Physical Sciences and Mathematics Commons^™

Boring But Demanding: Using Secondary Tasks To Counter The Driver Vigilance Decrement For Partially Automated Driving, Scott Mishler, Jing Chen

Psychology Faculty Publications

Objective

We investigated secondary–task–based countermeasures to the vigilance decrement during a simulated partially automated driving (PAD) task, with the goal of understanding the underlying mechanism of the vigilance decrement and maintaining driver vigilance in PAD.

Background

Partial driving automation requires a human driver to monitor the roadway, but humans are notoriously bad at monitoring tasks over long periods of time, demonstrating the vigilance decrement in such tasks. The overload explanations of the vigilance decrement predict the decrement to be worse with added secondary tasks due to increased task demands and depleted attentional resources, whereas the underload explanations predict the vigilance …

The Vulnerabilities Of Artificial Intelligence Models And Potential Defenses, Felix Iov

Cybersecurity Undergraduate Research Showcase

The rapid integration of artificial intelligence (AI) into various commercial products has raised concerns about the security risks posed by adversarial attacks. These attacks manipulate input data to disrupt the functioning of AI models, potentially leading to severe consequences such as self-driving car crashes, financial losses, or data breaches. We will explore neural networks, their weaknesses, and potential defenses. We will discuss adversarial attacks including data poisoning, backdoor attacks, evasion attacks, and prompt injection. Then, we will explore defense strategies such as data protection, input sanitization, and adversarial training. By understanding how adversarial attacks work and the defenses against them, …

High-Resolution And Quality Settings With Latent Consistency Models, Steven Chen, Junrui Zhang, Rui Ning

Cybersecurity Undergraduate Research Showcase

Diffusion Models have become powerful generative models which is capable of synthesizing high-quality images across various domains. This paper explores Stable Diffusion and mostly focuses on Latent Diffusion Models. Latent Consistency Models can enhance the inference with minimal iterations. It demonstrates the performance in image in-painting and class-conditional synthesis tasks. Throughout the experiment different datasets and parameter configurations, the paper highlights the image quality, processing time, and parameter. It also discussed the future directions including adding trigger-based implementation and emotional-based themes to replace the prompt.

The Security Of Deep Neural Networks, Jalaya Allen

Cybersecurity Undergraduate Research Showcase

Our society has transitioned from our primitive lifestyle to soon, an increasingly automatic one. That idea is further exemplified as we shift into an AI era, better known as Artificial intelligence. Artificial Intelligence is classified as computer systems that can perform tasks that typically require human intelligence. However, a common thought or question that most might have is, how is this done? How does AI process information the way we want it to and have access to so much information? AI is trained by systems called AI models. These modeling programs are trained on data to recognize patterns or make …

Computational Modeling And Analysis Of Facial Expressions And Gaze For Discovery Of Candidate Behavioral Biomarkers For Children And Young Adults With Autism Spectrum Disorder, Megan Anita Witherow

Electrical & Computer Engineering Theses & Dissertations

Facial expression production and perception in autism spectrum disorder (ASD) suggest the potential presence of behavioral biomarkers that may stratify individuals on the spectrum into prognostic or treatment subgroups. High-speed internet and the ease of technology have enabled remote, scalable, affordable, and timely access to medical care, such as measurements of ASDrelated behaviors in familiar environments to complement clinical observation. Machine and deep learning (DL)-based analysis of video tracking (VT) of expression production and eye tracking (ET) of expression perception may aid stratification biomarker discovery for children and young adults with ASD. However, there are open challenges in 1) facial …

Time Series Models For Predicting Application Gpu Utilization And Power Draw Based On Trace Data, Dorothy Xiaoshuang Parry

Electrical & Computer Engineering Theses & Dissertations

This work explores collecting performance metrics and leveraging various statistical and machine learning time series predictive models on a memory-intensive application, Inception v3. Trace data collected using nvidia-smi measured GPU utilization and power draw for two runs of Inception3. Experimental results from the statistical and machine learning-based time series predictive algorithms showed that the predictions from statistical-based models were unable to capture the complex changes in the trace data. The Probabilistic TNN model provided the best results for the power draw trace, according to the test evaluation metrics. For the GPU utilization trace, the RNN models produced the most accurate …

Automatic Classification Of Activities In Classroom Videos, Jonathan K. Foster, Matthew Korban, Peter Youngs, Ginger S. Watson, Scott T. Acton

VMASC Publications

Classroom videos are a common source of data for educational researchers studying classroom interactions as well as a resource for teacher education and professional development. Over the last several decades emerging technologies have been applied to classroom videos to record, transcribe, and analyze classroom interactions. With the rise of machine learning, we report on the development and validation of neural networks to classify instructional activities using video signals, without analyzing speech or audio features, from a large corpus of nearly 250 h of classroom videos from elementary mathematics and English language arts instruction. Results indicated that the neural networks performed …

Urban Flood Extent Segmentation And Evaluation From Real-World Surveillance Camera Images Using Deep Convolutional Neural Network, Yidi Wang, Yawen Shen, Behrouz Salahshour, Mecit Cetin, Khan Iftekharuddin, Navid Tahvildari, Guoping Huang, Devin K. Harris, Kwame Ampofo, Jonathan L. Goodall

Civil & Environmental Engineering Faculty Publications

This study explores the use of Deep Convolutional Neural Network (DCNN) for semantic segmentation of flood images. Imagery datasets of urban flooding were used to train two DCNN-based models, and camera images were used to test the application of the models with real-world data. Validation results show that both models extracted flood extent with a mean F1-score over 0.9. The factors that affected the performance included still water surface with specular reflection, wet road surface, and low illumination. In testing, reduced visibility during a storm and raindrops on surveillance cameras were major problems that affected the segmentation of flood extent. …

Triphlapan: Predicting Hla Molecules Binding Peptides Based On Triple Coding Matrix And Transfer Learning, Meng Wang, Chuqi Lei, Jianxin Wang, Yaohang Li, Min Li

Computer Science Faculty Publications

Human leukocyte antigen (HLA) recognizes foreign threats and triggers immune responses by presenting peptides to T cells. Computationally modeling the binding patterns between peptide and HLA is very important for the development of tumor vaccines. However, it is still a big challenge to accurately predict HLA molecules binding peptides. In this paper, we develop a new model TripHLApan for predicting HLA molecules binding peptides by integrating triple coding matrix, BiGRU + Attention models, and transfer learning strategy. We have found the main interaction site regions between HLA molecules and peptides, as well as the correlation between HLA encoding and binding …

Applications Of Ai/Ml In Maritime Cyber Supply Chains, Rafael Diaz, Ricardo Ungo, Katie Smith, Lida Haghnegahdar, Bikash Singh, Tran Phuong

School of Cybersecurity Faculty Publications

Digital transformation is a new trend that describes enterprise efforts in transitioning manual and likely outdated processes and activities to digital formats dominated by the extensive use of Industry 4.0 elements, including the pervasive use of cyber-physical systems to increase efficiency, reduce waste, and increase responsiveness. A new domain that intersects supply chain management and cybersecurity emerges as many processes as possible of the enterprise require the convergence and synchronizing of resources and information flows in data-driven environments to support planning and execution activities. Protecting the information becomes imperative as big data flows must be parsed and translated into actions …

Higher Education Faculty Perceptions Of Chatgpt And The Influencing Factors: A Sentiment Analysis Of X, Yoseph Mamo, Helen Crompton, Diane Burke, Christine E. Nickel

STEMPS Faculty Publications

ChatGPT, an AI chatbot developed by OpenAI, was released in November 2022, sparking a significant surge in global awareness and utilization of generative AI across various domains. Although recent studies have acknowledged the significance of ChatGPT in the education sector, they have yet to focus on exploring faculty attitudes toward ChatGPT. We gathered a comprehensive corpus of tweets containing “#ChatGPT” and “#highered” between November 30th, 2022, and April 30th, 2023. We analyzed data by triangulating VADER, NRC lexicon, and ground coding. Findings suggest that 40% of the expressed sentiments were positive, 51% were neutral, and 9% were negative. The study …

Ai-Designed Clothing And Perceived Values: What Can Move Consumers' Minds With The Ai-Designed Clothing?, Choi Dooyoung, Ha Kyung Lee

STEMPS Faculty Publications

This study investigates the perceived values of AI-designed clothing (quality, emotion, ease) and their impact on willingness to pay (WTP) and word-of-mouth (WOM), with the moderating effect of gender differences. A total of 314 respondents completed the survey via MTurk. Participants watched a video clip demonstrating how an AI system creates various clothing designs by altering garment elements (e.g., style, size). After watching the video clip, they were asked to answer a series of questions about the AI-designed clothing and themselves. The collected data were analyzed using AMOS 26.0. Results showed that, for male and female consumers, the quality value …

Dilf: Differentiable Rendering-Based Multi-View Image-Language Fusion For Zero-Shot 3d Shape Understanding, Xin Ning, Zaiyang Yu, Lusi Li, Weijun Li, Prayag Tiwari

Computer Science Faculty Publications

Zero-shot 3D shape understanding aims to recognize “unseen” 3D categories that are not present in training data. Recently, Contrastive Language–Image Pre-training (CLIP) has shown promising open-world performance in zero-shot 3D shape understanding tasks by information fusion among language and 3D modality. It first renders 3D objects into multiple 2D image views and then learns to understand the semantic relationships between the textual descriptions and images, enabling the model to generalize to new and unseen categories. However, existing studies in zero-shot 3D shape understanding rely on predefined rendering parameters, resulting in repetitive, redundant, and low-quality views. This limitation hinders the model’s …

A Survey On Few-Shot Class-Incremental Learning, Songsong Tian, Lusi Li, Weijun Li, Hang Ran, Xin Ning, Prayag Tiwari

Computer Science Faculty Publications

Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental …

A Chinese Power Text Classification Algorithm Based On Deep Active Learning, Song Deng, Qianliang Li, Renjie Dai, Siming Wei, Di Wu, Yi He, Xindong Wu

Computer Science Faculty Publications

The construction of knowledge graph is beneficial for grid production, electrical safety protection, fault diagnosis and traceability in an observable and controllable way. Highly-precision text classification algorithm is crucial to build a professional knowledge graph in power system. Unfortunately, there are a large number of poorly described and specialized texts in the power business system, and the amount of data containing valid labels in these texts is low. This will bring great challenges to improve the precision of text classification models. To offset the gap, we propose a classification algorithm for Chinese text in the power system based on deep …

Identifying Patterns For Neurological Disabilities By Integrating Discrete Wavelet Transform And Visualization, Soo Yeon Ji, Sampath Jayarathna, Anne M. Perrotti, Katrina Kardiasmenos, Dong Hyun Jeong

Computer Science Faculty Publications

Neurological disabilities cause diverse health and mental challenges, impacting quality of life and imposing financial burdens on both the individuals diagnosed with these conditions and their caregivers. Abnormal brain activity, stemming from malfunctions in the human nervous system, characterizes neurological disorders. Therefore, the early identification of these abnormalities is crucial for devising suitable treatments and interventions aimed at promoting and sustaining quality of life. Electroencephalogram (EEG), a non-invasive method for monitoring brain activity, is frequently employed to detect abnormal brain activity in neurological and mental disorders. This study introduces an approach that extends the understanding and identification of neurological disabilities …

Learning Optimal Inter-Class Margin Adaptively For Few-Shot Class-Incremental Learning Via Neural Collapse-Based Meta-Learning, Hang Ran, Weijun Li, Lusi Li, Songsong Tian, Xin Ning, Prayag Tiwari

Computer Science Faculty Publications

Few-Shot Class-Incremental Learning (FSCIL) aims to learn new classes incrementally with a limited number of samples per class. It faces issues of forgetting previously learned classes and overfitting on few-shot classes. An efficient strategy is to learn features that are discriminative in both base and incremental sessions. Current methods improve discriminability by manually designing inter-class margins based on empirical observations, which can be suboptimal. The emerging Neural Collapse (NC) theory provides a theoretically optimal inter-class margin for classification, serving as a basis for adaptively computing the margin. Yet, it is designed for closed, balanced data, not for sequential or few-shot …

Robots Still Outnumber Humans In Web Archives In 2019, But Less Than In 2015 And 2012, Himarsha R. Jayanetti, Kritika Garg, Sawood Alam, Michael L. Nelson, Michele C. Weigle

Computer Science Faculty Publications

The significance of the web and the crucial role of web archives in its preservation highlight the necessity of understanding how users, both human and robot, access web archive content, and how best to satisfy this disparate needs of both types of users. To identify robots and humans in web archives and analyze their respective access patterns, we used the Internet Archive’s (IA) Wayback Machine access logs from 2012, 2015, and 2019, as well as Arquivo.pt’s (Portuguese Web Archive) access logs from 2019. We identified user sessions in the access logs and classified those sessions as human or robot based …

Machine Learning As A Tool For Early Detection: A Focus On Late-Stage Colorectal Cancer Across Socioeconomic Spectrums, Hadiza Galadima, Rexford Anson-Dwamena, Ashley Johnson, Ghalib Bello, Georges Adunlin, James Blando

Community & Environmental Health Faculty Publications

Purpose: To assess the efficacy of various machine learning (ML) algorithms in predicting late-stage colorectal cancer (CRC) diagnoses against the backdrop of socio-economic and regional healthcare disparities. Methods: An innovative theoretical framework was developed to integrate individual- and census tract-level social determinants of health (SDOH) with sociodemographic factors. A comparative analysis of the ML models was conducted using key performance metrics such as AUC-ROC to evaluate their predictive accuracy. Spatio-temporal analysis was used to identify disparities in late-stage CRC diagnosis probabilities. Results: Gradient boosting emerged as the superior model, with the top predictors for late-stage CRC diagnosis being anatomic site, …

Automatic Hemorrhage Segmentation In Brain Ct Scans Using Curriculum-Based Semi-Supervised Learning, Solayman H. Emon, Tzu-Liang (Bill) Tseng, Michael Pokojovy, Peter Mccaffrey, Scott Moen, Md Fashiar Rahman

Mathematics & Statistics Faculty Publications

One of the major neuropathological consequences of traumatic brain injury (TBI) is intracranial hemorrhage (ICH), which requires swift diagnosis to avert perilous outcomes. We present a new automatic hemorrhage segmentation technique via curriculum-based semi-supervised learning. It employs a pre-trained lightweight encoder-decoder framework (MobileNetV2) on labeled and unlabeled data. The model integrates consistency regularization for improved generalization, offering steady predictions from original and augmented versions of unlabeled data. The training procedure employs curriculum learning to progressively train the model at diverse complexity levels. We utilize the PhysioNet dataset to train and evaluate the proposed approach. The performance results surpass those of …

Accelerating Markov Chain Monte Carlo Sampling With Diffusion Models, N. T. Hunt-Smith, W. Melnitchouk, F. Ringer, N. Sato, A. W. Thomas, M. J. White

Physics Faculty Publications

Global fits of physics models require efficient methods for exploring high-dimensional and/or multimodal posterior functions. We introduce a novel method for accelerating Markov Chain Monte Carlo (MCMC) sampling by pairing a Metropolis-Hastings algorithm with a diffusion model that can draw global samples with the aim of approximating the posterior. We briefly review diffusion models in the context of image synthesis before providing a streamlined diffusion model tailored towards low-dimensional data arrays. We then present our adapted Metropolis-Hastings algorithm which combines local proposals with global proposals taken from a diffusion model that is regularly trained on the samples produced during the …

Infusing Machine Learning And Computational Linguistics Into Clinical Notes, Funke V. Alabi, Onyeka Omose, Omotomilola Jegede

Mathematics & Statistics Faculty Publications

Entering free-form text notes into Electronic Health Records (EHR) systems takes a lot of time from clinicians. A large portion of this paper work is viewed as a burden, which cuts into the amount of time doctors spend with patients and increases the risk of burnout. We will see how machine learning and computational linguistics can be infused in the processing of taking clinical notes. We are presenting a new language modeling task that predicts the content of notes conditioned on historical data from a patient's medical record, such as patient demographics, lab results, medications, and previous notes, with the …

Sparse Representer Theorems For Learning In Reproducing Kernel Banach Spaces, Rui Wang, Yuesheng Xu, Mingsong Yan

Mathematics & Statistics Faculty Publications

Sparsity of a learning solution is a desirable feature in machine learning. Certain reproducing kernel Banach spaces (RKBSs) are appropriate hypothesis spaces for sparse learning methods. The goal of this paper is to understand what kind of RKBSs can promote sparsity for learning solutions. We consider two typical learning models in an RKBS: the minimum norm interpolation (MNI) problem and the regularization problem. We first establish an explicit representer theorem for solutions of these problems, which represents the extreme points of the solution set by a linear combination of the extreme points of the subdifferential set, of the norm function, …

Predicting The Need For Cardiovascular Surgery: A Comparative Study Of Machine Learning Models, Arman Ghavidel, Pilar Pazos, Rolando Del Aguila Suarez, Alireza Atashi

Engineering Management & Systems Engineering Faculty Publications

This research examines the efficacy of ensemble Machine Learning (ML) models, mainly focusing on Deep Neural Networks (DNNs), in predicting the need for cardiovascular surgery, a critical aspect of clinical decision-making. It addresses key challenges such as class imbalance, which is pivotal in healthcare settings. The research involved a comprehensive comparison and evaluation of the performance of previously published ML methods against a new Deep Learning (DL) model. This comparison utilized a dataset encompassing 50,000 patient records from a large hospital between 2015-2022. The study proposes enhancing the efficacy of these models through feature selection and hyperparameter optimization, employing techniques …

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 …

Domain Adaptive Federated Learning For Multi-Institution Molecular Mutation Prediction And Bias Identification, W. Farzana, M. A. Witherow, I. Longoria, M. S. Sadique, A. Temtam, K. M. Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Deep learning models have shown potential in medical image analysis tasks. However, training a generalized deep learning model requires huge amounts of patient data that is usually gathered from multiple institutions which may raise privacy concerns. Federated learning (FL) provides an alternative to sharing data across institutions. Nonetheless, FL is susceptible to a few challenges including inversion attacks on model weights, heterogenous data distributions, and bias. This study addresses heterogeneity and bias issues for multi-institution patient data by proposing domain adaptive FL modeling using several radiomics (volume, fractal, texture) features for O6-methylguanine-DNA methyltransferase (MGMT) classification across multiple institutions. The proposed …

The Educational Affordances And Challenges Of Chatgpt: State Of The Field, Helen Crompton, Diane Burke

STEMPS Faculty Publications

ChatGPT was released to the public in November 30, 2022. This study examines how ChatGPT can be used by educators and students to promote learning and what are the challenges and limitations. This study is unique in providing one of the first systematic reviews using peer review studies to provide an early examination of the field. Using PRISMA principles, 44 articles were selected for review. Grounded coding was then used to reveal trends in the data. The findings show that educators can use ChatGPT for teaching support, task automation, and professional development. These were further delineated further by axial sub …

Types Of Teacher-Ai Collaboration In K-12 Classroom Instruction: Chinese Teachers' Perspective, Jinhee Kim

STEMPS Faculty Publications

The advancing power and capabilities of artificial intelligence (AI) have expanded the roles of AI in education and have created the possibility for teachers to collaborate with AI in classroom instruction. However, the potential types of teacher-AI collaboration (TAC) in classroom instruction and the benefits and challenges of implementing TAC are still elusive. This study, therefore, aimed to explore different types of TAC and the potential benefits and obstacles of TAC through Focus Group Interviews with 30 Chinese teachers. The study found that teachers anticipated six types of TAC, which are thematized as One Teach, One Observe; One Teach, One …

The Role Of Shopping Orientations And Intrinsic Experiential Value In Consumer's Willingness To Follow Embodied-Ai's Advice In Fashion Shoe Stores, Christina Soyoung Song, Ji Young Lee, Dooyoung Choi

STEMPS Faculty Publications

This study employs a synthesis of Intrinsic Motivation Theory with three shopping orientations, namely “adventure,” “idea,” and “personalized” shopping, in order to examine their potential influence on individuals' motivation towards shopping. We proposed that consumers’ experiential value of intrinsic enjoyment is an indispensable mediator that affects their willingness to follow EAI’s advice. The study offers novel insights into the way that consumers’ characteristics of influencing others’ clothing consumption affect their shopping motivations to find adventure and stimulation, keep up with new fashion trends and products information, and their preference to patronize stores and interact with store staff on a personal …

Age Of Sensing Empowered Holographic Isac Framework For Nextg Wireless Networks: A Vae And Drl Approach, Apurba Adhikary, Avi Deb Raha, Yu Qiao, Md. Shirajum Munir, Monishanker Halder, Choong Seon Hong

School of Cybersecurity Faculty Publications

This paper proposes an artificial intelligence (AI) framework that leverages integrated sensing and communication (ISAC), aided by the age of sensing (AoS) to ensure the timely location updates of the users for a holographic MIMO (HMIMO)- enabled wireless network. The AI-driven framework guarantees optimal power allocation for efficient beamforming by activating the minimal number of grids from the HMIMO base station. An optimization problem is formulated to maximize the sensing utility function, aiming to maximize the signal-to-interference-plus-noise ratio (SINR) of the received signal, beam-pattern gains to improve the sensing SINR of reflected echo signals and maximizing the evidence lower bound …