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

Digital Commons Network™

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

2023

Discipline
Institution
Keyword
Publication
Publication Type
File Type

Articles 37261 - 37290 of 38775

Full-Text Articles in Entire DC Network

Guest Editorial Special Section On The 2022 Ieee International Instrumentation And Measurement Technology Conference, Sergio Rapuano, Kristen M. Donnell, Pawel Niewczas Jan 2023

Guest Editorial Special Section On The 2022 Ieee International Instrumentation And Measurement Technology Conference, Sergio Rapuano, Kristen M. Donnell, Pawel Niewczas

Electrical and Computer Engineering Faculty Research & Creative Works

No abstract provided.

Go to article

A Statistical Shmoo For A Decision Feedback Equalizer (Dfe), Junyong Park, Donghyun Kim Jan 2023

A Statistical Shmoo For A Decision Feedback Equalizer (Dfe), Junyong Park, Donghyun Kim

Electrical and Computer Engineering Faculty Research & Creative Works

This article proposes a statistical shmoo for a Decision Feedback Equalizer (DFE). A statistical shmoo shows a Bit-Error Rate (BER) distribution of a system depending on conditions such as a threshold voltage and sampling time. The previous statistical eye diagram can be converted to a statistical shmoo except for the case of a DFE. In the shmoo, rows and columns represent different threshold voltages and sampling times, respectively. Thus, the DFE operation also depends on each row and column. Furthermore, a DFE may have error propagations because of substantial noise. Therefore, this article proposes a statistical shmoo for an ideal …

Go to article

Accelerated Statistical Eye Diagram Estimation Method For Efficient Signal Integrity Analysis, Junyong Park, Youngwoo Kim, Donghyun Kim Jan 2023

Accelerated Statistical Eye Diagram Estimation Method For Efficient Signal Integrity Analysis, Junyong Park, Youngwoo Kim, Donghyun Kim

Electrical and Computer Engineering Faculty Research & Creative Works

This article proposes an accelerated statistical eye diagram estimation method for efficient signal integrity (SI) analysis. An eye diagram is a critical metric in the SI analysis, however obtaining an eye diagram is time-consuming in simulation. The required time might be a few weeks depending on the complexity. Because the eye diagram is obtained by superposition of the received waveforms. Statistical eye diagram estimation methods were proposed to make the eye diagram acquisition efficient, however, it still has a limited improvement due to a large number of convolution operations. To address this limitation, the proposed method includes two approaches: (i) …

Go to article

Multiple Uav-Lidar Placement Optimization Under Road Priority And Resolution Requirements, Zachary Osterwisch, Omar Rinchi, Ahmad Alsharoa, Hakim Ghazzai, Yehia Massoud Jan 2023

Multiple Uav-Lidar Placement Optimization Under Road Priority And Resolution Requirements, Zachary Osterwisch, Omar Rinchi, Ahmad Alsharoa, Hakim Ghazzai, Yehia Massoud

Electrical and Computer Engineering Faculty Research & Creative Works

An unmanned aerial vehicle (UAV) integrated with the remote sensing technology of light detection and ranging (LiDAR) can provide accurate and real-time road traffic information. In this paper, we propose to equip UAVs with LiDAR sensors for Intelligent Transportation Systems (ITS) applications. The goal is to find the optimal 3D placement of multiple UAV-LiDAR (ULiDs) for a given road segmentation. We formulate an optimization problem to find the optimal placement such that the road coverage efficiency is maximized. The optimization problem is constrained by notable ULiD specifications such as field-of-view (FoV), point-cloud density, geographic information system (GIS) location, and road …

Go to article

Implementing The Fast Full-Wave Electromagnetic Forward Solver Using The Deep Convolutional Encoder-Decoder Architecture, He Ming Yao, Lijun Jiang, Michael Ng Jan 2023

Implementing The Fast Full-Wave Electromagnetic Forward Solver Using The Deep Convolutional Encoder-Decoder Architecture, He Ming Yao, Lijun Jiang, Michael Ng

Electrical and Computer Engineering Faculty Research & Creative Works

In this communication, a novel deep learning (DL)-based solver is proposed for the electromagnetic forward (EMF) process. It is based on the complex-valued deep convolutional neural networks (DConvNets) comprising an encoder network and a corresponding decoder network with pixel-wise regression layer. The encoder network takes the incident EM wave and the contrast (permittivity) distribution of the object as the input. It channels the processed data into the corresponding decoder network to predict the total EM field due to the scatter of the input incident EM wave. The training of the proposed DConvNets is done using the simple synthetic dataset. Due …

Go to article

Experimental Study For Improving The Productivity Of Laser Foil Printing, Tunay Turk, Ming-Chuan Leu Jan 2023

Experimental Study For Improving The Productivity Of Laser Foil Printing, Tunay Turk, Ming-Chuan Leu

Mechanical and Aerospace Engineering Faculty Research & Creative Works

This Study Aims to Improve the Productivity of Laser Foil Printing (LFP), Which is a Foil-Based Metal Additive Manufacturing (AM) Process. LFP Uses a Dual-Laser System to Fabricate a 3-Dimensional Part in a Layered Fashion by Performing Four Steps in Each Layer: Spot Welding, Pattern Welding, Contour Cutting, and Edge Polishing, All of Which Performed by Use of Lasers. We Experimentally Examined the Welding and Polishing Steps in This Study to Enhance LFP Productivity. the Jump Speed, Dwelling Duration, and Weld Path of Spot Welding and the Line Welding Speed and Wait Time between Weld Lines of Pattern Welding Are …

Go to article

Detection Of Surface Cracks In Metals Using Microwave And Millimeter-Wave Nondestructive Testing Techniques-A Review, Mohamed A. Abou-Khousa, Mohammed Saif Ur Rahman, Kristen M. Donnell, Mohammad Tayeb Al (Tayeb) (Al) Qaseer Jan 2023

Detection Of Surface Cracks In Metals Using Microwave And Millimeter-Wave Nondestructive Testing Techniques-A Review, Mohamed A. Abou-Khousa, Mohammed Saif Ur Rahman, Kristen M. Donnell, Mohammad Tayeb Al (Tayeb) (Al) Qaseer

Electrical and Computer Engineering Faculty Research & Creative Works

Integrity Assessment of Metallic Structures Requires Inspection Tools Capable of Detecting and Evaluating Cracks Reliably. to This End, Many Microwave and Millimeter-Wave Nondestructive Testing and Evaluation (NDT&E) Methods Have Been Developed and Applied Successfully in the Past. Detection of Fatigue Cracks with Widths Less Than 5 Μ M using Noncontact Microwave-Based Inspection Methods Was Demonstrated in the 1970s. Since their Introduction, These Methods Have Evolved Considerably Toward Enhancing the Detection Sensitivity and Resolution. Undertaking Key Application Challenges Has Attracted Considerable Attention in the Past Three Decades and Led to the Development of the Near-Field Techniques for Crack Detection. to Address …

Go to article

A Throughput Fast Measurement Method For Two-Antenna Equipped Wireless Mimo Terminals, Penghui Shen, Quan Yu, Daryl G. Beetner, Yihong Qi Jan 2023

A Throughput Fast Measurement Method For Two-Antenna Equipped Wireless Mimo Terminals, Penghui Shen, Quan Yu, Daryl G. Beetner, Yihong Qi

Electrical and Computer Engineering Faculty Research & Creative Works

According to the Third Generation Partnership Project Specification, a Period of 8-12.8 H is Required to Evaluate the Multiple-Input-Multiple-Output (MIMO) Performance of a Wireless Terminal for a Single Frequency Point and Channel Model Combination. the Following Article Proposes a Semi-Simulation, Semi-Measurement-Based MIMO throughput Modeling Scheme Which Can Reduce the 8-12.8-H Measurement Time to 40-60 Min, Corresponding to More Than a Ten Times Improvement of the Test Efficiency, Without Loss of the Test Accuracy.

Go to article

Mixed-Input Learning For Multi-Point Landing Guidance With Hazard Avoidance Part Ii: Learning-Based Guidance Algorithm, Sixiong You, Chaoying Pei, Vinay Kenny, Ran Dai, Jeremy R. Rea Jan 2023

Mixed-Input Learning For Multi-Point Landing Guidance With Hazard Avoidance Part Ii: Learning-Based Guidance Algorithm, Sixiong You, Chaoying Pei, Vinay Kenny, Ran Dai, Jeremy R. Rea

Mechanical and Aerospace Engineering Faculty Research & Creative Works

This paper investigates the three-dimensional (3D) multi-point landing guidance (MLG) problem with hazard avoidance by developing a mixed-input learning-based method to achieve precise and fuel-efficient planetary landing in future Mars missions. Specifically, we aim to find a safe, fuel-efficient landing point and generate a fuel-optimal trajectory simultaneously in real-time. First, by introducing binary variables, the MLG problem is formulated as an optimal control problem with quadratic constraints. Then, by formulating the Hamiltonian function, the necessary conditions of optimality for the MLG problem are obtained, where the critical parameters are identified to represent the complete optimal solution. After that, to find …

Go to article

A Machine Learning Approach To Support Neuromorphic Device Design And Microfabrication, Abdi Yamil Vicenciodelmoral, Md Mehedi Hasan Tanim, Feng Zhao, Xinghui Zhao Jan 2023

A Machine Learning Approach To Support Neuromorphic Device Design And Microfabrication, Abdi Yamil Vicenciodelmoral, Md Mehedi Hasan Tanim, Feng Zhao, Xinghui Zhao

Electrical and Computer Engineering Faculty Research & Creative Works

Neuromorphic chips provide a potential solution for sustainable computing, as they attempt to mimic the neuronal architectures in human brain and show great potentials in reducing energy consumption in the order of magnitude and also improve the computational performance. However, the fabrication process for neuromorphic chips is costly and currently based on trial-and-error, which adds complexity to the design process. In this paper, we address these challenges by designing and developing machine learning guided microfabrication process for Resistive Random Access Memory (RRAM), which is a key device in neuromorphic chips. Specifically, our research makes the following contributions: 1) we successfully …

Go to article

Graduated Driver Licensing Program, Jeeyen Koo, Andrew Martin, Jennifer Walton Jan 2023

Graduated Driver Licensing Program, Jeeyen Koo, Andrew Martin, Jennifer Walton

Kentucky Transportation Center Research Report

To address challenges related to teen driver safety, Kentucky adopted a simple graduated driver licensing (GDL) program in 1996 and further expanded it in 2006 by adding an intermediate licensing phase, requirements for supervised practice driving, and instituting restrictions on passenger age. Despite GDL programs having been adopted throughout the US, young drivers (ages 16 – 20) continue to be overrepresented in fatal crashes. In 2019, despite this segment making up roughly 5.3 percent of licensed drivers it accounted for 11.5 percent of fatal vehicle crashes (Kentucky recorded 732 crash fatalities, of which 73 involved young drivers). Although teen driver …

Go to article

2+1 Roadway Design Guidance Update, Jeff Jasper, Jeff Wolfe, Robin Baskette, Paul Ross, Chris Van Dyke Jan 2023

2+1 Roadway Design Guidance Update, Jeff Jasper, Jeff Wolfe, Robin Baskette, Paul Ross, Chris Van Dyke

Kentucky Transportation Center Research Report

The frequency and severity of crashes on rural two-lane roadways have increased in the US relative to other road types. This trend can be explained by the growing number of vehicles, higher speeds, narrow shoulders, and vehicle mixes. One solution for improving traffic flow and safety outcomes on rural two-lane roadways is to adopt a 2+1 design, which confers the benefits of four-lane highways but at a lower cost. Transportation agencies throughout Europe — and increasingly the US — have seen good results from 2+1 layouts. Crash data from Sweden, Germany, Finland, and Denmark reveal better safety outcomes following the …

Go to article

Pedestrian And Bicycle Improvement Scoring Method For Shift–2024, Nikiforos Stamatiadis, Daria Korostina, Teng Wang, Reginald Souleyrette Jan 2023

Pedestrian And Bicycle Improvement Scoring Method For Shift–2024, Nikiforos Stamatiadis, Daria Korostina, Teng Wang, Reginald Souleyrette

Kentucky Transportation Center Research Report

State transportation agencies have limited funding to deliver multimodal transportation programs that address the needs of all users. To allocate project funding in an impartial and objective manner, many agencies have adopted data-driven scoring systems that are used to evaluate the merits of proposed capital improvement projects. The Kentucky Transportation Cabinet introduced the Strategic Highway Investment Formula for Tomorrow (SHIFT) for this purpose. Until now SHIFT, has evaluated projects based five core variables — congestion, safety, benefit-cost ratio, asset management, economic growth. To address local needs, SHIFT has also allocated points that Area Development Districts, metropolitan planning organizations, and Cabinet …

Go to article

Electron Beam Treatment For The Removal Of 1,4-Dioxane In Water And Wastewater, Robert Pearce, Xi Li, John Vennekate, Gianluigi Ciovati, Charles Bott Jan 2023

Electron Beam Treatment For The Removal Of 1,4-Dioxane In Water And Wastewater, Robert Pearce, Xi Li, John Vennekate, Gianluigi Ciovati, Charles Bott

Electrical & Computer Engineering Faculty Publications

Electron beam (e-beam) treatment uses accelerated electrons to form oxidizing and reducing radicals when applied to water without the use of external chemicals. In this study, electron beam treatment was used to degrade 1,4-dioxane in several water matrices. Removal improved in the progressively cleaner water matrices and removals as high as 94% to 99% were observed at a dose of 2.3 kGy in secondary effluent. 1,4-dioxane removal was confirmed to be primarily through hydroxyl radical oxidation. The calculated electrical energy per order was found to be 0.53, 0.26, and 0.08 kWh/m3/order for secondary effluent (Avg. total organic carbon …

Go to article

Comparison Of Machine Learning Methods For Classification Of Alexithymia In Individuals With And Without Autism From Eye-Tracking Data, Furkan Iigin, Megan A. Witherow, Khan M. Iftekharuddin Jan 2023

Comparison Of Machine Learning Methods For Classification Of Alexithymia In Individuals With And Without Autism From Eye-Tracking Data, Furkan Iigin, Megan A. Witherow, Khan M. Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Alexithymia describes a psychological state where individuals struggle with feeling and expressing their emotions. Individuals with alexithymia may also have a more difficult time understanding the emotions of others and may express atypical attention to the eyes when recognizing emotions. This is known to affect individuals with Autism Spectrum Disorder (ASD) differently than neurotypical (NT) individuals. Using a public data set of eye-tracking data from seventy individuals with and without autism who have been assessed for alexithymia, we train multiple traditional machine learning models for alexithymia classification including support vector machines, logistic regression, decision trees, random forest, and multilayer perceptron. …

Go to article

High Figure Of Merit Spin Polarized Electron Sources Grown Via Mocvd, Benjamin Belfore, Adam Masters, Deewakar Poudel, Greg Blume, Stephen Polly, Erdong Wang, Seth M. Hubbard, Marcy Stutzman, Joseph M. Grames, Matt Poelker, Matt Grau, Sylvain Marsillac Jan 2023

High Figure Of Merit Spin Polarized Electron Sources Grown Via Mocvd, Benjamin Belfore, Adam Masters, Deewakar Poudel, Greg Blume, Stephen Polly, Erdong Wang, Seth M. Hubbard, Marcy Stutzman, Joseph M. Grames, Matt Poelker, Matt Grau, Sylvain Marsillac

Electrical & Computer Engineering Faculty Publications

Spin polarized photocathodes are key to the future operation of electron accelerators such as the ones at Thomas Jefferson National Accelerator Facility and Brookhaven National Laboratory. Currently, these photocathodes come in short supply due to limited production by molecular beam epitaxy. By developing a process to implement similar structures using metal organic chemical vapor deposition, the availability of these devices can be increased. In this paper, we detail the implementation of recent photocathode advancements via metal organic chemical vapor deposition process and show an improvement in both polarization and quantum efficiency of our devices compared to those fabricated via molecular …

Go to article

Prediction Of Dynamic Mechanical Behaviors Of Coral Concrete Under Different Corrosive Environments And Its Enhancement Mechanism, Jingjie Wei, Boyuan Cheng, Lixiao Li, Wu Jian Long, Kamal Khayat Jan 2023

Prediction Of Dynamic Mechanical Behaviors Of Coral Concrete Under Different Corrosive Environments And Its Enhancement Mechanism, Jingjie Wei, Boyuan Cheng, Lixiao Li, Wu Jian Long, Kamal Khayat

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

The marine structures are usually exposed to dynamic loadings within short periods and chemical attacks, resulting in severe dynamical damage or failure to concrete structures. The study of the time-dependent changes in the dynamic mechanical behavior of coral concrete under different corrosive environments and low-frequency waves is limited. For the safety and reliable use of coral concrete in the marine environment, different corrosion environments (chloride ions, sulfate ions, and mixed chloride-sulfate ions) and low-frequency waves (0.5–2.0 Hz) were designed to evaluate the dynamic properties of concrete. A model considering the effect of corroded age is formulated to predict the damping …

Go to article

Key Factors Affecting Labor Productivity In Offsite Construction Projects, Rayan H. Assaad, Islam H. El-Adaway, Makarand Hastak, Kim Lascola Needy Jan 2023

Key Factors Affecting Labor Productivity In Offsite Construction Projects, Rayan H. Assaad, Islam H. El-Adaway, Makarand Hastak, Kim Lascola Needy

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Offsite construction has been shown to possess many advantages and benefits in dealing with the construction industry's challenges, which include poor labor productivity. Nevertheless, all previous productivity-related research studies have focused mainly on factors impacting labor productivity in traditional stick-built construction methods. This paper filled this knowledge gap by following a multistep interrelated research methodology. First, a research team of 19 construction professionals and academics developed and distributed an industry survey to (1) quantify the likelihood of occurrence and relative impact of risk factors that adversely impact labor productivity in offsite construction projects; (2) identify and prioritize key risk factors …

Go to article

Identifying Design-Build Decision-Making Factors And Providing Future Research Guidelines: Social Network And Association Rule Analysis, Ramy Khalef, Islam H. El-Adaway Jan 2023

Identifying Design-Build Decision-Making Factors And Providing Future Research Guidelines: Social Network And Association Rule Analysis, Ramy Khalef, Islam H. El-Adaway

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

There is a dire need to rebuild existing infrastructure with strategic and efficient methods. Design-build (DB) becomes a potential solution that provides fast-tracked delivery as a more time and cost-efficient project delivery method. Past research studied factors influencing DB but without providing a holistic analytic approach. This paper fills this knowledge gap. First, a systematic literature review is performed using the preferred reporting items for systematic reviews and meta-analyses techniques, and a set of factors affecting DB projects are then identified and clustered, using k-means clustering, based on the whole literature discussions. Second, a graph theory approach, social network analysis …

Go to article

Assessing The Predictive Capability Of The Nno Ballistic Limit Equation For Low-Density Projectile Impact, William P. Schonberg Jan 2023

Assessing The Predictive Capability Of The Nno Ballistic Limit Equation For Low-Density Projectile Impact, William P. Schonberg

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

The design of nearly all Earth-orbiting spacecraft includes some sort of added shielding that protects the spacecraft against impacts by meteoroids and orbital debris. The effectiveness of the shielding is typically assessed using ballistic limit equations (BLEs) that are developed using data from high-speed impact tests on key spacecraft components and elements. These equations predict whether or not a particular system or structural element will sustain a critical failure following a specific impact event. As such, they are essential components of spacecraft system design as well as any quantitative spacecraft risk assessments that may need to be performed as part …

Go to article

Densifying Hydration Products Of Alite By A Bio-Inspired Admixture, Yi Fang, Jialai Wang, Liang Wang, Xin Qian, Xiaodong Wang, Wenyu Liao, Peiyuan Chen, Hongyan Ma Jan 2023

Densifying Hydration Products Of Alite By A Bio-Inspired Admixture, Yi Fang, Jialai Wang, Liang Wang, Xin Qian, Xiaodong Wang, Wenyu Liao, Peiyuan Chen, Hongyan Ma

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

A bio-inspired, plant-derived polyphenol, tannic acid (TA) was identified as a renewable admixture to improve the compressive strength of concretes. Aiming to understand the underlying mechanism responsible for this strength improvement, this study examines how TA mediates the hydration of tricalcium silicate (alite). Experimental study shows that TA can form complex with calcium ions through chelating, retarding the hydration of the alite and changing of the hydration products. Particularly, X-ray diffraction analysis shows that TA makes calcium hydroxide preferentially grow on the [0 0 1] face. Fourier-transform infrared spectroscopy and 29Si MAS NMR results reveal that the mean chain length …

Go to article

Comparative Analysis Of Gas Versus Electric Demand In Tiny House Communities For The Homeless, Christopher D. Beveridge Jan 2023

Comparative Analysis Of Gas Versus Electric Demand In Tiny House Communities For The Homeless, Christopher D. Beveridge

Cal Poly Humboldt theses and projects

Housing insecurity affects many communities. Because they can provide private and dignified spaces for living at low cost, tiny houses have become prominent in discussion about affordable housing. This project assesses whether electric or natural gas space heating provides the most cost-effective option for a tiny house in Arcata, California. Drawing from a comparative analysis between two tiny house communities for the homeless (THCHs), Home Yard Cottages in Spokane, Washington and Opportunity Village in Eugene, Oregon, this project offers recommendations for the eventual development of a THCH in Arcata. Comparison of energy bills from the THCHs with historical weather data …

Go to article

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 Jan 2023

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 …

Go to article

Ierl: Interpretable Ensemble Representation Learning - Combining Crowdsourced Knowledge And Distributed Semantic Representations, Yuxin Zi, Kaushik Roy, Vignesh Narayanan, Manas Gaur, Amit Sheth Jan 2023

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 …

Go to article

Knowledge Graph Guided Semantic Evaluation Of Language Models For User Trust, Kaushik Roy, Tarun Garg, Vedant Palit, Yuxin Zi, Vignesh Narayanan, Amit Sheth Jan 2023

Knowledge Graph Guided Semantic Evaluation Of Language Models For User Trust, Kaushik Roy, Tarun Garg, Vedant Palit, Yuxin Zi, Vignesh Narayanan, Amit Sheth

Publications

A fundamental question in natural language processing is - what kind of language structure and semantics is the language model capturing? Graph formats such as knowledge graphs are easy to evaluate as they explicitly express language semantics and structure. This study evaluates the semantics encoded in the self-attention transformers by leveraging explicit knowledge graph structures. We propose novel metrics to measure the reconstruction error when providing graph path sequences from a knowledge graph and trying to reproduce/reconstruct the same from the outputs of the self-attention transformer models. The opacity of language models has an immense bearing on societal issues of …

Go to article

Cook-Gen: Robust Generative Modeling Of Cooking Actions From Recipes, Revathy Venkataramanan, Kaushik Roy, Kanak Ray, Renjith Prasad, Yuxin Zi, Vignesh Narayanan, Amit Sheth Jan 2023

Cook-Gen: Robust Generative Modeling Of Cooking Actions From Recipes, Revathy Venkataramanan, Kaushik Roy, Kanak Ray, Renjith Prasad, Yuxin Zi, Vignesh Narayanan, Amit Sheth

Publications

As people become more aware of their food choices, food computation models have become increasingly popular in assisting people in maintaining healthy eating habits. For example, food recommendation systems analyze recipe instructions to assess nutritional contents and provide recipe recommendations. The recent and remarkable successes of generative AI methods, such as auto-regressive large language models, can lead to robust methods for a more comprehensive understanding of recipes for healthy food recommendations beyond surface-level nutrition content assessments. In this study, we explore the use of generative AI methods to extend current food computation models, primarily involving the analysis of nutrition and …

Go to article

Acm Web Conference 2023, Usha Lokala, Kaushik Roy, Utkarshani Jaimini, Amit Sheth Jan 2023

Acm Web Conference 2023, Usha Lokala, Kaushik Roy, Utkarshani Jaimini, Amit Sheth

Publications

Improving the performance and explanations of ML algorithms is a priority for adoption by humans in the real world. In critical domains such as healthcare, such technology has significant potential to reduce the burden on humans and considerably reduce manual assessments by providing quality assistance at scale. In today’s data-driven world, artificial intelligence (AI) systems are still experiencing issues with bias, explainability, and human-like reasoning and interpretability. Causal AI is the technique that can reason and make human-like choices making it possible to go beyond narrow Machine learning-based techniques and can be integrated into human decision-making. It also offers intrinsic …

Go to article

Tutorial - Shodhguru Labs: Knowledge-Infused Artificial Intelligence For Mental Healthcare, Kaushik Roy Jan 2023

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, …

Go to article

Tutorial - Shodhguru Labs: Optimization And Hyperparameter Tuning For Neural Networks, Kaushik Roy Jan 2023

Tutorial - Shodhguru Labs: Optimization And Hyperparameter Tuning For Neural Networks, Kaushik Roy

Publications

Neural networks have emerged as a powerful and versatile class of machine learning models, revolutionizing various fields with their ability to learn complex patterns and make accurate predictions. The performance of neural networks depends significantly on the appropriate choice of hyperparameters, which are critical factors governing their architecture, regularization, and optimization techniques. As the demand for high-performance neural networks grows across diverse applications, the need for efficient optimization and hyperparameter tuning methods becomes paramount. This paper presents a comprehensive exploration of optimization strategies and hyperparameter tuning techniques for neural networks. Neural networks have emerged as a powerful and versatile class …

Go to article

L3 Ensembles: Lifelong Learning Approach For Ensemble Of Foundational Language Models*, Aidin Shiri, Kaushik Roy, Amit Sheth, Manas Gaur Jan 2023

L3 Ensembles: Lifelong Learning Approach For Ensemble Of Foundational Language Models*, Aidin Shiri, Kaushik Roy, Amit Sheth, Manas Gaur

Publications

Fine-tuning pre-trained foundational language models (FLM) for specific tasks is often impractical, especially for resource-constrained devices. This necessitates the development of a Lifelong Learning (L3) framework that continuously adapts to a stream of Natural Language Processing (NLP) tasks efficiently. We propose an approach that focuses on extracting meaningful representations from unseen data, constructing a structured knowledge base, and improving task performance incrementally. We conducted experiments on various NLP tasks to validate its effectiveness, including benchmarks like GLUE and SuperGLUE. We measured good performance across the accuracy, training efficiency, and knowledge transfer metrics. Initial experimental results show that the proposed L3 …

Go to article

First Prev Next Last