检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tang, Jialiang Chen, Shuo Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Center for Advanced Intelligence Project RIKEN Japan Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train student networks by collecting massive real examples and generating synthetic examples, respectively. However, they inevitably become weak in practical scenarios due to the difficulties in gathering or emulating sufficient real-world data. To solve this problem, we propose a novel method called Hybrid Data-Free Distillation (HiDFD), which leverages only a small amount of collected data as well as generates sufficient examples for training student networks. Our HiDFD comprises two primary modules, i.e., the teacher-guided generation and student distillation. The teacher-guided generation module guides a Generative Adversarial Network (GAN) by the teacher network to produce high-quality synthetic examples from very few real-world collected examples. Specifically, we design a feature integration mechanism to prevent the GAN from overfitting and facilitate the reliable representation learning from the teacher network. Meanwhile, we drive a category frequency smoothing technique via the teacher network to balance the generative training of each category. In the student distillation module, we explore a data inflation strategy to properly utilize a blend of real and synthetic data to train the student network via a classifier-sharing-based feature alignment technique. Intensive experiments across multiple benchmarks demonstrate that our HiDFD can achieve state-of-the-art performance using 120 times less collected data than existing methods. Code is available at https://***/tangjialiang97/HiDFD. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare

arXiv

引用

arXiv 2025年

作者： Zhang, Hang Lou, Qian Wang, Yanshan Intelligent Systems Program School of Computing and Information University of Pittsburgh PA United States Department of Computer Science University of Central Florida OrlandoFL United States Department of Health Information Management University of Pittsburgh PA United States Department of Biomedical Informatics University of Pittsburgh PA United States Clinical and Translational Science Institute University of Pittsburgh PittsburghPA United States University of Pittsburgh Medical Center PittsburghPA United States

Large language models (LLMs) are increasingly utilized in healthcare applications. However, their deployment in clinical practice raises significant safety concerns, including the potential spread of harmful information. This study systematically assesses the vulnerabilities of seven LLMs to three advanced black-box jailbreaking techniques within medical contexts. To quantify the effectiveness of these techniques, we propose an automated and domain-adapted agentic evaluation pipeline. Experiment results indicate that leading commercial and open-source LLMs are highly vulnerable to medical jailbreaking attacks. To bolster model safety and reliability, we further investigate the effectiveness of Continual Fine-Tuning (CFT) in defending against medical adversarial attacks. Our findings underscore the necessity for evolving attack methods evaluation, domain-specific safety alignment, and LLM safety-utility balancing. This research offers actionable insights for advancing the safety and reliability of AI clinicians, contributing to ethical and effective AI deployment in healthcare. © 2025, CC BY-NC-SA.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Learning-based Control for PMSM Using Distributed Gaussian Processes with Optimal Aggregation Strategy

Learning-based Control for PMSM Using Distributed Gaussian P...

引用

Annual Conference of Industrial Electronics Society

作者： Zhenxiao Yin Xiaobing Dai Zewen Yang Yang Shen Georges Hattab Hang Zhao Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Chair of Information-oriented Control Technical University of Munich Munich Germany Center for Artificial Intelligence in Public Health Research (ZKI-PH) Robert Koch Institute Berlin Germany Department of Mathematics and Computer Science Freie Universität Berlin Berlin Germany Department of Electronic & Computer Engineering The Hong Kong University of Science and Technology Hong Kong China

The growing demand for accurate control in varying and unknown environments has sparked a corresponding increase in the requirements for power supply components, including permanent magnet synchronous motors (PMSMs). To infer the unknown part of the system, machine learning techniques are widely employed, especially Gaussian process regression (GPR) due to its flexibility of continuous system modeling and its guaranteed performance. For practical implementation, distributed GPR is adopted to alleviate the high computational complexity. However, the study of distributed GPR from a control perspective remains an open problem. In this paper, a control-aware optimal aggregation strategy of distributed GPR for PMSMs is proposed based on the Lyapunov stability theory. This strategy exclusively leverages the posterior mean, thereby obviating the need for computationally intensive calculations associated with posterior variance in alternative approaches. Moreover, the straightforward calculation process of our proposed strategy lends itself to seamless implementation in high-frequency PMSM control. The effectiveness of the proposed strategy is demonstrated in the simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring the Economic Feasibility of Advanced Air Mobility in the Early Stages

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on intelligent Vehicles 2024年第5期9卷 4826-4830页

作者： Jingqiu Guo Long Chen Lingxi Li Xiaoxiang Na Ljubo Vlacic Fei-Yue Wang Key Laboratory of Road and Traffic Engineering of the Ministry of Education Tongji University Shanghai China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Department of Electrical and Computer Engineering Purdue School of Engineering and Technology Indiana University–Purdue University Indianapolis (IUPUI) Indianapolis IN USA Department of Engineering University of Cambridge Cambridge U.K. Institute of Intelligent and Integrated Systems and the School of Engineering and Built Environment Griffith University Nathan QLD Australia State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Engineering Macau University of Science and Technology Macau China

Advanced Air Mobility (AAM) envisages a sustainable, safe, convenient, and affordable air transport system. In socio-technical transition of AAM, there are a number of trade-offs in ecosystem that need to be studied. Three perspectives on economic feasibility are explored: first, based on history of VTOL services and value of time estimates, we discuss whether AAM can provide customers with competitive mobility services; second, what are the stakeholders’ insights on the deployment of AAM; last, the experience in the development of autonomous driving technology, such as parallel intelligence, can inform future AAM research.

关键词： Active appearance model Costs Economics Transportation Helicopters Aircraft propulsion Public transportation

来源：评论

学校读者我要写书评

暂无评论

e-ViL: A dataset and benchmark for natural language explanations in vision-language tasks

arXiv

引用

arXiv 2021年

作者： Kayser, Maxime Camburu, Oana-Maria Salewski, Leonard Emde, Cornelius Do, Virginie Akata, Zeynep Lukasiewicz, Thomas Department of Computer Science University of Oxford University of Tübingen Max Planck Institute for Intelligent Systems Max Planck Institute for Informatics

Recently, there has been an increasing number of efforts to introduce models capable of generating natural language explanations (NLEs) for their predictions on vision-language (VL) tasks. Such models are appealing, because they can provide human-friendly and comprehensive explanations. However, there is a lack of comparison between existing methods, which is due to a lack of re-usable evaluation frameworks and a scarcity of datasets. In this work, we introduce eViL and e-SNLI-VE. e-ViL is a benchmark for explainable vision-language tasks that establishes a unified evaluation framework and provides the first comprehensive comparison of existing approaches that generate NLEs for VL tasks. It spans four models and three datasets and both automatic metrics and human evaluation are used to assess model-generated explanations. e-SNLI-VE is currently the largest existing VL dataset with NLEs (over 430k instances). We also propose a new model that combines UNITER [15], which learns joint embeddings of images and text, and GPT-2 [38], a pre-trained language model that is well-suited for text generation. It surpasses the previous state of the art by a large margin across all datasets. Code and data are available here: https://***/maximek3/e-ViL. Copyright © 2021, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Constructive Barrier Feedback for Collision Avoidance in Leader-Follower Formation Control

Constructive Barrier Feedback for Collision Avoidance in Lea...

引用

IEEE Conference on Decision and Control

作者： Zhiqi Tang Rita Cunha Tarek Hamel Carlos Silvestre Institute for Systems and Robotics Instituto Superior Técnico Universidade de Lisboa Portugal I3S-CNRS Université Côte d'Azur and Institut Universitaire de France France Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macao China

This paper proposes a novel constructive barrier feedback for reactive collision avoidance between two agents. It incorporates this feature in a formation tracking control strategy for a group of 2nd-order dynamic robots defined in three-dimensional space. Using only relative measurements between neighboring agents, we propose an elegant decentralized controller as the sum of a nominal tracking controller and the constructive barrier feedback for leader-follower formations under a directed single-spanning tree graph topology. The key ingredient is the use of divergent flow as a dissipative term, which slows down the relative velocity in the direction of the neighboring robots without compromising the nominal controller's performance. Compared to traditional barrier function-based optimization controllers, the proposed constructive barrier feedback avoids feasibility issues and results in more computationally efficient control algorithms with systematic equilibrium analysis. Simulations are provided to validate the effectiveness of the proposed control method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pothole Detection in Asphalt Roads: A Comprehensive Approach for Enhanced Road Maintenance and Safety with AlexNet Model

Pothole Detection in Asphalt Roads: A Comprehensive Approach...

引用

Telecommunications Conference (ITC-Egypt), International

作者： Mark Emad Sobhi Abdelmalak Nima Khodadadi Ahmed Mohamed Zaki Marwa M. Eid Faris H. Rizk Abdelhameed Ibrahim Abdelaziz A. Abdelhamid Laith Abualigah El-Sayed M. El-kenawy Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Mansoura Egypt Department of Civil and Architectural Engineering University of Miami Coral Gables FL USA Computer Science and Intelligent Systems Research Center Blacksburg Virginia USA Faculty of Artificial Intelligence Delta University for Science and Technology Mansoura Egypt Faculty of Engineering School of ICT Design and Information & Communications Technology (EDICT) Bahrain Polytechnic Isa Town Bahrain Department of Computer Science Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Computer Science Department Al al-Bayt University Mafraq Jordan MEU Research Unit Middle East University Amman Jordan Jadara Research Center Jadara University Irbid Jordan

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

The research article described in this paper puts forward a novel method of using an integrated software approach and high-end hardware devices for adaptive and intelligent detection of potholes on asphalt roads. The Pothole Detection Dataset is used for the dataset analysis, and we put VGG19Net, ResNet-50, GoogLeNet, and AlexNet among the computer vision models to analyze the applicability of these models. Different types of networks were compared, and AlexNet showed the best results as it achieved 92.15% accuracy, 91.38 % sensitivity (TPR), and a surprisingly high F-score, which reached 96.52%. Furthermore, by using its time of 279.35 seconds, which might be considered very fast, AlexNet shows many strengths in helping to do this, as well as identifying road anomalies, making it a perfect candidate for real-world utilization. This research demonstrates the emergence of sophisticated integrated pothole repair solutions, emphasizing the importance of both software and hardware in developing sophisticated pothole detection. Practices and this research could be an example for further surveying road inspection technologies.

关键词： computer vision Analytical models Adaptation models Asphalt Roads Computational modeling Hardware

来源：评论

学校读者我要写书评

暂无评论

DISENTANGLING FACTORS OF VARIATION USING FEW LABELS 8

DISENTANGLING FACTORS OF VARIATION USING FEW LABELS

引用

8th International Conference on Learning Representations, ICLR 2020

作者： Locatello, Francesco Tschannen, Michael Bauer, Stefan Rätsch, Gunnar Schölkopf, Bernhard Bachem, Olivier Department of Computer Science ETH Zurich Switzerland Max Planck Institute for Intelligent Systems Tübingen Germany Google Research Brain Team

Learning disentangled representations is considered a cornerstone problem in representation learning. Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to consistently learn disentangled representations. However, in many practical settings, one might have access to a limited amount of supervision, for example through manual labeling of (some) factors of variation in a few training examples. In this paper, we investigate the impact of such supervision on state-of-the-art disentanglement methods and perform a large scale study, training over 52 000 models under well-defined and reproducible experimental conditions. We observe that a small number of labeled examples (0.01-0.5% of the data set), with potentially imprecise and incomplete labels, is sufficient to perform model selection on state-of-the-art unsupervised models. Further, we investigate the benefit of incorporating supervision into the training process. Overall, we empirically validate that with little and imprecise supervision it is possible to reliably learn disentangled representations. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Oil Spill Detection: A Machine Learning Approach for Satellite Image Classification

Revolutionizing Oil Spill Detection: A Machine Learning Appr...

引用

Telecommunications Conference (ITC-Egypt), International

作者： Khaled Sherif Faris H. Rizk Ahmed Mohamed Zaki Marwa M. Eid Nima Khodadadi Abdelhameed Ibrahim Abdelaziz A. Abdelhamid Laith Abualigah El-Sayed M. El-Kenawy Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Mansoura Egypt Computer Science and Intelligent Systems Research Center Blacksburg Virginia USA Faculty of Artificial Intelligence Delta University for Science and Technology Mansoura Egypt Department of Civil and Architectural Engineering University of Miami Coral Gables FL USA Faculty of Engineering Design and Information & Communications Technology (EDICT) School of ICT Bahrain Polytechnic Isa Town Bahrain Department of Computer Science Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Computer Science Department Al al-Bayt University Mafraq Jordan MEU Research Unit Middle East University Amman Jordan Jadara Research Center Jadara University Irbid Jordan

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

Identifying and labeling oil spills in satellite imagery is an essential activity of both environmental monitoring and disaster response actions. This work is dedicated to applying an Artificial Neural Network (ANN) model for gathering oil spill data by using a dataset that is specially curated for this reason. Our dataset was developed from satellite pictures of the ocean, some of which depict oil spills and some that do not. The features were extracted from each picture using computer vision algorithms. Our ANN model is trained to distinguish between two classes: The metrics that are looked at consist of accuracy, sensitivity, specificity, PPV, NPV, and statistical significance, and they illustrate how the model performs. As a result, the ANN model gets an accuracy of 96.88% and a sensitivity of 92.86% at the same time, while the specificity is 99.88%. The sensitivity of this diagnostic test is 96.30%, and the specificity is 94.74%. A p-value of 0.985997 means that the reported finding reaches a statistical significance, which is enough to support our hypothesis. This can be concluded from the results of ANN, showing the potential of this model to successfully classify the image patches into two sets, namely the ones covered by oil spills and the oil spill-free ones. The research work is a great contribution to the development of the area of environmental monitoring through the machine learning methods used for quick and appropriate detection of environmental hazards.

关键词： Sensitivity Oils Computational modeling Disasters Artificial neural networks Machine learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Assessing the Robustness of nnU-Net in the Detection of Prostate Lesions via Bi-Parametric MRI

Assessing the Robustness of nnU-Net in the Detection of Pros...

引用

Data science and Engineering in Healthcare, Medicine and Biology, IEEE EMBS Special Topic Conference on

作者： Dimitrios I. Zaridis Eugenia Mylona Nikolaos Tachos Charalampos Kalantzopoulos Vasileios C. Pezoulas Dimitrios D. Koutsouris George K. Matsopoulos Kostas Marias Manolis Tsiknakis Dimitrios I. Fotiadis Biomedical Engineering Laboratory School of Electrical and Computer Engineering National Technical University of Athens GR15773 Athens Greece Biomedical Research Institute FORTH Ioannina Greece University of Ioannina Ioannina Greece Institute of Computer Science FORTH Heraklion Greece Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Crete Greece FORTH-IMBB Ioannina Greece Materials Science and Engineering Department Unit of Medical Technology and Intelligent Information Systems University of Ioannina Ioannina GR 45110 Greece

Within the scope of prostate cancer diagnostic imaging, distinguishing lesions is challenging due to their subtle appearance and the prostate gland’s complexity. This study employed the nnU-Net, a state-of-the-art medical image segmentation model, on a dataset of 301 patients from 2 openly available datasets to identify whether lesion sizes are affecting the model’s performance. By applying t-SNE dimensionality reduction algorithm among dice score and respective lesion sizes, we found that nnU-Net behaves differently for lesions smaller than 9mm compared to lesions larger than 15mm. These insights can inform specialized training approaches for future deep learning models in prostate lesion *** Relevance: The main contributions of this study is, to investigate whether lesion sizes affects nnU-Net’s deficiency leading to the development of more specialized models in respect to these factors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：