Engineering Commons^™

Detecting Substance Use Disorder Using Social Media Data And Dark Web: Time And Knowledge Aware Study, Usha Lokala, Orchid Chetia Phukan, Triyasha Ghosh Dastidar, Francois Lamy, Raminta Daniulaityte, Amit Sheth

Faculty Publications

Opioid and substance misuse is rampant in the United States today, with the phenomenon known as the "opioid crisis". The relationship between substance use and mental health has been extensively studied, with one possible relationship being: substance misuse causes poor mental health. However, the lack of evidence on the relationship has resulted in opioids being largely inaccessible through legal means. This study analyzes the substance use posts on social media with opioids being sold through crypto market listings. We use the Drug Abuse Ontology, state-of-the-art deep learning, and knowledge-aware BERT-based models to generate sentiment and emotion for the social media …

Left Ventricle Function And Post-Transcriptional Events With Exercise Training In Pigs, Stephanie L. Samani, Shayne C. Barlow, Lisa A. Freeburg, Traci L. Jones, Marlee Poole, Mark A. Sarzynski Ph.D., Faha, Facsm, Michael R. Zile, Tarek Shazly, Francis G. Spinale

Faculty Publications

Background

Standardized exercise protocols have been shown to improve overall cardiovascular fitness, but direct effects on left ventricular (LV) function, particularly diastolic function and relation to post-transcriptional molecular pathways (microRNAs (miRs)) are poorly understood. This project tested the central hypothesis that adaptive LV remodeling resulting from a large animal exercise training protocol, would be directly associated with specific miRs responsible for regulating pathways relevant to LV myocardial stiffness and geometry.

Methods and results

Pigs (n = 9; 25 Kg) underwent a 4 week exercise training protocol (10 degrees elevation, 2.5 mph, 10 min, 5 days/week) whereby LV chamber stiffness (KC) …

Left Ventricle Function And Post-Transcriptional Events With Exercise Training In Pigs, Stephanie L. Samani, Shayne C. Barlow, Lisa A. Freeburg, Traci L. Jones, Marlee Poole, Mark A. Sarzynski Facsm, Michael R. Zile, Tarek Shazly, Francis G. Spinale

Faculty Publications

Background

Standardized exercise protocols have been shown to improve overall cardiovascular fitness, but direct effects on left ventricular (LV) function, particularly diastolic function and relation to post-transcriptional molecular pathways (microRNAs (miRs)) are poorly understood. This project tested the central hypothesis that adaptive LV remodeling resulting from a large animal exercise training protocol, would be directly associated with specific miRs responsible for regulating pathways relevant to LV myocardial stiffness and geometry.

Methods and results

Pigs (n = 9; 25 Kg) underwent a 4 week exercise training protocol (10 degrees elevation, 2.5 mph, 10 min, 5 days/week) whereby LV chamber stiffness (KC) …

Life Cycle Assessment Of Hydrothermal Carbonization: A Review Of Product Valorization Pathways, Andrea Ogunleye, Joseph Flora, Nicole Berge

Faculty Publications

Hydrothermal carbonization (HTC) has the potential to be a sustainable and environmentally beneficial approach for organic waste treatment. It is likely that HTC product use will dictate the viability of large-scale HTC facilities; therefore, understanding the viability and environmental implications associated with HTC product valorization pathways is critical. The overall goal of this review is to gain an understanding of how HTC product valorization is currently being modeled in life cycle assessment studies, and to use such information to assess current research and/or data needs associated with product valorization. To accomplish this, a review of existing HTC literature was conducted …

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 …

Traveling The Pathway To A Culturally Competent Health Care Provider: Incorporating Study Abroad Into Your Curriculum, A L. Johnston Green, C J. Heffner

Clinical Practice in Athletic Training

Introduction: As athletic training employment settings expand and diversify, so does the patient population with whom these healthcare providers interact. This growth furthers the need to ensure that students enrolled in an athletic training program (ATP) accredited by the Commission on Accreditation of Athletic Training Education (CAATE) are educated to provide culturally competent care. Culturally competent care is provided when decisions made diminish the inequalities that may be present in a system based upon a patient’s individual circumstances. Implementing cultural competency education may be integrated into athletic training education in various manners as necessitated by each institution’s unique circumstances. Programs …

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. …

Tutorial: Knowledge-Infused Artificial Intelligence For Mental Healthcare, Kaushik Roy

Publications

Artificial Intelligence (AI) systems for mental healthcare (MHCare) have been ever-growing after realizing the importance of early interventions for patients with chronic mental health (MH) conditions. Social media (SocMedia) emerged as the go-to platform for supporting patients seeking MHCare. The creation of peer-support groups without social stigma has resulted in patients transitioning from clinical settings to SocMedia supported interactions for quick help. Researchers started exploring SocMedia content in search of cues that showcase correlation or causation between different MH conditions to design better interventional strategies. User-level Classification-based AI systems were designed to leverage diverse SocMedia data from various MH conditions, …

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.

A Comprehensive Survey On Rare Event Prediction, Chathurangi Shyalika Jayakody Kankanamalage, Ruwan Wickramarachchi, Amit Sheth

Publications

Rare event prediction involves identifying and forecasting events with a low probability using machine learning (ML) and data analysis. Due to the imbalanced data distributions, where the frequency of common events vastly outweighs that of rare events, it requires using specialized methods within each step of the ML pipeline, i.e., from data processing to algorithms to evaluation protocols. Predicting the occurrences of rare events is important for real-world applications, such as Industry 4.0, and is an active research area in statistics and ML. This paper comprehensively reviews the current approaches for rare event prediction along four dimensions: rare event data, …

Empowering Causal Machine Learning For Large-Scale Manufacturing Pipelines With Knowledge Graphs, Yuxin Zi, Cory Henson, Amit P. Sheth

Faculty Publications

Understanding causal relations within manufacturing pipelines is crucial for key manufacturing tasks such as anomaly detection and root cause analysis. However, existing causal machine learning (causal ML) approaches struggle to scale effectively to the vast number of variables present in manufacturing settings. We advocate for incorporating domain knowledge within the manufacturing pipelines, represented as knowledge graphs (KGs), for designing causal ML methods for large-scale manufacturing problems. Knowledge graphs can encode rich contextual information about the interactions and dependencies between different components and stages of the manufacturing pipeline, providing a structured framework to guide the discovery of causal relationships. By incorporating …

Neurosymbolic Ai Approach To Attribution In Large Language Models, Deepa Tilwani, Revathy Venkataramanan, Amit P. Sheth

Faculty Publications

Attribution in large language models (LLMs) remains a significant challenge, particularly in ensuring the factual accuracy and reliability of the generated outputs. Current methods for citation or attribution, such as those employed by tools like Perplexity.ai and Bing Search-integrated LLMs, attempt to ground responses by providing real-time search results and citations. However, so far, these approaches suffer from issues such as hallucinations, biases, surface-level relevance matching, and the complexity of managing vast, unfiltered knowledge sources. While tools like Perplexity.ai dynamically integrate web-based information and citations, they often rely on inconsistent sources such as blog posts or unreliable sources, which limits …

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. …

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 …

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 …

Proknow: Process Knowledge For Safety Constrained And Explainable Question Generation For Mental Health Diagnostic Assistance In The Age Of Large Language Models, Kaushik Roy, Manas Gaur, Misagh Soltani, Vipula Rawte, Ashwin Allen, Amit P. Sheth

Publications

Current Virtual Mental Health Assistants (VMHAs) primarily offer counseling and suggestive care but do not assist with patient diagnosis due to their lack of training in safety-constrained and specialized clinical process knowledge, referred to as ProKnow. In this work, we define ProKnow as an ordered set of information aligned with evidence-based guidelines or categories of conceptual understanding used by domain experts. We also introduce a new dataset of diagnostic conversations guided by safety constraints and Pro- Know, known as ProKnow-data. We develop a method for natural language question generation (NLG) designed to interactively gather diagnostic information from patients, termed ProKnow-algo. …

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 …

Protecting Zn Anodes By Atomic Layer Deposition Of Zro2 To Extend The Lifetime Of Aqueous Zn-Ion Batteries, Shichen Sun, Yeting Wen, Aiden Billings, Roya Rajabi, Boyu Wang, Kangkang Zhang, Kevin Huang

Faculty Publications

Aqueous rechargeable Zn-ion batteries (ARZIBs) are a newly emerged class of electrochemical cells suited for large-scale stationary energy storage applications due to their unique advantages in safety, cost, and supply chain. To advance ARZIB technology toward commercialization, the corrosion problem of Zn anodes in aqueous electrolytes must be adequately addressed. Here we report our efforts to tackle this issue by using atomic layer deposition (ALD) to coat the Zn anode surface with a protective nanoscale ZrO₂ thin film, collectively denoted as ALD-ZrO₂@Zn in this study. We show the pertinent properties of ALD-ZrO₂@Zn in aqueous Zn-salt …

An Ontology Design Pattern For Representing Causality, Utkarshani Jaimini, Cory Henson, Amit Sheth

Publications

The causal pattern is a proposed ontology design pattern for representing the structure of causal relations in a knowledge graph. This pattern is grounded in the concepts defined and used by the CausalAI community i.e., Causal Bayesian Networks and do-calculus. Specifically, the pattern models three primary concepts: (1) causal relations, (2) causal event roles, and (3) causal effect weights. Two use cases involving a sprinkler system and asthma patients are provided along with their relevant competency questions.

Eeg Functional Connectivity In Infants At Elevated Familial Likelihood For Autism Spectrum Disorder, Christian O'Reilly, Scott Huberty, Stefon Van Noordt, James Desjardins, Nicky Wright, Julie Scorah, Sara Jane Webb, Mayada Elsabbagh, Basis Team

Publications

Background

Many studies have reported that autism spectrum disorder (ASD) is associated with atypical structural and functional connectivity. However, we know relatively little about the development of these differences in infancy.

Methods

We used a high-density electroencephalogram (EEG) dataset pooled from two independent infant sibling cohorts, to characterize such neurodevelopmental deviations during the first years of life. EEG was recorded at 6 and 12 months of age in infants at typical (N = 92) or elevated likelihood for ASD (N = 90), determined by the presence of an older sibling with ASD. We computed the functional connectivity between …

Catalytic Hydrogenation Of Dimethyl Oxalate To Ethylene Glycol Using Silver Based Catalysts On Sba-15, Nicolas Edouard Gleason-Boure

Theses and Dissertations

Ethylene glycol (EG) is an important industrial chemical in the manufacturing of certain plastics. There is growing industrial interest in the production of dimethyl oxalate (DMO) from syngas, which can be hydrogenated to produce EG. Many studies have focused on the catalytic reduction of DMO using copper-based catalysts on silica supports, but fewer studies have been done on the effects of silver for this reaction. This work presents an in-depth study of silver catalysts prepared via various methods including incipient wetness impregnation, charge enhanced dry impregnation, and the use of various organic solvents. Reaction studies show that using pure methanol …

Elastic Sensing Skin For Monitoring Of Concrete Structures, Emmanuel Abiodun Ogunniyi

Theses and Dissertations

Soft elastomeric capacitors (SECs) are emerging as potential low-cost solutions for monitoring cracks and strains in concrete infrastructure, a crucial aspect of structural health monitoring. Effective long-term monitoring of civil infrastructure can reduce the risk of structural failures and potentially reduce the cost and frequency of inspections. However, deploying structural health monitoring (SHM) technologies for bridge monitoring is expensive, especially long-term, due to the density of sensors required to detect, localize, and quantify cracks. Previous research on soft elastomeric capacitors (SEC) has shown their viability for low-cost monitoring of cracks in transportation infrastructure. However, when deployed on concrete for strain …

Simulation-Based Optimization Of A Dc Microgrid: With Machine-Learning-Based Models And Hybrid Meta-Heuristic Algorithms, Tyler Van Deese

Theses and Dissertations

The field of economic dispatch (ED) focuses on optimizing power flow in a power system to minimize costs. It has the potential to significantly enhance system effectiveness, and efficiency, and reduce operating costs. Various techniques have been employed to tackle this problem, each with its own strengths and weaknesses. One promising approach is simulation-based optimization (SBO), which allows for accurate modeling of system interactions and improved representation of expected results. However, SBO requires running numerous simulations to identify an optimal solution, and there is a possibility of not achieving the global optimum. This work aims to address these challenges using …

Design Of A Test Frame And Its Corresponding Test Methods For A Deployable Composite Boom, William Luther Montgomery

Theses and Dissertations

Deployable composite booms (DCB) are an advanced class of support beams growing in applications including solar collectors and solar sails. DCBs can be coiled or folded into a compact footprint and the ability to be deployed, and in some design, concepts redeployed, making them optimal components for aerospace where weight and volume are finite resources. DCBs are a cutting-edge technology that has yet to be perfected with a need for longer booms with increased stiffnesses to accommodate the latest proposed designs. Atomic-6 has proposed a 16-foot boom manufactured using an autoclave process which aims to reach the goal of producing …

Polybenzimidazole Membranes For Electrochemical Applications With Harsh Operating Conditions, Kris Likit-Anurak

Theses and Dissertations

Polybenzimidazole (PBI) membranes are high temperature proton exchange membranes (PEMs) which have advantages such as being able to operate in high temperatures, strong acid environments, and have no need for external humidity during operation. PBI membranes have been demonstrated to work effectively in multiple electrochemical devices, including fuel cells, hydrogen separation pumps, redox flow batteries, and a hybrid sulfur electrolyzer. In this work, para-PBI and densified para-PBI membrane have been used to improve electrochemical performance in harsh operating conditions that are both high temperature (≥120 ̊C) and high acid concentration (≥ 5M). First, we demonstrated the use of para-PBI membranes …

Water Quality Monitoring And Mapping Using Rapidly Deployable Sensor Nodes, Mohamed Abdelwahab

Theses and Dissertations

Efficient and continuous monitoring of water quality parameters plays a pivotal role in responding to pollution incidents and ensuring the safety of both human consumption and ecological resources. This research introduces an affordable and dependable in-situ water quality sensor package designed for seamless continuous monitoring, providing essential data to facilitate informed decision-making in water resource management. The sensor package enables comprehensive on-site assessment of key water characteristics, including pH, temperature, turbidity (measured in NTU), and total dissolved solids (TDS, measured in ppm). Spatial interpolation techniques, specifically Kriging, are employed to extrapolate variable values at unobserved locations based on nearby measurements. …

Design And Fabrication Of High-Resolution Epitaxial 4h-Sic Metal Insulator Semiconductor Detectors, Omerfaruk Karadavut

Theses and Dissertations

In the last two decades, significant strides have been made in the epitaxial film growth of 4H-silicon carbide (4H-SiC), establishing it as a premier wide bandgap material for radiation detection application under harsh environments. This is primarily attributed to its unique combination of physical properties such as high thermal conductivity, wide bandgap, robust breakdown field, and radiation hardness. Metal/4H-SiC epitaxial layer Schottky barrier diodes (SBDs) have emerged as reliable radiation detectors for harsh environments. However, the utilization of thicker epitaxial layer devices encounters challenges due to the minimum achievable doping concentration in 4H-SiC epitaxial layers, necessitating higher bias voltages for …

Load Determination, Strengthening, And Behavior Study Of Prestressed Concrete Channel Bridge Girders In South Carolina, Elhussien Khaled Elbatanouny

Theses and Dissertations

The South Carolina Department of Transportation (SCDOT) is currently engaged in a multi-year effort to assess the structural integrity of its inventory of over 9,000 bridges. This assessment process is expected to result in an increase in the number of bridges that require load postings, repairs, or replacements across South Carolina. This could potentially lead to adverse economic repercussions due to restricted truck routes, bridge closures, repair work, and the need for bridge replacements. To alleviate the escalating costs associated with these challenges, it is imperative to explore methods aimed at reducing the need for load postings and bridge closures …