Electrical and Computer Engineering Commons^™

C 3 An: Custom, Compact And Composite Ai Systems - A Neurosymbolic Approach: 4Th-Generation Evolution Of Intelligent Systems, Amit P. Sheth, Kaushik Roy, Revathy Venkataramanan, Venkatesan Nadimuthu

Publications

Artificial Intelligence (AI) systems continue to evolve rapidly. From the architecture perspective, it is evolving from large, monolithic models trained on massive internet data to complex, multi-component “compound” systems and “agentic” frameworks capable of semi-autonomous decision-making. These systems show immense promise yet face numerous challenges in reliability, consistency, transparency, and alignment with user goals. In this article, we propose Custom, Compact and Composite AI with Neurosymbolic (C3AN) approach, a framework that paves way to 4th-generation of AI that integrates data, knowledge, and human expertise to build robust, intelligent and trustworthy AI systems defined by 14 foundation elements.

Custom emphasizes …

Safe Data-Enabled Control Of Human-In-The-Loop Robotic Manipulator Systems, Ritirupa Dey, Avimanyu Sahoo, Vignesh Narayanan

Publications

Safe control of human-in-the-loop (HIL) robotic manipulators is critical for applications such as assistive robotics, teleoperation in hazardous environments, and collaborative manufacturing. However, this remains challenging due to the lack of a unified framework that simultaneously addresses safety constraints, external disturbances, unmodeled dynamics, and dynamic role switching in the HIL setting. In this paper, we propose a novel NN-driven HIL control framework in which human–robot dyadic interaction occurs through the haptic channel. Using Lyapunov stability analysis, we theoretically show that the proposed NN-based controller ensures accurate joint trajectory tracking, compensates for system uncertainties, and adapts to human inputs modeled as …

Towards Rare Event And Anomaly Prediction In Manufacturing: Bridging Methodological Gaps In Industrial Applications, Chathurangi Shyalika, Renjith Prasad, Ruwan Wickramarachchi, Amit Sheth

Publications

Rare event prediction is critical in industrial applications, including real-world Industry 4.0 applications. These events, defined by their low occurrence frequency, are often difficult to predict due to the skewed data distribution, which complicates modeling and evaluation. In our research, we provide a comprehensive review of current approaches to rare event prediction across four key dimensions: rare event data, data processing techniques, algorithmic approaches, and evaluation methodologies [1]. By analyzing diverse datasets with multiple modalities, including numerical, image, text, and audio, we categorize the primary challenges and present the gaps in current research. Specifically, we present three novel research contributions …

A Benchmark Knowledge Graph Of Driving Scenes For Knowledge Completion Tasks, Ruwan Wickramarachchi, Cory Henson, Amit Sheth

Publications

Knowledge graph completion (KGC) is a problem of significant importance due to the inherent incompleteness in knowledge graphs (KGs). The current approaches for KGC using link prediction (LP) mostly rely on a common set of benchmark datasets that are quite different from real-world industrial KGs. Therefore, the adaptability of current LP methods for real-world KGs and domain-specific ap- plications is questionable. To support the evaluation of current and future LP and KGC methods for industrial KGs, we introduce DSceneKG, a suite of real-world driving scene knowledge graphs that are currently being used across various industrial applications. The DSceneKG is publicly …

Ontology Design Metapattern For Relationtype Role Composition, Utkarshani Jaimini, Ruwan Wickramarachchi, Cory Henson, Amit Sheth

Publications

RelationType is a metapattern that specifies a property in a knowledge graph that directly links the head of a triple with the type of the tail. This metapattern is useful for knowledge graph link prediction tasks, specifically when one wants to predict the type of a linked entity rather than the entity instance itself. The RelationType metapattern serves as a template for future extensions of an ontology with more fine-grained domain information.

Visual Causal Question And Answering With Knowledge Graph Link Prediction, Utkarshani Jaimini, Cory Henson, Amit Sheth

Publications

The ability to answer causal questions is important for any system that requires robust scene under- standing. In this demonstration, we develop a prototype system that leverages our causal link prediction framework, CausalLP. CausalLP framework uses a visual causal knowledge graph and associated knowledge graph embedding for two visual causal question and answering tasks- (i) causal explanation and (ii) causal prediction. In the live demonstration sessions, the participants will be invited to test the efficiency and effectiveness of the system for visual causal question and answering.

Causal Neuro-Symbolic Ai For Root Cause Analysis In Smart Manufacturing, Utkarshani Jaimini, Cory Henson, Amit Sheth

Publications

Root cause analysis is the process of investigating the cause of a failure and providing measures to prevent future failures. It is an active area of research due to the complexities in manufacturing production lines and the vast amount of data that requires manual inspection. We present a combined approach of causal neuro-symbolic AI for root cause analysis to identify failures in smart manufacturing production lines. We have used data from an industry-grade rocket assembly line and a simulation package to demonstrate the effectiveness and relevance of our approach.

Causal Knowledge Graph For Scene Understanding In Autonomous Driving, Utkarshani Jaimini, Cory Henson, Amit Sheth

Publications

The current approaches to autonomous driving focus on learning from observation or simulated data. These approaches are based on correlations rather than causation. For safety-critical applications, like autonomous driving, it’s important to represent causal dependencies among variables in addition to the domain knowledge expressed in a knowledge graph. This will allow for a better understanding of causation during scenarios that have not been observed, such as malfunctions or accidents. The causal knowledge graph, coupled with domain knowledge, demonstrates how autonomous driving scenes can be represented, learned, and explained using counterfactual and intervention reasoning to infer and understand the behavior of …

Sex Differences In Active Avoidance And Neural Circuit Mechanisms In Contextual Fear Generalization, Carly Vincent

Theses and Dissertations

The current studies were aimed to investigate two behavioral hallmarks of anxiety and stress-related disorders, avoidance responses and the over-generalization of fear. In the first set of studies, active avoidance and extinction learning, that parallels exposure therapy in preclinical rodent models, were used. It is known that stress can influence aversive learning and extinction training, which can result in poor extinction retention. However, it is not well understood how the stress response is facilitating extinction resistance in active avoidance learning across sexes. Therefore, the first set of studies aimed to investigate the role of biological sex and glucocorticoid receptor (GR) …

Development Of Avalanche Photo Detector For Uv-C Using Gallium Oxide Material System, Md Ghulam Ghulam Zakir

Theses and Dissertations

This work describes the metal-organic chemical vapor deposition (MOCVD) optimization process for epitaxially grown gallium oxide (Ga2O3) layers, electrical field distribution, and the design for Avalanche Photo Detector (APD). MOCVD is a well-accepted process in the semiconductor industry, as it is well-known for its precise deposition of ultra-thin, high-quality semiconductor layers with extraordinary control over composition and thickness. The choice of Ga2O3 is due to r its distinctive properties of ultra-wide bandgap and low turn-on resistance. Thus, Ga₂O₃-based materials can withstand high voltage and current with the least energy loss, making them an attractive choice for …

Thermal Management Of Power Electronic Devices Using Single Crystal Aln Heat Spreaders, Md Abdullah-Al Mamun

Theses and Dissertations

Due to high critical electric field and saturation velocity, wide bandgap (WBG) III-Nitride semiconductor materials (AlxGa1-xN) and their heterostructures have gone through extensive research in academia and industry for applications requiring high-voltage, high-current, high-frequency, and high-temperature transistor operation. AlGaN/GaN high electron mobility transistor (HEMT) has been commercialized for 650-V power converters, smartphones, PCs, USB wall power outlets, on-board and off-board EV chargers, and numerous other applications. However, AlGaN/GaN HEMTs grown on low-cost sapphire or Si substrates face significant self-heating issues due to the poor thermal conductivity of the substrate. The high thermal resistance (RTH) and heat capacity of the substrates …

Developing A Hierarchical Digital Twin Framework For Dc Microgrid Implementation, Khari Sado

Theses and Dissertations

This research introduces a hierarchical digital twin framework for DC microgrids implementation, particularly those utilized in naval power systems. Unlike traditional digital twins, this hierarchical digital twin structure offers a layered perspective. Hierarchical digital twin design promotes computational efficiency by distributing computational burden across a layered configuration that integrates lower-level digital twin blocks with a system digital twin. The layered approach breaks down complex systems into smaller manageable units that can be examined individually and collectively. Central to this strategy is the adoption of a multi-domain and multi-functional technique through the integration of the digital image framework. This allows the …

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 assistance.

Evaluating The Role Of Data Enrichment Approaches Towards Rare Event Analysis In Manufacturing, Chathurangi Shyalika, Ruwan Wickramarachchi, Fadi El Kalach, Ramy Harik, Amit P. Sheth

Publications

Rare events are occurrences that take place with a significantly lower frequency than more common, regular events. These events can be categorized into distinct categories, from frequently rare to extremely rare, based on factors like the distribution of data and significant differences in rarity levels. In manufacturing domains, predicting such events is particularly important, as they lead to unplanned downtime, a shortening of equipment lifespans, and high energy consumption. Usually, the rarity of events is inversely correlated with the maturity of a manufacturing industry. Typically, the rarity of events affects the multivariate data generated within a manufacturing process to be …

Design And Development Of A Direct Medium Voltage Solar Pv Resonant Inverter, Parthkumar Sureshkumar Bhuvela

Theses and Dissertations

In a grid-tied photovoltaic (PV) system connected to a medium voltage (MV) grid, an inverter is generally employed with a line frequency transformer (LFT) to connect to the grid. These LFTs are large in size and weight, exhibit high cost and losses. In recent studies, the LFTs replaced by are by (high frequency transformer) HFT embedded in DC-DC converters. These DC-DC converters are used to boost voltage levels and DC-AC inverters are employed for MV inversion. This leads to high frequency switching at MV which increases losses in inversion stage. In this study, a novel MV grid-connected solar PV inverter …

Cognitive Manufacturing: Definition And Current Trends, Fadi El Kalach, Ibrahim Yousif, Thorsten Wuest, Amit Sheth, Ramy Harik

Publications

Manufacturing systems have recently witnessed a shift from the widely adopted automated systems seen throughout industry. The evolution of Industry 4.0 or Smart Manufacturing has led to the introduction of more autonomous systems focused on fault tolerant and customized production. These systems are required to utilize multimodal data such as machine status, sensory data, and domain knowledge for complex decision making processes. This level of intelligence can allow manufacturing systems to keep up with the ever-changing markets and intricate supply chain. Current manufacturing lines lack these capabilities and fall short of utilizing all generated data. This paper delves into the …

Ri2ap: Robust And Interpretable 2d Anomaly Prediction In Assembly Pipelines, Chathurangi Shyalika, Kaushik Roy, Renjith Prasad, Fadi El Kalach, Yuxin Zi, Priya Mittal, Vignesh Narayanan, Ramy Harik, Amit Sheth

Publications

Predicting anomalies in manufacturing assembly lines is crucial for reducing time and labor costs and improving processes. For instance, in rocket assembly, premature part failures can lead to significant financial losses and labor inefficiencies. With the abundance of sensor data in the Industry 4.0 era, machine learning (ML) offers potential for early anomaly detection. However, current ML methods for anomaly prediction have limitations, with F1 measure scores of only 50% and 66% for prediction and detection, respectively. This is due to challenges like the rarity of anomalous events, scarcity of high-fidelity simulation data (actual data are expensive), and the complex …

Duality Of Ensemble Systems Through Moment Representations, Vignesh Narayanan, Wei Zhang, Jr-Shin Li

Publications

Controlling large-scale dynamic population systems, known as ensemble control, is a pervasive and essential task in many emerging applications from diverse scientific domains. Previous focuses in the area of ensemble control have been placed on seeking open-loop control strategies due to unavailability of state feedback information for each individual system in the ensemble. In this paper, we develop a foundational framework for analysis and control of ensemble systems with closed feedback control loops. We introduce the notion of ensemble moments and construct moment systems associated with the ensemble systems. By extending the classical moment problem in mathematical analysis and statistics, …

Study Of Interface Charges Between In-Situ Grown Dielectric And Gan/Algan Hfet Structure By Metal-Organic Chemical Vapor Deposition, Muhammad Hassan Tahir, Nifat Jahan, Md Ghulam Zakir

Faculty Publications

The integration of an oxide layer in metal-oxide-semiconductor high electron mobility transistors (MOSHFETs) plays a crucial role in minimizing gate leakage current and enabling wider gate voltage swings. In this study, we present the fabrication and characterization of GaN/AlGaN heterostructure field-effect transistors (HFETs) capped with a Ga₂O₃ dielectric layer. The oxide was deposited via an in-situ process within a single MOCVD reactor without vacuum interruption. Our findings demonstrate that the in-situ capped HFETs exhibit a significantly lower interface charge density of 4 × 10¹² cm⁻² compared to 1 × 10¹³ cm⁻²·eV⁻¹ observed in ex-situ grown counterparts. These results highlight the …

Study Of Indium-Silicon Co-Doped Gallium Oxide For Effective N-Type Doping, Muhammad Hassan Tahir, Nifat Jahan, Md Ghulam Zakir

Faculty Publications

We present the research efforts to achieve effective n-type doping in gallium oxide (Ga2O3), an ultrawide bandgap semiconductor, grown by metal-organic chemical vapor deposition (MOCVD). The application of semiconductors for power electronics requires wide and ultrawide bandgap materials that can be doped to create higher electron (n-type) or hole (p-type) densities. Ga2O3, with a bandgap of 4.9 eV, is an emerging and promising material. The bandgap of Ga2O3 is much higher than other wide bandgap material that have been adopted by or in the process of adoption by the industry for power electronics. However, the doping of Ga2O3 has some …

Gallium Oxide Based Avalanche Photo Detector, Muhammad Hassan Tahir Mr, Nifat Jahan, Md Ghulam Zakir

Faculty Publications

Gallium oxide (Ga₂O₃), an ultrawide bandgap semiconductor with a bandgap of 4.6 eV and a high critical electric field of 10.3 MV/cm, offers strong potential for high-performance avalanche photodetectors (APDs). This project explores the design and characterization of a Ga₂O₃-based APD featuring doped and undoped epitaxial layers optimized for high electric field generation and low thermal conductivity, enabling stable operation in high-temperature environments. Simulation results show a uniform electric field of 1 MV/cm under a 100 V applied bias, while material characterization confirms excellent surface smoothness with a mean roughness of ~1.1 nm and an electron mobility of 21.7 cm²/V·s …

Design Of A Launchable Remote-Controlled Rover And Protective Aeroshell, Matthew Loewer, Colby Weeks, Lake Williams, Jackson Zazzaro

Senior Theses

Planetary rovers, vehicles that can traverse challenging terrain, have excelled in their exploration missions to other celestial bodies. They have been especially suitable for exploring Mars, as rovers such as Opportunity and Perseverance have collected valuable geological, atmospheric, seismic, and magnetic information from the Martian surface. Rovers will remain vital in future space exploration missions, and it is necessary to understand their design and functionality. This paper focuses on the design and prototyping of a miniature rover that can survive the rough Martian terrain while collecting and submitting environmental data for scientific analysis. The design is based off proven Martian …

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 …

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, …

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. …