Engineering Commons^™

Proknow: Process Knowledge For Safety Constrained And Explainable Question Generation For Mental Health Diagnostic Assistance, Kaushik Roy, Manas Gaur, Misagh Soltani, Vipula Rawte, Ashwin Kalyan, Amit Sheth

Publications

Current Virtual Mental Health Assistants (VMHAs) provide counseling and suggestive care. They refrain from patient diagnostic assistance because of a lack of training on safety-constrained and specialized clinical process knowledge (Pro-Know). In this work, we define ProKnow as an ordered set of information that maps to evidence-based guidelines or categories of conceptual understanding to experts in a domain. We also introduce a new dataset of diagnostic conversations guided by safety constraints and ProKnow that healthcare professionals use (ProKnow-data). We develop a method for natural language question generation (NLG) that collects diagnostic information from the patient interactively (ProKnow-algo). We demonstrate the …

Ierl: Interpretable Ensemble Representation Learning - Combining Crowdsourced Knowledge And Distributed Semantic Representations, Yuxin Zi, Kaushik Roy, Vignesh Narayanan, Manas Gaur, Amit Sheth

Publications

Large Language Models (LLMs) encode meanings of words in the form of distributed semantics. Distributed semantics capture common statistical patterns among language tokens (words, phrases, and sentences) from large amounts of data. LLMs perform exceedingly well across General Language Understanding Evaluation (GLUE) tasks designed to test a model’s understanding of the meanings of the input tokens. However, recent studies have shown that LLMs tend to generate unintended, inconsistent, or wrong texts as outputs when processing inputs that were seen rarely during training, or inputs that are associated with diverse contexts (e.g., well-known hallucination phenomenon in language generation tasks). Crowdsourced and …

A Semantic Web Approach To Fault Tolerant Autonomous Manufacturing, Fadi El Kalach, Ruwan Wickramarachchi, Ramy Harik, Amit Sheth

Publications

The next phase of manufacturing is centered on making the switch from traditional automated to autonomous systems. Future factories are required to be agile, allowing for more customized production, and resistance to disturbances. Such production lines would be able to reallocate resources as needed and minimize downtime while keeping up with market demands. These systems must be capable of complex decision-making based on parameters such as machine status, sensory/IoT data, and inspection results. Current manufacturing lines lack this complex capability and instead focus on low-level decision-making on the machine level without utilizing the generated data to its full extent. This …

Tutorial - Shodhguru Labs: 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, …

The Troubling Emergence Of Hallucination In Large Language Models--An Extensive Definition, Quantification, And Prescriptive Remediations, Vipula Rawte, Swagata Chakraborty, Agnibh Pathak, Anubhav Sarkar, S.M Towhidul Islam Tonmoy, Aman Chadha, Amit Sheth, Amitava Das

Publications

The recent advancements in Large Language Models (LLMs) have garnered widespread acclaim for their remarkable emerging capabilities. However, the issue of hallucination has parallelly emerged as a by-product, posing significant concerns. While some recent endeavors have been made to identify and mitigate different types of hallucination, there has been a limited emphasis on the nuanced categorization of hallucination and associated mitigation methods. To address this gap, we offer a finegrained discourse on profiling hallucination based on its degree, orientation, and category, along with offering strategies for alleviation. As such, we define two overarching orientations of hallucination: (i) factual mirage (FM) …

Design, Modeling And Analysis Of An Ac-Ac Dual Active Bridge Converter, Kartikeya Jayadurga Prasad Veeramraju

Doctoral Dissertations

"The Solid-State Transformer (SST) is gaining attention as an alternative to conventional iron-core transformers in the power electronic community. The power industry's increasing demands for smaller size, higher efficiency, and greater energy density have made the SST an attractive option. Among various power electronic converter topologies, the Dual Active Bridge (DAB) has become popular for its bidirectional power flow capability and galvanic isolation, primarily in the DC application space. Advancements in semiconductor technologies have introduced new bidirectional switches, opening avenues for novel SST topologies. This research investigates the application of the DAB as a single-stage SST and focuses on advancements …

Introduction Of A Variable Inductance Transformer For The Design Of Resonant Power Converters, Angshuman Sharma

Doctoral Dissertations

"Magnetic integration is a hot topic in power electronics that concerns the use of a transformer's leakage and magnetizing inductances purposefully in isolated power electronic converters, thereby giving the opportunity to save the cost and footprint of any additional inductor. This is of prime interest, especially in CLLLC resonant converters which require up to three inductors. For a complete integration of these inductances, the concept of a variable inductance transformer (VIT) is introduced in this thesis. A VIT is an adaptive magnetic structure that facilitates an easy adjustment of both magnetizing and leakage inductances to meet their desired values. However, …

Geometry-Aware Methodology For Coupling Mechanism Analysis And Radiation Mechanism Analysis, Xu Wang

Doctoral Dissertations

"Due to the wide-band spectrum of digital signals, a variety of noise generators, including microprocessors, liquid crystal displays, digital microphones, high-speed traces, and double-data-rate memory modules, are found in consumer electronics products. Noise generated by digital circuits can couple to the antennas and degrade their sensitivity. Additionally, it also couples to metallic housings or heatsinks and produces a significant amount of emission. In this research, methodologies are presented to analyze the coupling and radiation mechanism in electronic devices.

To investigate the coupling between the distributive geometries in the radio frequency interference (RFI) problem, a mesh-dependent partition-based coupling mechanism analysis method …

Fiber Optic Sensors For Liquid Identifications, Wassana Naku

Doctoral Dissertations

"The fiber optic Fabry-Perot interferometer (FPI) is a widely utilized sensing configuration, offering numerous advantages over conventional electronic sensors, including high accuracy, distributed sensing capabilities, immunity to electromagnetic interference, and compact size. In this study, we propose a remarkably simple fiber optic-tip sensor system combined with machine learning techniques for the identification of pure and volatile organic liquids (VOLs).

A liquid droplet forms an extrinsic FPI (EFPI), with its effective reflectance being a function of the droplet's length. As the droplet evaporates, its length decreases. We conducted immersion tests using optical fiber tip sensors and monitored the time-transient responses of …

Providing A Framework For Seagrass Mapping In United States Coastal Ecosystems Using High Spatial Resolution Satellite Imagery, Megan M. Coffer, David D. Graybill, Peter J. Whitman, Blake A. Schaeffer, Wilson B. Salls, Richard C. Zimmerman, Victoria Hill, Marie Cindy Lebrasse, Jiang Li, Darryl J. Keith, James Kaldy, Phil Colarusso, Gary Raulerson, David Ward, W. Judson Kenworthy

OES Faculty Publications

Seagrasses have been widely recognized for their ecosystem services, but traditional seagrass monitoring approaches emphasizing ground and aerial observations are costly, time-consuming, and lack standardization across datasets. This study leveraged satellite imagery from Maxar's WorldView-2 and WorldView-3 high spatial resolution, commercial satellite platforms to provide a consistent classification approach for monitoring seagrass at eleven study areas across the continental United States, representing geographically, ecologically, and climatically diverse regions. A single satellite image was selected at each of the eleven study areas to correspond temporally to reference data representing seagrass coverage and was classified into four general classes: land, seagrass, no …

Impact Of Atmospheric Correction On Classification And Quantification Of Seagrass Density From Worldview-2 Imagery, Victoria J. Hill, Richard C. Zimmerman, Paul Bissett, David Kohler, Blake Schaeffer, Megan Coffer, Jiang Li, Kazi Aminul Islam

OES Faculty Publications

Mapping the seagrass distribution and density in the underwater landscape can improve global Blue Carbon estimates. However, atmospheric absorption and scattering introduce errors in space-based sensors’ retrieval of sea surface reflectance, affecting seagrass presence, density, and above-ground carbon (AGC_seagrass) estimates. This study assessed atmospheric correction’s impact on mapping seagrass using WorldView-2 satellite imagery from Saint Joseph Bay, Saint George Sound, and Keaton Beach in Florida, USA. Coincident in situ measurements of water-leaving radiance (L_w), optical properties, and seagrass leaf area index (LAI) were collected. Seagrass classification and the retrieval of LAI were compared after empirical line …

Enhancing Traffic Safety In Unpredicted Environments With Integration Of Adas Features With Sensor Fusion In Intelligent Electric Vehicle Platform With Implementation Of Environmental Mapping Technology, David S. Obando Ortegon

College of Graduate Studies: Theses & Dissertations

A major objective on society is to reduce the number of accidents and fatalities on the road for drivers, and pedestrians. Therefore, the automotive engineering field is working on this problem through the development and integration of safety technologies such as advanced driving assistance systems. For this reason, this work was intended to develop and evaluate the performance of different ADAS features and IV technologies under unexpected scenarios. This by the development of safety algorithms applied to the intelligent electric vehicle designed and built in this work, through the use of ADAS sensors based on sensor fusion. Evaluation of AEB, …

Methods On Implementing Radar And Antenna Solutions To Defense And Biomedical Problems, Jalexis E. Vanga Guzman

College of Graduate Studies: Theses & Dissertations

Growing developments in antenna and radio frequency systems have created a strong incentive for researchers to study and apply electromagnetic (EM)-based solutions to modern defense and biomedical problems. The ability to transmit and receive EM waves using antenna systems has not only increased global connectivity, but also increased the need for innovation in antenna size reduction and development of radar systems.

Size reduction techniques have been extensively studied for antennas after the development of electrically small antennas (ESAs) which follow Chu’s limit. ESAs allow the implementation of antennas with much smaller foot-size than traditional full-sized designed while keeping the same …

Efficient Training On Alzheimer’S Disease Diagnosis With Learnable Weighted Pooling For 3d Pet Brain Image Classification, Xin Xing, Muhammad Usman Rafique, Gongbo Liang, Hunter Blanton, Zu Zhang, Chris Wang, Nathan Jacobs, Ai-Ling Lin

Computer Science Faculty Publications (Archived)

Three-dimensional convolutional neural networks (3D CNNs) have been widely applied to analyze Alzheimer’s disease (AD) brain images for a better understanding of the disease progress or predicting the conversion from cognitively impaired (CU) or mild cognitive impairment status. It is well-known that training 3D-CNN is computationally expensive and with the potential of overfitting due to the small sample size available in the medical imaging field. Here we proposed a novel 3D-2D approach by converting a 3D brain image to a 2D fused image using a Learnable Weighted Pooling (LWP) method to improve efficient training and maintain comparable model performance. By …

Data-Integrity Aware Stochastic Model For Cascading Failures In Power Grids, Rezoan Ahmed Shuvro, Pankaz Das, Jamir Shariar Jyoti, Joana M. Abreu, Majeed M. Hayat

Electrical and Computer Engineering Faculty Research and Publications

The reliable operation of power grids during cascading failures is heavily dependent on the interdependencies between the power grid components and the supporting communications and control networks. Moreover, the system operators' expertise in dealing with cascading failures can play a pivotal role during contingencies. In this paper, a dynamical probabilistic model is developed based on Markov-chains, which captures the dynamics of cascading failures in the power grid. Specifically, a previously developed Markov-chain based model is extended to capture the trade-off between the benefits of having a robust communication infrastructure and its vulnerability from data integrity (e.g., cyber-attacks). State-space reduction of …

Energy-Aware Ai-Driven Framework For Edge-Computing-Based Iot Applications, Muhammad Zawish, Nouman Ashraf, Rafay Iqbal Ansari, Steven Davy

Conference papers

The significant growth in the number of Internet of Things (IoT) devices has given impetus to the idea of edge computing for several applications. In addition, energy harvestable or wireless-powered wearable devices are envisioned to empower the edge intelligence in IoT applications. However, the intermittent energy supply and network connectivity of such devices in scenarios including remote areas and hard-to-reach regions such as in-body applications can limit the performance of edge computing-based IoT applications. Hence, deploying state-of-the-art convolutional neural networks (CNNs) on such energy-constrained devices is not feasible due to their computational cost. Existing model compression methods, such as network …

Wind Energy Harvesting And Conversion Systems: A Technical Review, Sinhara M. H. D. Perera, Ghanim Putrus, Michael Conlon, Mahinsasa Narayana, Keith Sunderland

Articles

Wind energy harvesting for electricity generation has a significant role in overcoming the challenges involved with climate change and the energy resource implications involved with population growth and political unrest. Indeed, there has been significant growth in wind energy capacity worldwide with turbine capacity growing significantly over the last two decades. This confidence is echoed in the wind power market and global wind energy statistics. However, wind energy capture and utilisation has always been challenging. Appreciation of the wind as a resource makes for difficulties in modelling and the sensitivities of how the wind resource maps to energy production results …

Impact Of Distributed Energy Resources In Smart Homes And Community-Based Electricity Market, Aziz Saif, Shafi K. Khadem, Michael Conlon, Brian Norton

Articles

Toward the achievement of decarbonised European smart grid network by 2050, the European Commission (EC) has given high importance to its “Clean Energy for all Europeans Package (CEP)” by empowering individuals and groups of consumers to participate in this energy transition. Such energy transition demands residential households to transform the energy-positive smart homes into energy-active smart homes, thus building a smart community. This transformation will expedite if the residential customers are provided with a better choice of supply, access to reliable energy prices, possibility to produce and sell their own electricity with increased transparency and better regulation for more involvement …

Metaheuristic Optimization Techniques Used In Controlling Of An Active Magnetic Bearing System For High-Speed Machining Application, Suraj Suraj, Pabitra Kumar Biswas Pabitra Kumar Biswas, Sukanta Debnath, Anumoy Ghosh, Thanikanti Sudhakar Babu, Hossam Zawbaa, Salah Kemal

Articles

Smart control tactics, wider stability region, rapid reaction time, and high-speed performance are essential requirements for any controller to provide a smooth, vibrationless, and efficient performance of an in-house fabricated active magnetic bearing (AMB) system. In this manuscript, three pre-eminent population-based metaheuristic optimization techniques: Genetic algorithm (GA), Particle swarm optimization (PSO), and Cuckoo search algorithm (CSA) are implemented one by one, to calculate optimized gain parameters of PID controller for the proposed closed-loop active magnetic bearing (AMB) system. Performance indices or, objective functions on which these optimization techniques are executed are integral absolute error (IAE), integral square error (ISE), integral …

Analysis Of Degradation Of Sb2se3 Thin Film Solar Cells Deploying A Time-Dependent Approach Linked With 1d-Amps Simulation, Ming-Lang Tseng, Malek Gassoumi, Nima Ghadiri

Articles

In this paper, we have developed a time-dependent model to study defect growth in the absorber layer of Sb2Se3 thin film solar cells. This model has been integrated with the AMPS-1D simulation platform to investigate the impact of increasing defect density at different positions within the Sb2Se3 layer on the electrical parameters of the solar cell. We adopted the Gloeckler standard model for thin films in AMPS to represent Sb2Se3 materials. The study focuses on tracking the degradation of device performance parameters as donor-like mid-gap states accumulate in the Sb2Se3 layer over time. We monitored the variation of key electrical …

Optical Properties Of Periodically And Aperiodically Nanostructured P-N Junctions, Z. Taliashvili, E Łusakowska E Łusakowska, S. Chusnutdinow, A. Tavkhelidze, L. Jangidze, S. Sikharulidze, Nima Ghadiri, Z. Chubinidze, R. Melkadze

Articles

Recently, semiconductor nanograting layers have been introduced and their optical properties have been studied. Spectroscopic ellipsometry has shown that nanograting significantly modifies the dielectric function of c-Si layers. Photoluminescence spectroscopy reveals the emergence of an emission band with a remarkable peak structure. It has been observed that nanograting also alters the electronic and magnetic properties. In this study, we investigate the quantum efficiency and spectral response of Si p-n junctions fabricated using subwavelength grating layers and aperiodically nanostructured layers.

Simulation And Analysis Of Synthetic Aperture Radar Images, Jonathan Blackledge

Books/Book chapters

The principal model for an image, generated by the interaction of an incident wave field with an inhomogeneous medium, is based on the ‘weak scattering approximation’. This approximation forms the basis for image processing, analysis and image understanding associated with applications over a broad range of frequencies. The physical limitations of such a model are typically overcome by introducing an additional stochastic field term that takes into account those effects that do not conform to the weak scattering approximation, coupled with background ‘system noise’. In this chapter, a solution to the scattering problem is presented, which is based on an …

Does Self-View Mode Generate Video Conferencing Fatigue? An Experiment Using Eeg Signals, Jin Xu, Eoin Whelan, Ann O'Brien, Denis O’Hora

Conference papers

The ability to see or hide one’s own image is a typical feature of video conferencing platforms. This study will conduct an EEG-based neurobiological experiment to determine if the self-view mode generates video conference fatigue and if this differs between males and females. 40 volunteers will participate in a simulated video conference meeting with the self-view mode on and off at different times. In addition, an EEG-based fatigue monitor will be proposed to demonstrate the level of human mental fatigue. The experimental insights will provide direct biological evidence of the impact of video conferencing features on the user experience and …

Co-Design Of An Interactive Wellness Park: Exploring Design Requirements For A Multimodal Outdoor Physical Web Installation With Older Adults, Fatima Badmos

Academic Posters Collection

The global demographic landscape is experiencing a notable shift, characterised by a growing proportion of adults over 60. According to projections, the proportion of individuals aged 60 and above is expected to reach one-sixth of the global population by 2030. Furthermore, by 2050, this demographic is projected to exceed a staggering two billion people. Amidst this shift, there is an urgent need to develop interactive and innovative solutions to address older adults' unique challenges, particularly in outdoor physical activity.

A co-design methodology involving older adults’ participation from the idea generation to the application development process will be adopted to address …

Household Electricity Consumption: A Study On The Role Of Micro-Renewable Energy Systems In Vietnam, Luong Vinh Quoc Duy, Damien Cassells, Jim Hanly

Articles

Although nearly all households in Vietnam have connected to the national grid, electricity shortage in the residential sector is still an issue. One measure of residential electricity shortage is the micro-renewable energy system (micro-RES), but little is known about the drivers for household adoption of such system and whether the presence of a micro-RES can help to reduce household energy consumption. This paper examines the characteristics of households that have adopted a micro-RES and investigates whether the presence of micro-RES would result in a decrease in energy demand by using fixed-effects models. Analysis was carried out on the 2016 and …

(3-Aminopropyl) Triethoxysilane-Based Immobilization Of Pt/Wo3 On A Microfiber Sensor For High Sensitivity Hydrogen Sensing, Qiao Gao, Bin Liu, Juan Liu, Shengpeng Wan, Tao Wu, Xing-Dao He, Ping Lu, Jinhui Yuan, Renli Ma, Zabih Ghassemlooy, Gerald Farrell, Qiang Wu

Articles

A novel high stability hydrogen sensor based on a Pt/WO3 coated single-mode tapered-no-core single-mode (STNCS) fiber interferometer is proposed and experimentally studied. The STNCS structure is treated by (3-Aminopropyl) triethoxysilane (APTES) and then coated with Pt/WO3 nanorods. Compared to the traditional method of using poly (dimethylsiloxane) (PDMS) to adhere Pt/WO3 nanorods on the fiber surface, the APTES modified fiber forms strong covalent bonds with Pt/WO3 with stronger adhesion to the fiber surface, resulting in improved long-term stability. Experimental results show that the sensitivity of the sensor varies from -31.05 nm/% to -4.30 nm/% as the hydrogen concentration increases from 0 …

The Role Of Soc In Ensuring The Security Of Iot Devices: A Review Of Current Challenges And Future Directions, Hajar Bennouri, Abdiaziz Abdi, Iqbal Hossain, Alexandre Pujol

Conference papers

The growing popularity and deployment of Internet of Things (IoT) devices has led to serious security concerns. The integration of a security operations center (SOC) becomes increasingly important in this situation to ensure the security of IoT devices. In this article, we will present a summary of IoT device security issues, their vulnerabilities, a review of current challenges to keep these devices secure, and discuss the role that SOC can bring in protecting IoT devices while considering the challenges encountered and the directions to consider when implementing a reliable SOC for IoT monitoring.

Work In Progress: A Virtual Educational Robotics Coding Club Framework To Improve K-6 Students Emotional Engagement In Stem, Kate Carmody, Julie Booth, Jospehine Bleach, Pramod Pathak, Paul Styles

Conference papers

The growing popularity and deployment of Internet of Things (IoT) devices has led to serious security concerns. The integration of a security operations center (SOC) becomes increasingly important in this situation to ensure the security of IoT devices. In this article, we will present a summary of IoT device security issues, their vulnerabilities, a review of current challenges to keep these devices secure, and discuss the role that SOC can bring in protecting IoT devices while considering the challenges encountered and the directions to consider when implementing a reliable SOC for IoT monitoring.

Detection Of Pause In A Pedestrian’S Movement On A Linear Walkway Using Bluetooth Low Energy Received Signal Strength Indicator, Mayank Parmar, Paula Kelly, Damon Berry

Conference papers

In recent years, Bluetooth Low Energy (BLE) has amassed significant attention in several applications. Its potential, however, remains largely unexplored for understanding pedestrian behaviour. This study focuses on investigating the potential of BLE in identifying pedestrian activity in an outdoor linear walkway. We specifically examine the likelihood of detecting pauses in the movement of pedestrians on a linear walkway using the strength of the signals obtained from a BLE device carried by the pedestrian. To accomplish this, a volunteer pedestrian intentionally pauses at selected points on the chosen walkway for varying predetermined intervals. The obtained data was conditioned using a …

Capturing The Behaviour Of Volunteer Pedestrians In A Newly-Developed University Campus Using A Distributed Array Of Bluetooth Low Energy Devices, Ahlam Al Anbouri, Mayank Parmar, David Powell, Paula Kelly, Niall Holmes Dr., Damon Berry, Lorraine D'Arcy

Conference papers

Contemporary public infrastructure projects emphasise sustainable options that integrate pedestrian routes, leisure facilities and convenient access to public transport systems. It is important to understand the effectiveness of these contemporary designs. In the age of the General Data Protection Regulation (GDPR), there is a need to develop technologybased solutions that collect information about the behaviour of pedestrians in public spaces as they commute and engage in leisure pursuits while simultaneously preserving the privacy of these citizens. Bluetooth Low Energy (BLE), has privacypreserving features that make it worth considering as part of a technology solution for studies of this type. This …