Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons™

Open Access. Powered by Scholars. Published by Universities.®

Series

Discipline
Institution
Keyword
Publication Year
Publication
File Type

Articles 6751 - 6780 of 75310

Full-Text Articles in Engineering

Framework Of Internal Damage Identification In Inhomogeneous Medium Interweaving Wave Scattering Model And Deep Learning, Suyun Ham, Stefan Romanoschi, Yin Chao Wu, Dafnik Saril Kumar David Jan 2024

Framework Of Internal Damage Identification In Inhomogeneous Medium Interweaving Wave Scattering Model And Deep Learning, Suyun Ham, Stefan Romanoschi, Yin Chao Wu, Dafnik Saril Kumar David

Publications

The primary objective of this project is to investigate the framework of internal damage identification in inhomogeneous media (IHM) using deep learning techniques and wave scattering. The study focuses on two main steps: 1) analyzing the wave response pattern in homogeneous media (HM) and 2) characterizing the wave response variation (WRV) in IHM with different aggregate sizes and random distributions. The WRV patterns are then classified and used to predict internal damage using a convolutional neural network (CNN). The accuracy of the finite element (FE) model is verified using laboratory tests with artificial internal crack models of varying depths. The …

Go to article

Identifying Wrong-Way Driving Entry Points On Interstate Highways Using Land-Use Impact Assessment And 911 Calls, Farman Mia, Samer Dessouky Jan 2024

Identifying Wrong-Way Driving Entry Points On Interstate Highways Using Land-Use Impact Assessment And 911 Calls, Farman Mia, Samer Dessouky

Publications

The research aims to provide insight into the initiation event of Wrong-way Driving (WWD) on highways. The intense severity of a WWD accident is encouraging the authorities to install mitigation systems that will ensure safety for motorists on highways. The WWD events are mostly resulting of intoxicated driving, where the unconscious driver takes the wrong way to enter the highway and place other motorists into life-threatening danger. This research attempted to explore from basic knowledge of WWD occurrence to examine the origin and driving philosophy of intoxicated drivers from land-use impact and mathematical modeling point of views. To identify the …

Go to article

Automated Vehicle Impacts On Underserved Populations, Kate Kyung Hyun, Stephen Mattingly, Katie Kam Jan 2024

Automated Vehicle Impacts On Underserved Populations, Kate Kyung Hyun, Stephen Mattingly, Katie Kam

Publications

This research report describes the scenario framework created to determine the potential role automated vehicles (AVs) have in benefiting and adversely impacting the following underserved populations: people with disabilities and impairments (visually, hearing, physically, intellectually) and with autism spectrum disorder, younger and older populations, immigrants, low income, indigenous, rural, female and LGBTQ+, vulnerable road users (cyclists, pedestrians, low speed riders and drivers), and minority races. After presenting a literature review, three chapters explain the 3 modules of the framework: (1) scenario construction, (2) scenario factors, and (3) GIS methodology for evaluating community level AV impacts. Module 1 describes the use …

Go to article

Monotonic And Cyclic Behavior Of High Strength Reinforcing Steel (Hsrs) After High Temperature Exposure, Himan Hojat Jalali, Moein Ebrahimi, Khaled Abuhishmeh, Mohammadamin Soltanianfard Jan 2024

Monotonic And Cyclic Behavior Of High Strength Reinforcing Steel (Hsrs) After High Temperature Exposure, Himan Hojat Jalali, Moein Ebrahimi, Khaled Abuhishmeh, Mohammadamin Soltanianfard

Publications

Conventional reinforced concrete transportation structures in North America often use Grade 40 ksi-60 ksi reinforcing steel. The introduction of high strength reinforcing steel (HSRS) with higher yield strength in the reinforced concrete industry has led to many economic and workability advantages such as construction time saving, reduced labor cost and steel consumption which in turn alleviates congestion of reinforcement, savings in transportation and deliveries that finally results in lower carbon emission. Despite these benefits, many states, including those in Region 6, have not widely adopted the use of higher strength reinforcing steels in practice due to lack of knowledge and …

Go to article

Green Mobility In Texas: Comparative Environmental Impacts And Lifecycle Cost Analysis Of Hybrid, Electric, And Hydrogen Fuel Cell Cars, Raghava R. Kommalapati, Hongbo Du, Md Jobair Bin Alam Jan 2024

Green Mobility In Texas: Comparative Environmental Impacts And Lifecycle Cost Analysis Of Hybrid, Electric, And Hydrogen Fuel Cell Cars, Raghava R. Kommalapati, Hongbo Du, Md Jobair Bin Alam

Publications

Compared to gasoline/diesel cars and battery electric cars (BECs), hydrogen fuel cell cars (HFCCs) are relatively new. Two main advantages of HFCCs over electric vehicles are no special requirements for heavy batteries and long charging time. There is no HFCC in Texas; thus, exploring the use of electricity or hydrogen produced from renewable energies for personal cars and mitigating vehicle emissions is critical for sustaining a long-term decarburization strategy for megacities like Houston and Dallas. This project addressed this critical gap and developed environmental impacts and cost assessments for hybrid gasoline cars, BECs, and HFCCs in Texas under several possible …

Go to article

Smart3pm: Smart Pavement Monitoring, Management, And Maintenance, Damien Stephens, Mena Souliman, Mukul Shirvaikar, Samer Dessouky Jan 2024

Smart3pm: Smart Pavement Monitoring, Management, And Maintenance, Damien Stephens, Mena Souliman, Mukul Shirvaikar, Samer Dessouky

Publications

An application specific multi-platform smartphone application can utilize on-board accelerometer, gyroscope, and GPS sensors, along with software derived signals from the same sensors, to sample vibrational and geolocation datasets to capture pavement distresses such as potholes when mounted in a standardized configuration in a vehicle. Several observations were made with regard to the signals obtained from the accelerometer, gyroscope, and GPS sensors, and it was determined that the raw sensor outputs are capable of sampling statistically significant datasets which can be used to distinguish pavement distress from normal driving conditions. Furthermore, an approximate sensor noise margin is established, and a …

Go to article

Design Of 3d Printable Eco-Concrete By Utilizing Rheology Modifiers For Sustainable Infrastructure, Maryam Hojati, Muhammad Saeed Zafar Jan 2024

Design Of 3d Printable Eco-Concrete By Utilizing Rheology Modifiers For Sustainable Infrastructure, Maryam Hojati, Muhammad Saeed Zafar

Publications

In recent years, 3D printing technology has gained significant momentum across various industries within the construction sector, 3D printing has emerged as a promising technique; however, there are challenges associated with designing suitable construction materials and adjusting their properties for the 3D printing process. One of the key considerations in this regard is the rheological properties, encompassing parameters such as viscosity, yield stress, and thixotropy. These properties play a pivotal role in shaping the characteristics of 3D-printed concrete, both in its fresh and hardened states, including buildability, extrudability, and mechanical performance. Researchers have traditionally relied on chemical admixtures, such as …

Go to article

Development Of A Web Application For Traffic Accident Mapping And Analysis, Susan Bogus Halter, Su Zhang, Arian Golrokh Amin Jan 2024

Development Of A Web Application For Traffic Accident Mapping And Analysis, Susan Bogus Halter, Su Zhang, Arian Golrokh Amin

Publications

It is widely accepted that road traffic safety is a significant public health issue. One of the effective ways to improve road traffic safety is analyzing crash data to understand where traffic accidents occur, identify associated spatial and temporal patterns, and determine causation. In the State of New Mexico, locations of traffic accidents are currently visualized using a variety of static maps. Although these statics maps are easier to create and producers can control how users view the data, users cannot customize these maps to meet their special needs. That being said, new maps need to be created for any …

Go to article

Motorcycle Crash Analysis, Hatim Sharif, Samer Dessouky Jan 2024

Motorcycle Crash Analysis, Hatim Sharif, Samer Dessouky

Publications

The Fatality Analysis Reporting System database shows that, in stark contrast to the 34 percent decline in non-motorcyclist crash–related fatalities, motorcyclist crash–related fatalities were up 86 percent with only three year-to-year declines since 1997, while non-motorcyclist crash–related fatalities had 13 year-to-year declines since 1997. At the national level, the rate of motorcyclist fatalities per vehicle mile traveled is 29 times higher than the rate among passenger car occupants, with overall injury rates approximately five times higher among motorcyclists than passenger car occupants. Given the frequency of motorcycle crashes and their staggering toll in terms of loss of life and economic …

Go to article

Bridge Inspection Training And Enhanced Operations Using Augmented Reality, Fernando Moreu, Ali Mohammadkhorasani, Kaveh Malek Jan 2024

Bridge Inspection Training And Enhanced Operations Using Augmented Reality, Fernando Moreu, Ali Mohammadkhorasani, Kaveh Malek

Publications

This research project focused on the innovative application of Augmented Reality (AR) headsets to enhance bridge inspection processes and inspection training. The study encompassed the visualization of 3D point cloud data, utilized the Eye-Tracking features of AR headsets for inspection quantification, evaluate the applicability of AR in the bridge inspection training and instruction of an AR virtual menu for the in-field bridge inspection. The primary tasks included establishing a database connection for AR headset, designing an AR menu tailored for bridge inspection, devising an evaluation method based on Eye-Tracking capabilities, and integrating AR into bridge inspection training. Once the technical …

Go to article

Deep Reinforcement Learning-Based Digital Twin For Risk Improved Decision Making In Transportation Construction, Yong-Cheol Lee, Anisha Deria Jan 2024

Deep Reinforcement Learning-Based Digital Twin For Risk Improved Decision Making In Transportation Construction, Yong-Cheol Lee, Anisha Deria

Publications

Organizing and overseeing a large number of transportation construction and maintenance projects that generally entail several miles of a worksite are a critical burden for each DOT. In addition, it requires manual monitoring of a project or construction managers to identify a progress status, a work activity, and a safety issue in a job site. Because of the projected huge volume, complexity, significant impacts of future transportation infrastructure projects, it is evident that we are now facing a critical need to create a means of improving the results of work zone management and evaluating their impacts on our society. In …

Go to article

The Effect Of Covid-19 Lockdown On Traffic Crashes In Texas., Hatim Sharif, Samer Dessouky Jan 2024

The Effect Of Covid-19 Lockdown On Traffic Crashes In Texas., Hatim Sharif, Samer Dessouky

Publications

An analysis of traffic patterns during COVID-19 has identified that reduction in the miles traveled has a significant negative correlation with COVID-19 cases and deaths across the USA. Preliminary statistics in the US suggest an increase in fatal crashes over the period of the lockdown in comparison to the same period in previous years. Moreover, while total crashes are down, motor vehicle crashes involving non-motorists became more prevalent. At the same time, non-motorist traffic has increased while motor vehicle traffic and crashes have shifted to the local systems. The main goal of this research is to perform a comprehensive evaluation …

Go to article

Calcined Clays As Alternative Supplementary Cementitious Material And Precursor For Geopolymer Binders In Transportation Infrastructure, Hassan Noorvand, Miladin Radovic, Marwa Hassan, Adriana A. Alvarado, Oscar Huang Jan 2024

Calcined Clays As Alternative Supplementary Cementitious Material And Precursor For Geopolymer Binders In Transportation Infrastructure, Hassan Noorvand, Miladin Radovic, Marwa Hassan, Adriana A. Alvarado, Oscar Huang

Publications

This project aimed to assess the feasibility of using locally sourced calcined kaolinitic clays both as supplementary cementitious materials (SCMs) and as precursors for synthesizing geopolymers (GPs). For SCMs, a comprehensive set of characterizations was conducted, including X-ray fluorescence (XRF), X-ray diffraction (XRD), scanning electron microscopy (SEM), thermogravimetric analysis (TGA), particle size analysis, and loss on ignition (LOI), along with evaluations of concrete properties such as strength activity index (SAI), slump, air content, compressive strength, and surface resistivity. For GPs, compressive strength was tested. The study yielded several key findings: (1) Three types of calcined clays (CCs) were analyzed based …

Go to article

Prediction Of Moisture Resistance Of Polymeric Asphalt Binders Through The Atomic Force Microscopy (Afm) Technique, Zahid Hossain, Ashraf Elsayed, Khaja Sameer Sadat Jan 2024

Prediction Of Moisture Resistance Of Polymeric Asphalt Binders Through The Atomic Force Microscopy (Afm) Technique, Zahid Hossain, Ashraf Elsayed, Khaja Sameer Sadat

Publications

Moisture damage is a significant concern for state Departments of Transportation (DOTs) and other agencies due to its adverse impact on pavement performance as well as longevity. The main focus of the current study project is to quantify, at the molecular level, the interaction between binder and aggregate at the interface level in the form of adhesion forces between bitumen samples and minerals of various chemical compositions. First of all, A thorough review of the literature on moisture degradation in asphalts was conducted. Based on the literature review, a comprehensive project plan and test matrix were created. Binder samples from …

Go to article

Early-Age Strength Monitoring Of Sensor-Embedded 3d Printed Structures, Ali Kazemian, Marwa Hassan, Hassan Noorvand, Gabriel Arce, Kasra Banijamali Jan 2024

Early-Age Strength Monitoring Of Sensor-Embedded 3d Printed Structures, Ali Kazemian, Marwa Hassan, Hassan Noorvand, Gabriel Arce, Kasra Banijamali

Publications

Construction 3D printing (C3DP) is an automated technology that has the potential to reduce the construction time and cost by utilizing different types of robotic systems. Due to the absence of formwork in C3DP, potential excessive water evaporation can cause issues to the freshly-printed structures that are exposed to the ambient curing condition. Moreover, the 3D printed elements should carry the service loads in a short time after printing to provide a load-bearing capacity. Destructive and non-destructive methods are the two types of methods that are being used in the construction industry for quality monitoring. Due to the time-consuming nature …

Go to article

Personalized Bayesian Inference For Explainable Healthcare Management And Intervention, Utkarshani Jaimini, Krishnaprasad Thirunaravan, Maninder Kalra, Robin Dawson, Amit Sheth Jan 2024

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 …

Go to article

Towards Pragmatic Temporal Alignment In Stateful Generative Ai Systems: A Configurable Approach, Kaushik Roy, Yuxn Zi, Amit Sheth Jan 2024

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 …

Go to article

Finops-Driven Cloud Optimization Models For Enterprise Applications, Manikantha Varaprasad Inakollu Jan 2024

Finops-Driven Cloud Optimization Models For Enterprise Applications, Manikantha Varaprasad Inakollu

Computer Science and Engineering Faculty Publications

Cloud computing has revolutionized enterprise IT infrastructure, yet escalating costs and resource inefficiencies threaten to undermine these benefits. This research examines FinOps-driven optimization models that enable organizations to balance cloud performance, cost efficiency, and business value. The study addresses the critical challenge enterprises face in managing cloud expenditures while maintaining operational excellence. Through comprehensive analysis of FinOps principles and practical optimization frameworks, we develop models that integrate financial accountability, technical efficiency, and business alignment. Our research demonstrates that organizations implementing structured FinOps practices achieve 25-40% cost reductions without compromising application performance. The study contributes both theoretical frameworks for understanding cloud …

Go to article

Enhancing Erp Auditability And Compliance Using Permissioned Blockchain, A Framework For Transparent And Immutable Enterprise Resource Planning Systems., Manikantha Varaprasad Inakollu Jan 2024

Enhancing Erp Auditability And Compliance Using Permissioned Blockchain, A Framework For Transparent And Immutable Enterprise Resource Planning Systems., Manikantha Varaprasad Inakollu

Computer Science and Engineering Faculty Publications

Enterprise Resource Planning systems serve as the backbone of modern organizational operations, yet their centralized architecture creates significant challenges for auditability and regulatory compliance. This research proposes a permissioned blockchain framework to enhance ERP auditability by creating immutable, transparent, and traceable records of all system transactions and modifications. The study addresses critical gaps in current ERP systems where transaction histories can be altered, audit trails prove insufficient, and compliance verification remains cumbersome. Through examination of existing ERP limitations and blockchain capabilities, we develop an integrated architecture that maintains operational efficiency while providing cryptographic assurance of data integrity. Our framework employs …

Go to article

Sub-Band Backdoor Attack In Remote Sensing Imagery, Kazi Aminul Islam, Hongyi Wu, Chunsheng Xin, Rui Ning, Liuwan Zhu, Jiang Li Jan 2024

Sub-Band Backdoor Attack In Remote Sensing Imagery, Kazi Aminul Islam, Hongyi Wu, Chunsheng Xin, Rui Ning, Liuwan Zhu, Jiang Li

Electrical & Computer Engineering Faculty Publications

Remote sensing datasets usually have a wide range of spatial and spectral resolutions. They provide unique advantages in surveillance systems, and many government organizations use remote sensing multispectral imagery to monitor security-critical infrastructures or targets. Artificial Intelligence (AI) has advanced rapidly in recent years and has been widely applied to remote image analysis, achieving state-of-the-art (SOTA) performance. However, AI models are vulnerable and can be easily deceived or poisoned. A malicious user may poison an AI model by creating a stealthy backdoor. A backdoored AI model performs well on clean data but behaves abnormally when a planted trigger appears in …

Go to article

Adversarial Training Based Domain Adaptation Of Skin Cancer Images, Syed Qasim Gilani, Muhammad Umair, Maryam Naqvi, Oge Marques, Hee-Cheol Kim Jan 2024

Adversarial Training Based Domain Adaptation Of Skin Cancer Images, Syed Qasim Gilani, Muhammad Umair, Maryam Naqvi, Oge Marques, Hee-Cheol Kim

Electrical & Computer Engineering Faculty Publications

Skin lesion datasets used in the research are highly imbalanced; Generative Adversarial Networks can generate synthetic skin lesion images to solve the class imbalance problem, but it can result in bias and domain shift. Domain shifts in skin lesion datasets can also occur if different instruments or imaging resolutions are used to capture skin lesion images. The deep learning models may not perform well in the presence of bias and domain shift in skin lesion datasets. This work presents a domain adaptation algorithm-based methodology for mitigating the effects of domain shift and bias in skin lesion datasets. Six experiments were …

Go to article

Reevaluating The Paradox: Does Low-Dose Radiation From A-Bombs Affect Lifespan And Cancer Mortality?, Razieh Rashidfar, Zeynab Seyedi Sarhad, Seyed Mohammad Javad Mortazavi, Lembit Sihver Jan 2024

Reevaluating The Paradox: Does Low-Dose Radiation From A-Bombs Affect Lifespan And Cancer Mortality?, Razieh Rashidfar, Zeynab Seyedi Sarhad, Seyed Mohammad Javad Mortazavi, Lembit Sihver

Informatics and Engineering Systems Faculty Publications

No abstract provided.

Go to article

Neurosymbolic Value-Inspired Ai (Why, What, And How), Amit Sheth, Kaushik Roy Jan 2024

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. …

Go to article

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 Jan 2024

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. …

Go to article

Causal Event Graph-Guided Language-Based Spatiotemporal Question Answering, Kaushik Roy, Alessandro Oltramari, Yuxin Zi, Chathurangi Shyalika, Vignesh Narayanan, Amit Sheth Jan 2024

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 …

Go to article

Exploring Alternative Approaches To Language Modeling For Learning From Data And Knowledge, Yuxin Zi, Kaushik Roy, Vignesh Narayanan, Amit Sheth Jan 2024

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 …

Go to article

Tutorial: Knowledge-Infused Artificial Intelligence For Mental Healthcare, Kaushik Roy Jan 2024

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, …

Go to article

Causal Neuro-Symbolic Ai: A Synergy Between Causality And Neuro-Symbolic Methods, Utkarshani Jaimini, Cory Henson, Amit Sheth Jan 2024

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.

Go to article

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

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.

Go to article

Neurosymbolic Customized And Compact Copilots, Kaushik Roy, Megha Chakraborty, Yuxin Zi, Manas Gaur, Amit Sheth Jan 2024

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 …

Go to article

First Prev Next Last