Digital Commons Network^™

Advancing Task-Oriented Dialog Systems: Scalability, Generalization, And Evaluation, Adib Mosharrof

Theses and Dissertations--Computer Science

Task-oriented dialog (TOD) systems enable conversational interfaces for complex tasks like flight booking and restaurant reservations. However, deploying TOD systems at scale faces three critical barriers: scalability, generalization, and evaluation. Scalability is primarily restricted by the human-annotation bottleneck, as current systems depend on vast quantities of manually labeled data for every new domain, making deployment prohibitively expensive. Generalization remains a persistent challenge, as systems optimized for known domains often suffer significant performance degradation when encountering new, unseen ones. Existing evaluation metrics measure response quality and fluency, but fail to measure functional task success. As TOD systems are deployed across diverse …

A Comprehensive Survey Of Prompt Engineering Techniques In Large Language Models, Tonmoy Debnath, Md Nurul Absar Siddiky, Muhammad Enayetur Rahman, Prosenjit Das, Antu Kumar Guha, Muhammad Rezaur Rahman, H. M. Dipu Kabir

Electrical & Computer Engineering Faculty Publications

Prompt engineering has arisen as a pivotal discipline in optimizing the performance of Large Language Models (LLMs) by structuring inputs to enhance coherence, accuracy, and task alignment. This paper comprehensively surveys various prompting techniques, systematically categorizing them according to their application domains and methodological foundations. Fundamental approaches like zero-shot and few-shot prompting are examined along with advanced strategies, including chain-of-thought reasoning, retrieval-augmented generation, and self-consistency mechanisms. A rigorous qualitative analysis is conducted to evaluate each technique's strengths, limitations, and optimal use cases, offering a structured framework for selecting the most effective prompting strategies. Theoretical insights and empirical findings are consolidated …

Physics-Informed Temperature Prediction Of Lithium-Ion Batteries Using Decomposition-Enhanced Lstm And Bilstm Models, Seyed Saeed Madani, Yasmin Shabeer, Michael Fowler, Satyam Panchal, Carlos Ziebert, Hicham Chaoui, François Allard

Electrical & Computer Engineering Faculty Publications

Accurately forecasting the operating temperature of lithium-ion batteries (LIBs) is essential for preventing thermal runaway, extending service life, and ensuring the safe operation of electric vehicles and stationary energy-storage systems. This work introduces a unified, physics-informed, and data-driven temperature-prediction framework that integrates mathematically governed preprocessing, electrothermal decomposition, and sequential deep learning architectures. The methodology systematically applies the governing relations to convert raw temperature measurements into trend, seasonal, and residual components, thereby isolating long-term thermal accumulation, reversible entropy-driven oscillations, and irreversible resistive heating. These physically interpretable signatures serve as structured inputs to machine learning and deep learning models trained on temporally …

Comparative Assessment Of Energy And Emission Costs For Geothermal Heat Pumps And Fossil-Fuel Heating Systems Across U.S. Climatic Zones, Md Shahin Alam, Shima Afshar, Seyed Ali Arefifar, Mohammad Haq

Electrical & Computer Engineering Faculty Publications

In response to growing concerns over global warming and energy sustainability, transitioning from fossil-fuel-based heating systems to renewable alternatives is essential. This study evaluates the economic and environmental performance of geothermal heat pumps for building heating and compares it with conventional coal-fired boilers, natural-gas boilers, and diesel furnaces. Using the heating degree-day (HDD) method, heating energy demand was analyzed for four U.S. cities—Anchorage (AK), San Francisco (CA), Salt Lake City (UT), and Las Vegas (NV)—representing diverse climatic zones. The analysis integrates thermodynamic and economic parameters, including the coefficient of performance (COP = 2–5) and annual fuel-utilization efficiency (AFUE = 80–97%), …

Machine Learning-Based Lifetime Prediction Of Lithium Batteries: A Comparative Assessment For Electric Vehicle Applications, Abdelilah Hammou, Raffaele Petrone, Demba Diallo, Boubekeur Tala-Ighil, Philippe Makany Boussiengue, Hicham Chaoui, Hamid Gualous

Electrical & Computer Engineering Faculty Publications

This paper evaluates and compares four data-driven methods (Gaussian Process Regression (GPR), echo state network (ESN), gated recurrent unit (GRU), and long short-term memory (LSTM)) for lithium-ion capacity prognostics adapted to electric vehicle conditions. This comparison aims to find the most efficient prognosis method considering two constraints: the limitation of computational power and the unavailability of on-board capacity measurement that requires full charge and discharge conditions. The machine learning models are trained using capacity values estimated under vehicle conditions. The ageing data is collected from cycling tests of two battery chemistries, Lithium Fer Phosphate (LFP) and Nickel Manganese Cobalt (NMC), …

Digital Twin Technologies For Battery Systems: Advancements, Applications, And Future Directions, Seyed Saeed Madani, Yasmin Shabeer, Michael Fowler, Satyam Panchal, Carlos Ziebert, Hicham Chaoui, François Allard

Electrical & Computer Engineering Faculty Publications

The relationships among deep learning, edge computing, artificial intelligence (AI), and the most recent advancements in digital twin (DT) technology for battery energy storage systems are discussed in this paper. The study highlights the need for improved cloud-edge coordination, AI model development, and stronger cybersecurity features by demonstrating real-world applications of digital twin technology in electric vehicles (EVs), aircraft, and grid storage. It also described DT-based structures for fault detection, real-time monitoring, and optimization through standardization and battery management system (BMS) fusion. Because DT-based solutions for distributed energy resources (DERs) offer improved energy management systems, various studies have been conducted …

Qubit Lattice Algorithm Simulations Of The Scattering Of A Bounded Two Dimensional Electromagnetic Pulse From The Infinite Planar Dielectric Interface, Min Soe, George Vahala, Linda Vahala, Efstratios Koukoutsis, Abhay K. Ram, Kyriakos Hizanidis

Electrical & Computer Engineering Faculty Publications

Qubit lattice algorithm (QLA) simulations are performed for a two-dimensional spatially bounded pulse propagating onto a plane interface between two dielectric slabs. QLA is an initial value scheme that consists of a sequence of unitary collision and streaming operators, with appropriate potential operators, that recover Maxwell equations in inhomogeneous dielectric media to the second order in the lattice discreteness. For the case of total internal reflection, there is transient energy transfer into the second medium due to the evanescent fields as the Poynting unit vector of the pulse is rotated from its incident to reflected direction. Because of the finite …

An Explainable Cs-Mitigation Triangular (Ecsmt) Framework To Secure Graph Neural Networks, Sabah Ettahri, Sergio Pallas Enguita, Chung-Hao Chen, Wen-Chao Yang

Electrical & Computer Engineering Faculty Publications

This research addresses cyber risk by defending against backdoor attacks on Graph Neural Networks (GNNs). We propose the Explainable Complex System-Mitigation Triangular (ECSMT) Framework, which integrates Robust Training, Graph Regularization, and Data Sanitization into a lightweight, hardware-efficient defense layer. To evaluate structural generalizability, we conducted empirical evaluations across three distinct benchmark domains (AIDS, MUTAG, and PROTEINS) using a Graph Isomorphism Network (GIN) backbone. Under a baseline 5% backdoor subgraph trigger injection ratio, ECSMT achieves excellent utility retention, securing a Clean Accuracy (CA) of 97.33% (±0.62%) while reducing the Attack Success Rate (ASR) from 97.00% down to 69.45% on the primary …

Generalized Inverter Fault Detection Using Normalized Current Features And A Lightweight Bilstm Network, Mohammad Zamani Khaneghah, Mohamad Alzayed, Hicham Chaoui

Electrical & Computer Engineering Faculty Publications

Fault detection and diagnosis of three-phase inverter-fed motor drives is essential for ensuring system reliability, safety, and continuous operation in applications such as electric vehicles and industrial automation. This paper proposes a data-driven fault detection framework based on normalized current features and a lightweight bidirectional long short-term memory (BiLSTM) network which can be generalized to different motor power rating in the same controller system. A compact set of six time-domain features, consisting of the mean and root-mean-square (RMS) values of the phase currents, is extracted and normalized with respect to the average RMS value. This normalization effectively removes dependency on …

Automated Writer And Acquisition-Condition Classification Of Digitally Captured Handwriting Using Statistical Dynamic Features And Support Vector Machines, Long-Huang Tsai, Hsiang-Ju Lai, Wen-Chao Yang, Jiajun Jiang, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

Digitally captured handwriting preserves pen trajectories and dynamic signals, but it also records hardware- and input-dependent properties that can confound forensic interpretation. This study revises a support vector machine (SVM) screening framework using 16,500 samples from 30 writers, 11 writing-content categories, and five acquisition conditions spanning three tablets and stylus or finger input. Twenty-four raw and derived time-series variables were summarized by maximum, minimum, mean, median, and standard deviation, yielding 120 features; the mode statistic was removed. Writing direction and angular velocity were recalculated with atan2-based vector formulas. Unavailable device/API channels were encoded as zero, and Z-score parameters were estimated …

Modeling Rank Distribution And The Relative Importance Factor Index In Discrete Power-Law Models: Application To Social Resilience Using The Scopus Database, Brian Llinas, Jose Padilla, Humberto Llinas, Erika Frydenlund, Katherine Palacio

VMASC Publications

Prior research on power-law distributions has primarily focused on modeling frequency patterns, with less attention given to rank distributions and how ranked positions reflect relative importance among elements. In discrete power-law distributions, frequency-based metrics often provide limited discrimination in the tail, where elements may exhibit similar counts but differ in relative dominance. These patterns are especially evident, for instance, in academic publishing, where keywords, affiliations, and citations commonly exhibit power-law behavior. To address this limitation, we introduce the Relative Importance Factor (RIF) Index, a statistical measure derived from the estimated discrete power-law rank distribution rather than an additional independent parameter. …

Cybersecurity Center For Offshore Wind Energy (Final Project Round), Sachin Shetty

Center for Secure and Intelligent Critical Systems (CSICS) Publications

This project establishes a Cybersecurity Center for Offshore Wind Energy with the objective of designing and operating a cyber-physical testbed for wind energy farms (WEFs) that enables comprehensive cybersecurity research. The testbed incorporates a Supervisory Control and Data Acquisition (SCADA) system connected to turbine models via industrial-grade programmable logic controllers (PLCs) and remote terminal units (RTUs). It supports side-channel data acquisition, implementation and analysis of various cyberattack scenarios, and development of attack detection, mitigation, and best-practice guidance tailored to wind energy systems. During the project, the team expanded the number and fidelity of mathematical turbine models (MTMs), integrated these models …

Analysis Of Policies And Incentives For The Successful Implementation Of Hydrogen-Fueled Medium-Duty And Heavy-Duty Vehicles In Humboldt County, California, Alka Verma

Cal Poly Humboldt theses and projects

The 21st century has seen a significant rise in global greenhouse gas (GHG) emissions, with the transportation sector contributing 23% of these emissions. Medium-duty and heavy-duty vehicles (MD/HD) are particularly impactful, accounting for over a quarter of transport-related emissions. In Humboldt County, California, transportation represents 53% of total emissions, with MD/HD vehicles being a major contributor. As light-duty vehicles shift to zero-emission alternatives, the MD/HD sector faces unique challenges. Hydrogen fuel cell vehicles offer a promising solution, providing longer range, higher energy density, and quicker refueling compared to battery electric vehicles (BEVs). These features make hydrogen an attractive option for …

Bridging Physics-Based Modeling And Machine Learning To Predict Material Behavior: Applications In Fatigue Crack Growth And Dielectric Property Characterization, Ansan Pokharel

Graduate Theses, Dissertations, and Problem Reports (ETD)

This dissertation integrates physics-based modeling with machine learning (ML) to predict how materials behave under complex thermal and mechanical conditions. A key innovation of this work is the use of finite element analysis (FEA) to supplement experimental data. This approach creates more diverse and representative synthetic datasets, helping to reduce the limitations and biases that arise when training ML models solely on experimental measurements. The research focuses on two applications: improving the prediction of fatigue properties in superalloys and estimating temperature-dependent, high-frequency dielectric properties relevant to microwave-based chemical processing.

In the first study, low-cycle fatigue experiments were performed on the …

A Digital Calibration Source For 21 Cm Cosmology Telescopes, Kalyani Balkrishna Bhopi

Graduate Theses, Dissertations, and Problem Reports (ETD)

Precise calibration of radio telescope beams and gains is a central requirement for 21 cm intensity mapping experiments, which aim to measure large scale cosmological structure through the redshifted emission line of neutral hydrogen. Bright astrophysical foregrounds dominate the sky at these frequencies, and separating them from the cosmological signal demands precise control over instrumental systematics, particularly the telescope beam and its frequency-dependent response. Existing aerial calibration sources are incoherent broadband emitters, detectable only as total power. They provide no direct phase information and suffer from poor sensitivity in low signal-to-noise regimes.

We present the Precision Emitter for 21cm Array …

Control System Emendation And Ai-Driven Optimization For Enhancing A Smart Residential Microgrid, Anthony Nyoyoko

Master’s Theses

This thesis began with a simple idea: to restore the control system of a smart residential microgrid to respond intelligently to electricity prices while remaining safe, reliable, and practical on low-cost hardware. At the start, the goal was to design an economically aware microgrid that could look at electricity prices from the PJM market and make better operational decisions than traditional rule-based control. The motivation was straightforward. As residential renewable energy adoption increases, microgrids are expected to do more than just supply power. They are expected to respond to price volatility, integrate renewable generation, and operate reliably using embedded controllers …

Printer For Music Box, Chad Lewis, Caleb Murawski, Zion Smith, Bryan Tibbs

Williams Honors College, Honors Research Projects

The traditional method of creating music box sheet music involves manually punching holes into a paper strip using a hand-operated hole punch. This process involves precise knowledge of each note’s location and the ability to achieve perfect accuracy for hours.

The goal of this system is to automate this process, significantly reducing the time required while greatly improving the accuracy of the resulting music box playback. The user simply uploads a MIDI file of their choice into a user-friendly application. Here, the file is modified based on the user’s needs and sent to an automated hole-punching system to punch the …

C. Difficile Detection Method For First Responder Glove Application, Alli N. Senedak

Williams Honors College, Honors Research Projects

Clostridioides Difficile (C. diff) is a Anaerobic Gram-positive bacillus that is capable of spore formation, making it difficult to control its spread and duration in clinical environments. This phenomenon can provide danger to first responders, healthcare workers, and patients. The goal of this project is to create a biosensor capable of detecting C. diff in a clinical setting that can be applied to a glove apparatus. The project will involve the use of C. diff aptamers activated on the surface of an electrode. Once surface activation has been verified via surface analysis, the electrodes will be exposed to C. diff …

Connecting The Existing Fiber Infrastructure To The Future With Antiresonant Hollow Core Fibers, Timothy Bate

Graduate Studies Theses and Dissertations 2026

Optical fiber systems based on solid-core silica waveguides underpin modern telecommunications, high-power laser delivery, precision sensing, and coherent optical systems. However, nonlinear effects, material absorption, and thermal limitations within silica increasingly constrain further scaling in both optical power and transmission performance. Antiresonant hollow-core fibers provide a promising alternative by guiding light predominantly in air, substantially reducing nonlinear interactions, latency, and optical damage while enabling transmission regimes inaccessible to conventional solid-core fibers. Despite rapid advances in antiresonant hollow-core fiber attenuation and power handling, one of the largest remaining barriers to widespread adoption is reliable integration with the existing solid-core fiber ecosystem. …

High-Efficiency And Compact Virtual Reality Displays, Zhenyi Luo

Graduate Studies Theses and Dissertations 2026

Virtual reality (VR) and augmented reality (AR) technologies are revolutionizing the way humans interact with digital information. However, current near-eye display systems still face critical challenges regarding optical efficiency, image quality, and device weight. This dissertation focuses on addressing these limitations through innovative liquid-crystal (LC) optics and system-level design strategies to achieve high-efficiency and compact VR displays.

First, to solve the longstanding problem of severe chromatic aberrations in ultrathin LC optics, I proposed an achromatic diffractive LC device. By stacking three LC layers with specifically designed spectral responses and polarization selectivity, I successfully reduced the chromatic aberrations. This idea enables …

Chronofy: A Temporal-Logical Decay Architecture For Information Validity In Time-Aware Retrieval-Augmented Generation, Muntaser Syed, Marius Silaghi, Sheikh Abujar, Sharun Akter

Electrical Engineering and Computer Science Student Publications

Retrieval-Augmented Generation (RAG) systems retrieve and integrate external knowledge to ground large language model (LLM) outputs. However, current RAG architectures treat all retrieved facts as equally valid regardless of temporal provenance, leading to temporal hallucination, where plausible but obsolete facts corrupt the output. A clinical lab reading from yesterday is actionable; the same reading from six months ago is noise. We present Chronofy, a three-layer neuro-symbolic framework implementing the Temporal-Logical Decay Architecture (TLDA) that embeds temporal validity directly into the representation, retrieval, and reasoning layers of RAG systems. Layer 1 reserves a dedicated temporal subspace within Matryoshka embeddings to make …

Epistemic Edge: Subjective Logic Guardrails For Llm-Driven Iot Actuation, Muntaser Syed, Marius Silaghi

Electrical Engineering and Computer Science Student Publications

Deploying large language models (LLMs) as decision-making agents in safety-critical Internet of Things (IoT) systems introduces risks that purely behavioral guardrails, such as action whitelists, cannot fully address. This paper presents Epistemic Edge, a four-tier neuro-symbolic pipeline that augments LLM-driven actuation with subjective logic (SL) uncertainty quantification, temporal decay, and dual guardrails combining epistemic threshold checks with behavioral whitelists. We evaluate seven locally-deployed models: three PrismML Bonsai 1-bit models (1.7B, 4B, 8B), three 4-bit quantized models (Qwen3-8B, Llama 3.2-3B, Phi-3.5-mini), and the DeepSeek-R18B reasoning model, across eight ablation conditions and five IoT actuation scenarios (2,800 controlled trials). We further validate …

Healthcare Digital Twins: A Methodological Literature Review On Integrating Iot And Ai For Personalized Medicine And Predictive Care, Sara Shahnazinia, Mahsa Tavasoli, Abdolhossein Sarrafzadeh, Ali Karimoddini

Electrical & Computer Engineering Faculty Publications

Digital Twin (DT) technology has the potential to revolutionize healthcare delivery and enhance patient outcomes through personalized and precision medicine, simulation models for operations and interventions, and drug discovery. However, successful implementation of DTs in Internet of Things (IoT) and artificial intelligence (AI) healthcare is contingent upon addressing key challenges such as privacy, ethics, and robust data security. This paper presents a methodological literature review of DT applications in healthcare, systematically analyzing the current state of research, key enabling technologies, and implementation challenges. The review summarizes DT categorization approaches (application-based, technology-based, and real-time function-based); delineates core DT components such as …

Towards Optimal And Resilient Ac/Dc Microgrids: Control Design, Analysis, And Implementation, Jun Zhang

Electronic Theses and Dissertations

Microgrids serve as a small-scale power grid for utilizing renewable energy to enhance energy reliability, sustainability, and resilience. As an autonomous system, an islanded microgrid can disconnect from the utility grid and operate independently by maintaining system voltage and frequency. However, this new feature introduces coordination problems among distributed generators (DGs), such as 1) how to make sure the voltage profile and current sharing in DC microgrid with different types of converters; 2) how to reduce the impact of cyberattack when the system coordination is performed based on communication, and 3) how to calculate the steady state under a droop …

Nanomagnet Based Straintronic Devices For Unconventional Computing: Simulation And Performance Analysis, Rahnuma Rahman

Theses and Dissertations

Nanomagnetic devices are of great interest in digital hardware because of their non-volatility and dynamic ability to change magnetization but suffer from high switching error rates and temperature sensitivity. Magnetostrictive nanomagnets that utilize strain to switch between stable magnetization states encoding bit information are of interest since they are extremely energy efficient as piezoelectric layers can be used to rotate magnetization that have switching energies in the range of attojoules. Their stochasticity can also be useful in probabilistic, analog, neuromorphic, and collective computing systems, where occasional switching errors are not devastating. The dissertation extends spintronics beyond conventional computing schemes by …

Multi-Level Energy Optimization For Connected And Automated Vehicles: From Cooperative Multi-Vehicle Control To Individual Powertrain Management, Pruthwiraj Santhosh

Dissertations, Master's Theses and Master's Reports

The transportation sector currently accounts for nearly 30% of global energy consumption, necessitating urgent advancements in vehicle efficiency to meet Net Zero targets. Leveraging connectivity and automation, this dissertation proposes and validates methodologies to reduce the energy consumption of light-duty vehicles at both fleet and individual levels.

First, a validation framework is developed to bridge the “simulation-to-real world” gap in Cooperative Automated Vehicle (CAV) research. Moving beyond virtual simulations, the study establishes a methodology for physically validating centralized control architectures via a custom Cellular V2X network. By synchronizing vehicle-powertrain models with physical test vehicles, the framework successfully orchestrates complex arterial …

Towards Increasing The Retention Of Freshman Engineering Students: Implementing A New Course, Ee 101 Introduction To Electrical And Computer Engineering, Omer Lateef, Mingyu Lu, Waseem Alaqqad, Charan Litchfield, Kenan Hatipoglu

2026 Scholarly Teaching Conference: Poster Session Papers

To assist with improving student retention in the undergraduate electrical and computer engineering program, a course was developed and implemented at the freshman level in the Spring of 2021.  This course was named EE 101: Introduction to Electrical and Computer Engineering and served to give freshman students an opportunity to meet the professors of the ECE department and experience live sessions dedicated to presenting “upcoming” topics and research endeavors of their expertise.  Students typically will not be attending the electrical or computer engineering subjects until their sophomore year and this course, set in second semester for a freshman, attempts to …

Improving Medical Diagnostics With Vision-Language Models: Convex Hull-Based Uncertainty Analysis, Ferhat Ozgur Catak, Murat Kuzlu, Taylor Patrick, Michel Audette

Engineering Technology Faculty Publications

In recent years, vision-language models (VLMs) have been applied to various fields, including healthcare, education, finance, and manufacturing, with remarkable performance. However, concerns remain regarding VLMs’ consistency and uncertainty, particularly in critical applications such as healthcare, which demand a high level of trust and reliability. This paper proposes a novel approach to evaluate uncertainty in VLMs’ responses using a convex hull approach on a healthcare application for visual question answering (VQA). For any VLM, temperature refers to a sampling parameter used in probabilistic generation, which controls the randomness of the model’s output. The LLM-CXR model is selected as the medical …

Dystop: Dynamic Staleness Control And Topology Construction For Asynchronous Decentralized Federated Learning, Yizhou Shi, Qianpiao Ma, Yan Xu, Junlong Zhou, Ming Hu, Yunming Liao

Research Collection School Of Computing and Information Systems

Federated Learning (FL) has emerged as a potential distributed learning paradigm that enables model training on edge devices (i.e., workers) while preserving data privacy. However, its reliance on a centralized server leads to limited scalability. Decentralized federated learning (DFL) eliminates the dependency on a centralized server by enabling peer-to-peer model exchange. Existing DFL mechanisms mainly employ synchronous communication, which may result in training inefficiencies under heterogeneous and dynamic edge environments. Although a few recent asynchronous DFL (ADFL) mechanisms have been proposed to address these issues, they typically yield stale model aggregation and frequent model transmission, leading to degraded training performance …

Generative Ai-Driven Optimization In Flexible And Reconfigurable Manufacturing Systems, Salah Hammedi, Hicham Chaoui, Lotfi Nabli

Electrical & Computer Engineering Faculty Publications

Flexible and Reconfigurable Manufacturing Systems (FRMSs) are essential for coping with variability in modern production environments; however, efficient scheduling and rapid reconfiguration remain challenging. This paper presents a hybrid optimization framework that integrates Colored Petri Net (CPN) modeling with Generative Artificial Intelligence (GenAI) to enhance scheduling performance and system adaptability. The CPN formalism ensures verifiable modeling of system dynamics, while a transformer-based generative model produces candidate scheduling and reconfiguration strategies. Simulation experiments were conducted under static, dynamic, and adaptive scenarios, including machine breakdowns and dynamic job arrivals. Performance was evaluated using makespan, mean flow time, machine utilization, and reconfiguration latency. …