Review

Large Language Models (LLMs) are transforming conversational AI, yet their dependence on prompt-supplied context exposes them to context-switch attacks that covertly steer dialogue toward sensitive or malicious ends. A 70 one-sided conversation transcript evaluation set was constructed spanning various fraudulent scenarios. Each transcript embeds adversarial patterns drawn while preserving natural conversational flow. We introduce a hybrid defense that pairs a BERT-based semantic-drift detector (cosine-similarity threshold = 0.70) with a curated keyword and hack-phrase scanner to counter these threats. In aggregate, the system delivered 100 % recall, intercepting every simulated phishing or data-harvesting attempt. The keyword layer achieved perfect precision, generating …

Simulation Study On Optimizing Microgrid Scheduling With Electric Vehicle Participation Under V2g Mode, Zhongan Yu, Hongliang Xiao, Qiangwei Xia, Jiawei Liu

Journal of System Simulation

Abstract: To address the negative impact of source-load uncertainty on the stable operation of the grid, a two-stage optimization scheduling strategy for the microgrid participation of electric vehicles based on the vehicle-to-grid (V2G) mode is proposed. In the first stage, the charging and discharging costs of electric vehicles as well as the load fluctuation target are determined taking into account the battery losses. Through a zero-sum game, we objectively weigh the interests of both vehicle owners and the microgrid, utilizing the mobile energy storage characteristics of electric vehicles to optimize the load curve and integrate renewable energy; in the second …