Browsing Computer Science Faculty Publications by Title
Now showing items 1-16 of 16
-
Celebrating 25 Years of Document Engineering
(2025-08-27) -
Clinical Term Normalization Using Learned Edit Patterns and Subconcept Matching: System Development and Evaluation
(2021-01-14)Background: Clinical terms mentioned in clinical text are often not in their standardized forms as listed in clinical terminologies because of linguistic and stylistic variations. However, many automated downstream ... -
Enhancing Image Restoration through Hybrid VQVAE and Transformer Architectures: A Novel Approach
(2024-12-20)Image restoration is essential for enhancing the quality and utility of degraded images in various applications such as autonomous driving and robotics. Traditional convolutional neural network (CNN) approaches, while ... -
How Heavy is the Edge? Resource Utilization of Edge Generative AI on Distributed AI Infrastructure
(2025-12-03)Distributed AI infrastructures are extensively employed in cloud industry settings to accommodate the growing demands of AI services. However, extending such infrastructures to the edge remains under exploration. This study ... -
InArt: In-Network Aggregation with Route Selection for Accelerating Distributed Training
(ACM, 2024-05-05)Deep learning has brought about a revolutionary transformation in network applications, particularly in domains like e-commerce and online advertising. Distributed training (DT), as a critical means to expedite model ... -
Multi-Length Skills with Priors for Reinforcement Learning
(ACM, 2025-02-20)Leveraging prior experience has been effective in accelerating reinforcement learning (RL). One approach for leveraging prior experience consists of learning skills, which are temporally extended sequences of actions, and ... -
Multi-Level Explainable AI for ECG-Based Atrial Fibrillation Detection: Exploring LIME, SHAP, and Grad-CAM for Clinical Interpretation
(2025-05-16)Atrial fibrillation (AFib) detection through ECG interpretation remains a critical yet complex task in clinical settings. While deep learning models have shown promise in automated ECG analysis, their "black box" nature ... -
Navigating Daily Life: Insights from Powered Wheelchair Users on Assistive Technologies and Caregiver Support
(ACM, 2024-05-02)The increasing number of powered wheelchair users, driven by an aging global population and advancements in medical care, highlights a critical need to understand their unique experiences and challenges, particularly ... -
On Equivalence of Anomaly Detection Algorithms
(2022-08-08)In most domains anomaly detection is typically cast as an unsupervised learning problem because of the infeasability of labelling large datasets. In this setup, the evaluation and comparison of different anomaly detection ... -
Poster: A Lightweight Pruning for Mitigating Neural Network Backdoor on Edge
(2025-12-03)Image-based neural networks are widely used across diverse applications, yet their inherent susceptibility to backdoor attacks has raised growing concerns. In particular, data-free backdoor attacks, which exploit benign ... -
Refining Neural Network with Symbolic Regression
(2025-07-14)Classical neural network (NN) compression methods, such as NN pruning and distillation, focus on reducing the NN size. However, these methods often sacrifice accuracy in the process. To address this issue, we propose a ... -
Risk Prediction and Interpretation for Fall Events Using Explainable AI and Large Language Models
(2025-05-16)Falls represent a significant public health concern, particularly among older adults, with approximately 35.6 million cases annually in the United States alone. Traditional machine learning-based fall risk prediction methods ... -
Saliency-Guided Lightweight Backdoor Defense for Edge Intelligence
(2025-12-03)The expansion of edge intelligence across diverse devices and sites significantly broadens the attack surface, making backdoor attacks a critical security threat. Existing backdoor trigger mitigation methods rely heavily ... -
Semantics of RxJS
(2022-11-11)RxJS is a popular JavaScript library for reactive programming in Web applications. It provides numerous operators to create, combine, transform, and filter discrete events and to handle errors. These operators may be ... -
Stable Matchings with Restricted Preferences: Structure and Complexity
(2022-09-30)In the stable marriage (SM) problem, there are two sets of agents–traditionally referred to as men and women–and each agent has a preference list that ranks (a subset of) agents of the opposite sex. The goal is to find a ... -
Unveiling Neural Network Data Free Backdoor Threats in Industrial Control Systems
(ACM, 2023-11-20)The neural network data-free backdoor attack is an emerging and potent threat, which requires minimal resources and does not rely on original training data to implant backdoors. This threat poses a significant risk to ...