Engineering Commons^™

Real-Time Cyber-Power Testbed Enhancement And Synchrophasor Data Generation For Anomaly Detection Using Physics-Informed Machine Learning, Vasavi Sivaramakrishnan

Graduate Theses, Dissertations, and Problem Reports (ETD)

Advanced sensing and automation are essential to managing the evolving electric power system with tight coupling of information and power system layer. However, this increasing number of cyber-physical devices brings vulnerabilities from cyber threats and extreme weather events can endanger the power system on a physical level as well. Advanced monitoring and control algorithms with human operators in the loop are needed to enable power system resiliency despite these increasing threats. These advanced algorithms require validation using a realistic test system that mimics real-world scenarios.

This work focuses on a) developing a realistic real-time cyber-power testbed with hardware-in-the-loop to generate …

Cleaning And Characterization Of Chemical Vapor Deposited Graphene For Nanoelectronic Device Development, Sakib Ishraq

Graduate Theses, Dissertations, and Problem Reports (ETD)

Nanoelectronic devices based on graphene are a promising technology that combines the sensitivity and specificity of ion and element recognition with the accuracy and precision of electronics. The detection principle is based on the interaction of the target molecules with the nanodevice surface, which generates a measurable electrical signal. In the current study, graphene and its derivatives, synthesis and fabrication of high quality, good uniformity, and low defects graphene have been investigated as they are critical for high-performance and highly sensitive devices. Among many synthesis methods, chemical vapor deposition (CVD), have been used that needs to be transferred from the …

Low Power Remote Sensing System For Ceramic Thermocouples, Syed Khaleduzzaman

Graduate Theses, Dissertations, and Problem Reports (ETD)

The ceramic thermocouple sensor is a promising alternative to traditional thermocouple due to their corrosion resistance and cost-effective manufacturing. Currently, no electronic Interface or Integrated Circuit solution is commercially available which can be used to interface these thermocouples at low-cost and low power for accurate temperature measurement. An electronic system is needed to use these ceramic sensors which consumes less amount of power for an extensive period of time with remote monitoring option.

This thesis proposes a low-power electronic remote sensing system that works for ceramic thermocouples. The system consists of three parts. They are battery-operated sensor node electronic circuit, …

Active Uncertainty Representation Learning: Toward More Label Efficiency In Deep Learning, Salman Mohamadi

Graduate Theses, Dissertations, and Problem Reports (ETD)

The primary goal of this dissertation is to investigate and improve the efficiency of deep learning algorithms, especially within computer vision problem domains, from the perspective of label-efficiency. This investigation showed that deep learning algorithms are mostly notorious for the lack of uncertainty representation. Accordingly, we aimed to develop an array of deep learning frameworks rich with uncertainty representation. These frameworks are mainly within two current pillars of machine learning, deep active learning and self-supervised learning. These frameworks include deep active ensemble sampling for efficient sample selection within deep active learning, a two-stage ensemble-based general self-training approach for existing visual …

Analyzing Viability Of Blue Indium Gallium Nitride Leds For Use In Space Missions Using A Low Earth Orbit Cubesa, Bertrand Edward Wieliczko

Graduate Theses, Dissertations, and Problem Reports (ETD)

The payload capacity of spacecraft is constrained by the weight of the craft itself, including fuel and electronic systems. The protective measures used to shield onboard electronics from the harsh space environment, characterized by high-energy particles and significant temperature fluctuations, can further diminish the available payload capacity. This thesis explores the potential of naturally radiation-hard alternatives to commonly used electronic materials, such as Silicon, to reduce the need for shielding and other protective measures, thereby decreasing the weight and cost of space missions.

III-V semiconductor materials, such as Gallium Nitride (GaN), are known for their inherent resilience to temperature swings …

Frequency Division Multiplexing And Random Phasing For Improved Uniformity In Microwave Heating Applications, Logan M. Wilcox, Ali Mirala, Mohammad Tayeb Al Qaseer, Kristen M. Donnell

Electrical and Computer Engineering Faculty Research & Creative Works

Microwave heating has been recently used as an active thermal excitation method in thermography. Within the nondestructive testing and evaluation (NDT&E) realm, this method is referred to as active microwave thermography, or AMT. In AMT, unlike other thermal excitation methods utilized in thermography, microwave heating inherently provides a nonuniform heating pattern. This is a direct result of the radiating antenna used to deliver the energy. This nonuniform pattern may result in defect detection errors (i.e., false positives and/or negatives). To reduce this potential for detection error and improve the overall robustness of the technique, a new electromagnetic system, consisting of …

Neurosymbolic Value-Inspired Ai (Why, What, And How), Amit Sheth, Kaushik Roy

Publications

The rapid progression of Artificial Intelligence (AI) systems, facilitated by the advent of Large Language Models (LLMs), has resulted in their widespread application to provide human assistance across diverse industries. This trend has sparked significant discourse centered around the ever-increasing need for LLM-based AI systems to function among humans as part of human society, sharing human values, especially as these systems are deployed in high-stakes settings (e.g., healthcare, autonomous driving, etc.). Towards this end, neurosymbolic AI systems are attractive due to their potential to enable easy-tounderstand and interpretable interfaces for facilitating valuebased decision-making, by leveraging explicit representations of shared values. …

K-Perm: Personalized Response Generation Using Dynamic Knowledge Retrieval And Persona-Adaptive Queries, Kanak Raj, Kaushik Roy, Vamshi Bonagiri, Priyanshul Govil, Krishnaprasad Thirunarayan, Raxit Goswami, Manas Gaur

Publications

Personalizing conversational agents can enhance the quality of conversations and increase user engagement. However, they often lack external knowledge to tend to a user’s persona appropriately. This is particularly crucial for practical applications like mental health support, nutrition planning, culturally sensitive conversations, or reducing toxic behavior in conversational agents. To enhance the relevance and comprehensiveness of personalized responses, we propose using a two-step approach that involves (1) selectively integrating user personas and (2) contextualizing the response with supplementing information from a background knowledge source. We develop K-PERM (Knowledge-guided PErsonalization with Reward Modulation), a dynamic conversational agent that combines these elements. …

Causal Event Graph-Guided Language-Based Spatiotemporal Question Answering, Kaushik Roy, Alessandro Oltramari, Yuxin Zi, Chathurangi Shyalika, Vignesh Narayanan, Amit Sheth

Publications

Large Language Models have excelled at encoding and leveraging language patterns in large text-based corpora for various tasks, including spatiotemporal event-based question answering (QA). However, due to encoding a text-based projection of the world, they have also been shown to lack a fullbodied understanding of such events, e.g., a sense of intuitive physics, and cause-and-effect relationships among events. In this work, we propose using causal event graphs (CEGs) to enhance language understanding of spatiotemporal events in language models, using a novel approach that also provides proofs for the model’s capture of the CEGs. A CEG consists of events denoted by …

Exploring Alternative Approaches To Language Modeling For Learning From Data And Knowledge, Yuxin Zi, Kaushik Roy, Vignesh Narayanan, Amit Sheth

Publications

Despite their wide applications to language understanding tasks, large language models (LLMs) still face challenges such as hallucinations - the occasional fabrication of information, and alignment issues - the lack of associations with human-curated world models (e.g., intuitive physics or common-sense knowledge). Additionally, the black-box nature of LLMs makes it highly challenging to train them meaningfully in order to achieve a desired behavior. Specifically, the attempt to adjust LLMs’ concept embedding spaces can be highly intractable, which involves analyzing the implicit impact on LLMs’ numerous parameters and the resulting inductive biases. This paper proposes a novel architecture that wraps powerful …

Personalized Bayesian Inference For Explainable Healthcare Management And Intervention, Utkarshani Jaimini, Krishnaprasad Thirunaravan, Maninder Kalra, Robin Dawson, Amit Sheth

Publications

Chronic healthcare conditions such as Asthma re- quires constant monitoring and managing of symptoms and their triggers for better quality of life. Each asthma patient reacts very differently to potential triggers. Hence, there is a need to develop a explainable personalized framework for each patient to capture susceptibility to asthma triggers. We developed a personalized knowledge-based probabilistic model to predict asthma exacerbation for different environmental factors utilizing patient generated health data from pediatric asthma patients. Further, the personalized model provides a metric, called Health Coefficient, to quantify the health of a patient for varying environmental factors. We demonstrate the predictive …

Causal Neuro-Symbolic Ai: A Synergy Between Causality And Neuro-Symbolic Methods, Utkarshani Jaimini, Cory Henson, Amit Sheth

Publications

Causal Neuro-Symbolic AI combines the benefits of causality with Neuro-Symbolic Artificial Intelligence (NeSyAI). More specifically, it (1) enriches NeSyAI systems with explicit representations of causality, (2) integrates causal knowledge with domain knowledge, and (3) enables the use of NeSyAI techniques for causal AI tasks. The explicit causal representation yields insights that predictive models may fail to analyze from observational data. It can also assist people in decision-making scenarios where discerning the cause of an outcome is necessary to choose among various interventions.

Ontolog Summit 2024 Talk Report: Healthcare Assistance Challenges-Driven Neurosymbolic Ai, Kaushik Roy

Publications

Although Artificial Intelligence technology has proven effective in providing healthcare assistance by analyzing health data, it still falls short in supporting decision-making. This deficiency largely stems from the predominance of opaque neural networks, particularly in mental health care AI applications, which raise concerns about their unpredictable and unverifiable nature. This skepticism hinders the transition from information support to decision support. This presentation will explore neurosymbolic approaches that combine neural networks with symbolic control and verification mechanisms. These approaches aim to unlock AI’s full potential by enhancing information analysis and decision-making support for healthcare assistance1.

Neurosymbolic Customized And Compact Copilots, Kaushik Roy, Megha Chakraborty, Yuxin Zi, Manas Gaur, Amit Sheth

Publications

Large Language Models (LLMs) are credible with open-domain interactions such as question answering, summarization, and explanation generation [1]. LLM reasoning is based on parametrized knowledge, and as a consequence, the models often produce absurdities and inconsistencies in outputs (e.g., hallucinations and confirmation biases) [2]. In essence, they are fundamentally hard to control to prevent off-the-rails behaviors, are hard to fine-tune, customize for tailored needs, prompt effectively (due to the “tug-of-war” between external and parametric memory), and extremely resource-hungry due to the enormous size of their extensive parametric configurations [3,4]. Thus, significant challenges arise when these models are required to perform …

Towards Pragmatic Temporal Alignment In Stateful Generative Ai Systems: A Configurable Approach, Kaushik Roy, Yuxn Zi, Amit Sheth

Publications

Temporal alignment in stateful generative artificial intelligence (AI) systems remains an underexplored area, particularly beyond goal-driven approaches in planning. Stateful refers to maintaining a persistent memory or “state” across runs or sessions. This helps with referencing past information to make system outputs more contextual and relevant. This position paper proposes a framework for temporal alignment with several configurable toggles. We present four alignment mechanisms: knowledge graph path-based, neural score-based, vector similarity-based, and sequential process-guided alignment. By offering these interchangeable approaches, we aim to provide a flexible solution adaptable to complex and real-world applications. This paper discusses the potential benefits and …

Control And Optimization Of Energy Storage System In Power Distribution System, Waqas Ur Rehman

Doctoral Dissertations

"The widespread adoption of electric vehicles (EVs) and transportation electrification is encumbered by two chief barriers: i) the limited driving range of EVs in the market today and ii) inadequate fast-charging infrastructure for long-distance trips. Extreme fast charging (XFC) technology can recharge EVs in less than 10 minutes for 200 miles range. Firstly, a novel robust optimization-based mixed integer linear programming model is proposed to size a battery energy storage system (BESS) and PV system in an XFCS. In this part, it is assumed that the sizing and location of the XFCS are known. Secondly, the aforesaid assumption is relaxed, …

Non-Linearity Modeling And Quantifications For Practical Rf Interference Control, Shengxuan Xia

Doctoral Dissertations

"Radio frequency (RF) interference can degrade the receiving sensitivity of antennas (desense problem). It is essential to model the nonlinearity as it is the root-cause of the unwanted frequency components. Understanding the electromagnetic (EM) coupling or radiated emissions is also important.

Nonlinearity causes modulation-involved desense problems, and it consists of two categories: upconvertion of the baseband noise by the transmitting (TX) signal, and the passive intermodulation (PIM) of the transmitting signal itself. The upconvertion caused desense can be modeled and analyzed with the dipole-moment based coupling framework. PIM has been identified as another nonlinear distortion mechanism, specifically in the metallic …

Modeling And Analysis Of Dc-Dc Converters For Power Distribution Networks Design, Junho Joo

Doctoral Dissertations

"Accurate modeling of power distribution networks (PDN) including voltage regulator module (VRM) is critical for high-performance digital systems including low- to high-power applications such as laptops and mobile platforms. As a consolidated end-to-end power source, PDN can be divided into several parts: the VRM to regulate the external voltage source, printed circuit board (PCB) PDN, package PDN, and on-chip PDN. A transient current drawn from the on-die circuitry will produce an instantaneous voltage drop at the bump. The time domain behavior of such a drop and the subsequent recovery is called voltage droop which is strongly associated with the VRM …

Applications Of Computational Intelligence And Data Fusion Techniques For Biomedical Images, Anand Krishnadas Nambisan

Doctoral Dissertations

"The realm of melanoma diagnosis has been significantly advanced by deep learning (DL) techniques, yet the current approaches are not without limitations, including missed diagnoses and the challenge of interpreting these "black box" models. The research is comprised of three studies, each contributing uniquely towards advancing melanoma detection accuracy and interpretability. The first study focuses on improving the detection of specific dermoscopic structures through a deep learning-based segmentation approach, while the second study builds upon this by employing a fusion technique that combines traditional image features with advanced deep learning models. This method significantly improves melanoma detection, particularly in recall …

Accurate And Time Efficient Signal Integrity And Power Integrity Modeling Of High-Speed Digital Systems, Chaofeng Li

Doctoral Dissertations

"Signal integrity (SI) and power integrity (PI) play an important role in the modern high-speed digital system design, which are closely related to the printed circuit board (PCB) dielectric material property, the PCB interconnect performance, and the power delivery network (PDN) on PCB. Generally, the full-wave simulation is used to accurately analyze and evaluate the designed PCB. But full-wave simulation is not a good option for the complex PCB structure with high aspect ratio, for example, PCB vias, and PDN, which will require significant computing time and storage resources. Equivalent circuit models have been developed to efficiently predict the electrical …

Adversarial Transferability And Generalization In Robust Deep Learning, Tao Wu

Doctoral Dissertations

Despite its remarkable achievements across a multitude of benchmark tasks, deep learning (DL) models exhibit significant fragility to adversarial examples, i.e., subtle modifications applied to inputs during testing yet effective in misleading DL models. These meticulously crafted perturbations possess the remarkable property of transferability: an adversarial example that effectively fools one model often retains its effectiveness against another model, even if the two models were trained independently. This research delves into the characteristics influencing the transferability of adversarial examples from three distinct and complementary perspectives: data, model, and optimization. Firstly, from the data perspective, we propose a new method of …

Cross-Temporal Hierarchical Forecast Reconciliation Of Natural Gas Demand, Colin O. Quinn, George F. Corliss, Richard J. Povinelli

Electrical and Computer Engineering Faculty Research and Publications

Local natural gas distribution companies (LDCs) require accurate demand forecasts across various time periods, geographic regions, and customer class hierarchies. Achieving coherent forecasts across these hierarchies is challenging but crucial for optimal decision making, resource allocation, and operational efficiency. This work introduces a method that structures the gas distribution system into cross-temporal hierarchies to produce accurate and coherent forecasts. We apply our method to a case study involving three operational regions, forecasting at different geographical levels and analyzing both hourly and daily frequencies. Trained on five years of data and tested on one year, our model achieves a 10% reduction …

Urban Flood Extent Segmentation And Evaluation From Real-World Surveillance Camera Images Using Deep Convolutional Neural Network, Yidi Wang, Yawen Shen, Behrouz Salahshour, Mecit Cetin, Khan Iftekharuddin, Navid Tahvildari, Guoping Huang, Devin K. Harris, Kwame Ampofo, Jonathan L. Goodall

Civil & Environmental Engineering Faculty Publications

This study explores the use of Deep Convolutional Neural Network (DCNN) for semantic segmentation of flood images. Imagery datasets of urban flooding were used to train two DCNN-based models, and camera images were used to test the application of the models with real-world data. Validation results show that both models extracted flood extent with a mean F1-score over 0.9. The factors that affected the performance included still water surface with specular reflection, wet road surface, and low illumination. In testing, reduced visibility during a storm and raindrops on surveillance cameras were major problems that affected the segmentation of flood extent. …

Automated Flood Depth Estimation On Roadways, Kwame Ampofo, Megan A. Witherow, Alex Glandon, Monibor Rahman, Ahmed Temtam, Mecit Cetin, Khan M. Iftekharuddin

Civil & Environmental Engineering Faculty Publications

Recurrent nuisance flooding is common across many parts of the globe and causes extensive challenges for drivers on the roadways. The prevailing monitoring methods for roadway flooding are costly and not automated or effective. The ubiquity of visual data from cameras and advancements in computing such as deep learning may offer cost-effective methods for automated flood depth estimation on roadways based on reference objects such as cars. However, flood depth estimation faces challenges due to the limited amount of data annotated with water levels and diverse scenes showing reference objects at various scales and perspectives. This study proposes a novel …

Electrospun Pt-Tio₂ Nanofibers Doped With Hpa For Catalytic Hydrodeoxygenation, Amos Taiswa, Randy L. Maglinao, Jessica M. Andriolo, Sandeep Kumar, Jack L. Skinner

Civil & Environmental Engineering Faculty Publications

Electrospinning is utilized to fabricate catalytic nanofiber scaffold for biocrude upgrading in hydrodeoxygenation (HDO) following computational studies suggesting the need for nano-catalysts for efficient HDO conversion and selectivity. Here, Pt-TiO₂ nanofibers are fabricated through electrospinning, followed by wet impregnation with a heteropoly acid (HPA), tungstosilicic acid. Intensive heat treatments were incorporated during and after processes to obtain a HPA doped Pt-TiO₂ nano-catalyst. Catalytic HDO was performed in a batch reactor with phenol as the raw biocrude dissolved in hexadecane. The HPA doped Pt-TiO₂ catalyst demonstrated promising HDO performance of 37.2% conversion and a 78.9% selectivity to oxygen …

Generation Expansion Planning In Isolated Power Systems: A Robust Approach With Dunkelflaute Assessment, Taraneh Ghanbarzadeh, Daryoush Habibi, Asma Aziz

Research outputs 2022 to 2026

Generation expansion planning is vital for decarbonizing power systems and ensuring a reliable and sustainable energy future. Strategically adding new generation and grid capacity is essential for supporting a seamless transition to renewable energy while reducing greenhouse gas emissions. However, achieving the optimal capacity mix of energy resources to ensure network reliability and economic efficiency presents significant challenges, particularly for isolated electricity grids. These challenges are exacerbated during periods of low renewable generation and due to the inherent intermittency of weather-dependent energy resources. This paper presents a comprehensive approach to optimizing long-term expansion planning for an isolated electricity grid, focusing …

Optimal Operation Of An Islanded Hybrid Energy System Integrating Power And Gas Systems, Mehrdad Ghahramani, Daryoush Habibi, Seyyedmorteza Ghamari, Asma Aziz

Research outputs 2022 to 2026

Remote communities and geographically isolated areas require a secure supply of energy. Isolated hybrid energy systems offer an effective and reliable solution for delivering power to these regions. However, shifting to renewable energy sources introduces uncertainty challenges for low-inertia stand-alone systems. In this paper, we propose a two-stage energy management strategy to address the uncertainties of wind generation and load consumption while minimizing operational expenses. Furthermore, the study explores the integration of multi-carrier energy networks, in this case electricity and gas, to enhance the reliability of hybrid energy systems. Two modeling methods are proposed to tackle the uncertainties. First, a …

Blind Source Separation And Denoising Of Underwater Acoustic Signals, Ruba Zaheer, Iftekhar Ahmad, Quoc Viet Phung, Daryoush Habibi

Research outputs 2022 to 2026

Due to the addition of new underwater vessels and other natural noise contributors, the underwater environment is becoming congested and noisy. Undersea monitoring sonobuoys receive multiple mixed acoustic signals from different vessels that need to be separated and identified in the presence of underwater noise (UWN). It is extremely challenging to separate highly correlated acoustic signals from a noisy mixture without prior knowledge of mixing process and propagation channel. Also, in many cases, the separated signals from the noisy mixture doesn’t accurately describe the correct signal. This study proposes a novel multi-stage method to separate underwater acoustic source signals from …

Design Of An Adaptive Robust Pi Controller For Dc/Dc Boost Converter Using Reinforcement-Learning Technique And Snake Optimization Algorithm, Seyyedmorteza Ghamari, Mojtaba Hajihosseini, Daryoush Habibi, Asma Aziz

Research outputs 2022 to 2026

The DC/DC Boost converter exhibits a non-minimum phase system with a right half-plane zero structure, posing significant challenges for the design of effective control approaches. This article presents the design of a robust Proportional-Integral (PI) controller for this converter with an online adaptive mechanism based on the Reinforcement-Learning (RL) strategy. Classical PI controllers are simple and easy to build, but they need to be more robust against a wide range of disturbances and more adaptable to operational parameters. To address these issues, the RL adaptive strategy is used to optimize the performance of the PI controller. Some of the main …

Cross-Layer Performance Evaluation Of C-V2x, Dhruba Sunuwar

College of Graduate Studies: Theses & Dissertations

The evolution of connected vehicles from a distant futuristic concept to an integral part of daily life is indisputable. Vehicle-to-everything communication (V2X) serves as the cornerstone of this transformation, facilitating seamless interaction among vehicles, infrastructure, pedestrians, and networks. However, evaluating V2X system performance proves intricate due to the dynamic nature of vehicles influenced by mobility factors. To address this complexity, we have developed a specialized system-level simulator expressly for evaluating V2X communication performance. Notably, the simulator encompasses (i) intelligent transportation system (ITS) scenarios integrated into a geographical framework and (ii) the capability to assess cross-layer performance spanning physical (PHY) and …