检索结果-内蒙古大学图书馆

MGSER-SAM: Memory-Guided Soft Experience Replay with Sharpness-Aware Optimization for Enhanced Continual Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Xingyu Tang, Bo Department of Computer Science Tulane University New Orleans United States Department of Electrical and Computer Engineering Worcester Polytechnic Institute Worcester United States

Deep neural networks suffer from the catastrophic forgetting problem in the field of continual learning (CL). To address this challenge, we propose MGSER-SAM, a novel memory replay-based algorithm specifically engineered to enhance the generalization capabilities of CL models. We first intergrate the SAM optimizer, a component designed for optimizing flatness, which seamlessly fits into well-known Experience Replay frameworks such as ER and DER++. Then, MGSER-SAM distinctively addresses the complex challenge of reconciling conflicts in weight perturbation directions between ongoing tasks and previously stored memories, which is underexplored in the SAM optimizer. This is effectively accomplished by the strategic integration of soft logits and the alignment of memory gradient directions, where the regularization terms facilitate the concurrent minimization of various training loss terms integral to the CL process. Through rigorous experimental analysis conducted across multiple benchmarks, MGSER-SAM has demonstrated a consistent ability to outperform existing baselines in all three CL scenarios. Comparing to the representative memory replay-based baselines ER and DER++, MGSER-SAM not only improves the testing accuracy by 24.4% and 17.6% respectively, but also achieves the lowest forgetting on each benchmark. Copyright © 2024, The Authors. All rights reserved.

关键词： Image classification

Racial Skew in Fine-Tuned Legal AI Language Models

学校读者我要写书评

暂无评论

Racial Skew in Fine-Tuned Legal AI Language Models

IEEE International Conference on data Mining Workshops (ICDM Workshops)

作者： Vincent Quirante Malic Anamika Kumari Xiaozhong Liu Department of Information Science Indiana University Bloomington Bloomington USA Department of Computer Science Worcester Polytechnic Institute Worcester USA

Rapid growth in the application of large language models to an immense variety of use-case scenarios has occurred alongside increasing concern that such models learn, encode, and perpetuate harmful social biases. This concern merits particular scrutiny in legal contexts, which involve search, research, and reasoning tasks that stand to benefit greatly from LLMs, but also demand adherence to rigorous standards of fairness and equality before the law. In this paper, we operationalize legal equality in the U.S. legal context as a "blind" language model that, when prompted to select a race to fill in a blank, assigns equal probability to all choices. We then fine-tune a pretrained GPT-2 model on multiple subsets of American case law texts, accounting for time and the political lean of each court’s host state. We identify and measure the degree to which these models are unfair, deviating from legal equality by learning to associate different races with different legal contexts.

关键词：

Real-Time Joint Simulation of LiDAR Perception and Motion Planning for Automated Driving

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Zhanhong Zhang, Xiao Huang, Xinming The Department of Electrical & Computer Engineering Department of Computer Science Worcester Polytechnic Institute WorcesterMA01609 United States

Real-time perception and motion planning are two crucial tasks for autonomous driving. While there are many research works focused on improving the performance of perception and motion planning individually, it is still not clear how a perception error may adversely impact the motion planning results. In this work, we propose a joint simulation framework with LiDAR-based perception and motion planning for real-time automated driving. Taking the sensor input from the CARLA simulator with additive noise, a LiDAR perception system is designed to detect and track all surrounding vehicles and to provide precise orientation and velocity information. Next, we introduce a new collision bound representation that relaxes the communication cost between the perception module and the motion planner. A novel collision checking algorithm is implemented using line intersection checking that is more efficient for long distance range in comparing to the traditional method of occupancy grid. We evaluate the joint simulation framework in CARLA for urban driving scenarios. Experiments show that our proposed automated driving system can execute at 25 Hz, which meets the real-time requirement. The LiDAR perception system has high accuracy within 20 meters when evaluated with the ground truth. The motion planning results in consistent safe distance keeping when tested in CARLA urban driving scenarios. © 2023, CC BY.

关键词： Motion planning

Simultaneous Estimation of Manipulation Skill and Hand Grasp Force from Forearm Ultrasound Images

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Bimbraw, Keshav Nekkanti, Srikar Tiller, Daniel B. Deshmukh, Mihir Calli, Berk Howe, Robert D. Zhang, Haichong K. Robotics Engineering Worcester Polytechnic Institute WorcesterMA United States Data Science Worcester Polytechnic Institute WorcesterMA United States Biomedical Engineering Worcester Polytechnic Institute WorcesterMA United States Inova Medical Group AlexandriaVA United States Harvard Paulson School of Engineering and Applied Sciences CambridgeMA United States

Accurate estimation of human hand configuration and the forces they exert is critical for effective teleoperation and skill transfer in robotic manipulation. A deeper understanding of human interactions with objects can further enhance teleoperation performance. To address this need, researchers have explored methods to capture and translate human manipulation skills and applied forces to robotic systems. Among these, biosignal-based approaches, particularly those using forearm ultrasound data, have shown significant potential for estimating hand movements and finger forces. In this study, we present a method for simultaneously estimating manipulation skills and applied hand force using forearm ultrasound data. data collected from seven participants were used to train deep learning models for classifying manipulation skills and estimating grasp force. Our models achieved an average classification accuracy of 94.87% ± 10.16% for manipulation skills and an average root mean square error (RMSE) of 0.51 ± 0.19 N for force estimation, as evaluated using five-fold cross-validation. These results highlight the effectiveness of forearm ultrasound in advancing human-machine interfacing and robotic teleoperation for complex manipulation tasks. This work enables new and effective possibilities for human-robot skill transfer and tele-manipulation, bridging the gap between human dexterity and robotic control. © 2025, CC BY.

关键词： Mean square error

UCE-FID: Using Large Unlabeled, Medium Crowdsourced-Labeled, and Small Expert-Labeled Tweets for Foodborne Illness Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Ruofan Zhang, Dongyu Tao, Dandan Zhang, Huayi Feng, Hao Rundensteiner, Elke Data Science Program Worcester Polytechnic Institute Worcester United States Vanke School of Public Health Tsinghua University Beijing China ByteDance San Jose United States College of Ag&Environ Sciences North Carolina A&T State University Greensboro United States Computer Science/Data Science Program Worcester Polytechnic Institute Worcester United States

Foodborne illnesses significantly impact public health. Deep learning surveillance applications using social media data aim to detect early warning signals. However, labeling foodborne illness-related tweets for model training requires extensive human resources, making it challenging to collect a sufficient number of high-quality labels for tweets within a limited budget. The severe class imbalance resulting from the scarcity of foodborne illness-related tweets among the vast volume of social media further exacerbates the problem. Classifiers trained on a class-imbalanced dataset are biased towards the majority class, making accurate detection difficult. To overcome these challenges, we propose EGAL, a deep learning framework for foodborne illness detection that uses small expert-labeled tweets augmented by crowdsourced-labeled and massive unlabeled data. Specifically, by leveraging tweets labeled by experts as a reward set, EGAL learns to assign a weight of zero to incorrectly labeled tweets to mitigate their negative influence. Other tweets receive proportionate weights to counter-balance the unbalanced class distribution. Extensive experiments on real-world TWEET-FID data show that EGAL outperforms strong baseline models across different settings, including varying expert-labeled set sizes and class imbalance ratios. A case study on a multistate outbreak of Salmonella Typhimurium infection linked to packaged salad greens demonstrates how the trained model captures relevant tweets offering valuable outbreak insights. EGAL, funded by the U.S. Department of Agriculture (USDA), has the potential to be deployed for real-time analysis of tweet streaming, contributing to foodborne illness outbreak surveillance efforts. Copyright © 2023, The Authors. All rights reserved.

关键词： Budget control

Ishikawa, JESS, and Visual Analytics for Engineering

学校读者我要写书评

暂无评论

Ishikawa, JESS, and Visual Analytics for Engineering

2022 IEEE International Conference on Big data, Big data 2022

作者： Varde, Aparna S. Liang, Jianyu Yang, Zhaotong Sisson, Richard D. Montclair State University Department of Computer Science NJ United States Worcester Polytechnic Institute Mechanical and Materials Engineering MA United States

ISBN: (纸本)9781665480451

Domain-specific big data poses issues in knowledge discovery and decision support given its many Vs such as volume, variety, and visualization. In this work, we propose solutions via Ishikawa diagrams, JESS (Java Expert System Shell) with rule discovery, as well as visual analytics. We deploy data science and domain models, targeting engineering and scientific domains. Our results yield high accuracy, efficiency and cost-effectiveness. © 2022 IEEE.

关键词： Big data

Hands-On Learning: Teaching Parallel and Distributed Computing through Unplugged Activities in Undergraduate CS Courses 24

学校读者我要写书评

暂无评论

Hands-On Learning: Teaching Parallel and Distributed Computi...

Proceedings of the SC '24 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis

作者： Anurag Dasgupta Venkat Margapuri Simon Shamoun Shubbhi Taneja Matthew Toups Computer Science and Engineering Technology Valdosta State University Valdosta GA Department of Computing Sciences Villanova University Villanova PA Department of Computer Science Hofstra University Hempstead NY Department of Computer Science Worcester Polytechnic Institute Worcester Massachusetts Computer Science Department Tulane University New Orleans LA

ISBN: (纸本)9798350355543

The authors present and evaluate an unplugged activity to introduce parallel computing concepts to undergraduate students. Students in five CS classrooms used a deck of playing cards in small groups to consider how parallelization can improve performance and how improvement decreases with increased parallelization. Before and after the activity, students took a short survey about their solution and their ideas about parallelism. The authors carried out this activity in seven courses at five institutions in the 2023-2024 academic year. The results showed that students had an increased appreciation for parallelization and this type of activity.

关键词： CS

Realistic data Generation for 6D Pose Estimation of Surgical Instruments

学校读者我要写书评

暂无评论

Realistic Data Generation for 6D Pose Estimation of Surgical...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Juan Antonio Barragan Jintan Zhang Haoying Zhou Adnan Munawar Peter Kazanzides Department of Computer Science Johns Hopkins University Baltimore MD USA Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Automation in surgical robotics has the potential to improve patient safety and surgical efficiency, but it is difficult to achieve due to the need for robust perception algorithms. In particular, 6D pose estimation of surgical instruments is critical to enable the automatic execution of surgical maneuvers based on visual feedback. In recent years, supervised deep learning algorithms have shown increasingly better performance at 6D pose estimation tasks; yet, their success depends on the availability of large amounts of annotated data. In household and industrial settings, synthetic data, generated with 3D computer graphics software, has been shown as an alternative to minimize annotation costs of 6D pose datasets. However, this strategy does not translate well to surgical domains as commercial graphics software have limited tools to generate images depicting realistic instrument-tissue interactions. To address these limitations, we propose an improved simulation environment for surgical robotics that enables the automatic generation of large and diverse datasets for 6D pose estimation of surgical instruments. Among the improvements, we developed an automated data generation pipeline and an improved surgical scene. To show the applicability of our system, we generated a dataset of 7.5k images with pose annotations of a surgical needle that was used to evaluate a state-of-the-art pose estimation network. The trained model obtained a mean translational error of 2.59mm on a challenging dataset that presented varying levels of occlusion. These results highlight our pipeline’s success in training and evaluating novel vision algorithms for surgical robotics applications.

关键词： Training Visualization Medical robotics Three-dimensional displays Annotations Instruments Pose estimation

Empowering Collective Impact: Introducing SWAP for Resource Sharing

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Huang, Weixiao Deshusses, Elise J. Pazour, Jennifer Telliel, Yunus Trapp, Andrew C. Data Science Program Worcester Polytechnic Institute 100 Institute Road WorcesterMA United States Computer Science Program Worcester Polytechnic Institute 100 Institute Road WorcesterMA United States School of Arts and Sciences Worcester Polytechnic Institute 100 Institute Road WorcesterMA United States School of Business Worcester Polytechnic Institute 100 Institute Road WorcesterMA United States Industrial and Systems Engineering Rensselaer Polytechnic Institute 110 Eighth Street TroyNY United States

Nonprofit organizations (NPOs) lack resources, hindering the quality and quantity of service they can deliver. Meanwhile, NPOs at times have underutilized or even spare resources due to the inability to scale expertise in staffing and tangible resources to meet temporally shifting service demands. These observations motivate us to propose a novel resource sharing system, SWAP, which to the best of our knowledge, is the first resource sharing system that facilitates resource exchanges where NPOs can obtain resources by offering their own. SWAP consists of four elements: a collaborative auction-based sharing process, complete with an offering mechanism, a bidding mechanism, and the virtual currency, SWAPcredit, to facilitate liquidity in exchange;a central technology that represents the award determination problem with a multilateral exchange optimization model, generating optimal resource exchange outcomes;an online platform, the SWAP Hub, where NPOs can offer and bid on available resources, and receive exchange results;and human-centric co-design, shaping the understanding and design decisions of a research collective, that includes the authors and NPO professionals. We conduct a series of experiments using both empirical and simulated data to illustrate the benefits and potential of SWAP. Our results demonstrate that SWAP can address temporal resource needs in practice;show that optimal exchange outcomes can be generated even for large-scale SWAP markets;and provide strong evidence in support of guidance to inform the progression for future versions of SWAP. The SWAP system is presently implemented in Howard County, Maryland, USA, with ongoing enhancements and strong potential for future expansion. © 2023, The Authors. All rights reserved.

关键词： Integer programming