检索结果-内蒙古大学图书馆

3rd EAI International Conference on Blockchain Technology and Emerging Applications, BlockTEA 2023

作者： Liang, Ting He, Yaorui Huang, Pei Xia, Zhe School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology Wuhan430071 China

ISBN: (纸本)9783031600364

With the development of information technology, people can share their health records (PHRs) through the Internet and obtain rapid medical services, which makes mobile health become a promising field. PHRs are collected from wireless body area networks (WBANs) and will be shared with people in different fields through public channels, increasing the risk of leaking personal privacy. Ciphertext-policy attribute-based encryption (CP-ABE) is a popular solution for fine-grained access control, but most existing schemes cannot be directly applied to the WBANs with limited resources and dynamic changes in user roles. In this paper, to meet the requirement of the mHealth System, we propose blockchain-based hierarchical access control with efficient revocation in the mHealth system. We use the Extendable Hierarchical attribute-based encryption (EH-ABE), a file-related hierarchical access control scheme, to encrypt PHRs, which reduces the repetitive computation and storage overhead. The proposed scheme adds the function of offline/online encryption, which can greatly save the energy consumption of the sensors in the WBANs. In addition, this scheme can provide attribute-level user revocation and is proven to be IND-CCA secure. © ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Chasing Convex Functions with Long-term Constraints 41

Chasing Convex Functions with Long-term Constraints

引用

41st International Conference on Machine Learning, ICML 2024

作者： Lechowicz, Adam Christianson, Nicolas Sun, Bo Bashir, Noman Hajiesmaili, Mohammad Wierman, Adam Shenoy, Prashant Manning College of Information and Computer Sciences University of Massachusetts Amherst United States California Institute of Technology United States Cheriton School of Computer Science University of Waterloo ON Canada Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology United States

We introduce and study a family of online metric problems with long-term constraints. In these problems, an online player makes decisions xt in a metric space (X, d) to simultaneously minimize their hitting cost ft(xt) and switching cost as determined by the metric. Over the time horizon T, the player must satisfy a long-term demand constraint -t c(xt) ≥ 1, where c(xt) denotes the fraction of demand satisfied at time t. Such problems can find a wide array of applications to online resource allocation in sustainable energy/computing systems. We devise optimal competitive and learning-augmented algorithms for the case of bounded hitting cost gradients and weighted 1 metrics, and further show that our proposed algorithms perform well in numerical experiments. Copyright 2024 by the author(s)

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Towards Combating Frequency Simplicity-biased Learning for Domain Generalization 38

Towards Combating Frequency Simplicity-biased Learning for D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： He, Xilin Hu, Jingyu Lin, Qinliang Luo, Cheng Xie, Weicheng Song, Siyang Khan, Muhammad Haris Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Provincial Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets, namely as frequency shortcuts, instead of semantic information, resulting in poor generalization performance. Despite previous data augmentation techniques successfully enhancing generalization performances, they intend to apply more frequency shortcuts, thereby causing hallucinations of generalization improvement. In this paper, we aim to prevent such learning behavior of applying frequency shortcuts from a data-driven perspective. Given the theoretical justification of models' biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain. Intuitively, as frequency shortcuts are hidden in the dominant and highly dependent frequencies of dataset structure, dynamically perturbating the over-reliance frequency components could prevent the application of frequency shortcuts. To this end, we propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset, aiming to dynamically influence the learning behavior of the model and ultimately serving as a strategy to mitigate shortcut learning. Code is available at AdvFrequency. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Camouflage pattern adversarial generation model using color and semantic constraints 3

Camouflage pattern adversarial generation model using color ...

引用

3rd International Symposium on computer Applications and Information Systems, ISCAIS 2024

作者： Zhang, Hao Xie, Zhenping School of Artificial Intelligence and Computer Science Jiangnan University Jiangsu Wuxi214122 China Jiangsu Key Laboratory of Media Design and Software Technology Jiangsu Wuxi214122 China

ISBN: (纸本)9781510681316

In response to the challenge that traditional camouflage design methods struggle to evade detection by modern unmanned aerial reconnaissance, we propose a camouflage pattern generation adversarial network model using color-semantic constraints. A reference image generation model using color-semantic constraints has been established, which through sentence encoding model, generates reference images with fundamental texture and color features. This is achieved by incorporating adversarial loss, texture loss, and pixel-level loss. We design a color standardization processing strategy based on the SimCLR framework. This model generates semantic camouflage images in batches by designing data augmentation strategies, positive-negative sample similarity measurement strategies, and sample structural similarity algorithms, regard to reference images. Qualitative and quantitative experimental results demonstrate that our proposed method exhibits strong camouflage performance in different environmental settings. © 2024 SPIE.

关键词： Design

来源：评论

学校读者我要写书评

暂无评论

Analysis and Prediction of Factors Affecting Student Grades in Online Collaborative Learning Using Genetic Programming-based Approach 4

Analysis and Prediction of Factors Affecting Student Grades ...

引用

4th International Conference on Educational Technology, ICET 2024

作者： Si, Kaiyan Ye, Junmin Yu, Shuang Yin, Xinghan Ren, Wen Luo, Sheng Zhao, Gang Central China Normal University School of Computer Science Wuhan China Central China Normal University Faculty of Artificial Intelligence In Education Wuhan China Central China Normal University Hubei Key Laboratory of Digital Education Faculty of Artificial Intelligence In Education Wuhan China

ISBN: (纸本)9798350376944

computer-supported collaborative learning (CSCL) has been widely adopted as an instructional method that utilizes computer technology to support and facilitate cooperation and collaboration in the learning process. In order to achieve high-quality collaborative learning and provide personalized instruction to students in a CSCL environment, it is necessary to analyze collaborative interaction characteristics and predict student performance. There are still some limitations to the existing studies due to the underutilization of data on the student collaboration process and the poor interpretability of the models used. Therefore, this study fully mines students' collaborative session data, extracts relevant collaborative interaction features, and then constructs a student performance prediction model using the GP algorithm. Finally, we explored the accuracy of the GP model and validated it using another online collaborative course. The study showed that the GP prediction model was more accurate and stable than other machine learning methods, and the validation results in another course showed a high degree of consistency between student grades in the course and the model's predictions. In addition, the analysis results revealed that the number of statements, length of statements, and positive and negative emotions were the key factors affecting student grades in the CSCL environment. The findings help provide useful insights for further optimizing curriculum design and instructional interventions. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Smart Education Case: A detection method of the driver's smoking behavior 2

Smart Education Case: A detection method of the driver's smo...

引用

2nd International Conference on Informatics, Networking, and Computing, ICINC 2023

作者： Xu, Yujia Shi, Rui Pan, Deyu Yang, Li He, Tingting Ding, Ling School of Computer Science Hubei University of Education Wuhan China Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Central China Normal University Wuhan China

ISBN: (纸本)9781510674745

This article presents a case study of our process in Smart Education. This is a case of detecting driver smoking behavior, in which intelligent image processing technology was used. Let students know how to conduct academic research through case analysis. Train students how to do image preprocessing, how to do detection algorithm, how to deal with experimental results, how to do result analysis and so on. Drivers have a kinds of common abnormal behaviors, including smoking, making phone calls, eating, and leaving the steering wheel. Among them, smoking is closely related to the fatigue state of the driver;when drivers make other abnormal behaviors, their hands will leave the steering wheel, which is easy to cause the car to get out of control. Therefore, this paper mainly focuses on the abnormal driving behaviors of smoking and the hands leaving the steering wheel. © 2024 SPIE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Date-Driven Approach for Identifying State of Hemodialysis Fistulas: Entropy-Complexity and Formal Concept Analysis 11th

Date-Driven Approach for Identifying State of Hemodialysis...

引用

11th International Conference on Analysis of Images, Social Networks and Texts , AIST 2023

作者： Gromov, Vasilii A. Zvorykina, Ekaterina I. Beschastnov, Yurii N. Sohrabi, Majid School of Data Analysis and Artificial Intelligence Faculty of Computer Science HSE University Moscow109028 Russia Laboratory for Models and Methods of Computational Pragmatics HSE University Moscow Russia

ISBN: (纸本)9783031670077

The paper explores mathematical methods that differentiate regular and chaotic time series, specifically for identifying pathological fistulas. It proposes a noise-resistant method for classifying responding rows of normally and pathologically functioning fistulas. This approach is grounded in the hypothesis that laminar blood flow signifies normal function, while turbulent flow indicates pathology. The study explores two distinct methods for distinguishing chaotic from regular time series. The first method involves mapping the time series onto the entropy-complexity plane and subsequently comparing it to established clusters. The second method, introduced by the authors, constructs a concepts-objects graph using formal concept analysis. Both of these methods exhibit high efficiency in determining the state of the fistula. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

STRNet: Semantic Segmentation Based on Small Target Refinement at Large Scale 24

STRNet: Semantic Segmentation Based on Small Target Refineme...

引用

3rd International Conference on computer, artificial intelligence and Control Engineering, CAICE 2024

作者： Wang, Futian Shi, Tao Luo, Bin Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

ISBN: (纸本)9798400716942

In the past few years, most high-performance semantic segmentation models have focused on learning semantic information in high-level semantic features, and in order to obtain more features, they will use high-resolution images for high-rate downsampling. Although this will obtain a better segmentation effect, due to the high rate of subsampling, the segmentation effect of small and medium-sized targets in the image is very poor, and because the training is conducted with high-resolution images, it will bring huge pressure on computing resources. To solve this problem, we propose a new two-branch small target refinement model (STRNet), and in order to reduce the high cost of computing resources brought by high resolution images, we use low resolution images for training. A large number of experiments demonstrated that our approach improved Cityscapes and CamVid datasets by 2.0% and 3.8% over the strong baseline, respectively. © 2024 ACM.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Legal Risks and Governance Paths for Generative AI - A Case Study of ChatGPT 13

Legal Risks and Governance Paths for Generative AI - A Case ...

引用

13th International Conference on Information Technology in Medicine and Education, ITME 2023

作者： Zhenfeng, Wang Quanwang, Lin Huihui, Gao Xiehua, Yu University of Fujian Province Key Laboratory of Big Data and Artificial Intelligence China MinNan Science and Technology University Fujian China School of Computer and Information MinNan Science and Technology University Quanzhou China University of Fujian Key Laboratory of Big Data and Artificial Intelligence Quanzhou China

ISBN: (纸本)9798350319156

The release of OpenAI's ChatGPT chatbot has sparked widespread concern around the world about the threats and legal issues of generative AI. Although this technological innovation has opened a new chapter in the field of artificial intelligence, it has also caused the public to worry about its possible negative effects. In order to solve the above problems and reasonably regulate the legal risks of generative artificial intelligence, this paper mainly adopts the literature, quantitative and qualitative analysis methods, etc. The first part mainly introduces the development process and current situation of generative artificial intelligence, the second part mainly discusses the impact of generative artificial intelligence on tort law, the third part mainly discusses the legal risks of generative artificial intelligence, and the fourth part mainly discusses the governance path of generative artificial intelligence legal risks. The last part is the conclusion of the research. Among them, the fourth part is the focus of this paper. By taking these issues into account, we can provide legal guarantees for the sustainable development of the generative AI industry and ensure that the widespread application of AI benefits human society[1]. © 2023 IEEE.

关键词： artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Security within Security: Attack Detection Model with Defenses Against Attacks Capability for Zero-trust Networks

引用

IEEE Journal on Selected Areas in Communications 2025年第6期43卷 2312-2327页

作者： Wang, Tingting Fang, Kai Cai, Jijing Wang, Lina Tian, Jinyu Feng, Hailin Li, Jianqing Guizani, Mohsen Wang, Wei Macau University of Science and Technology Faculty of Innovation Engineering School of Computer Science and Engineering Macau999078 China Zhejiang A&F University College of Mathematics and Computer Science Hangzhou311300 China Machine Learning Department United Arab Emirates Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen518172 China Beijing Institute of Technology School of Medical Technology Beijing100081 China

Traditional traffic anomaly-based attack detection methods in Zero-trust Networks (ZTN) suffer from inherent security vulnerabilities, as they neglect considerations regarding their security defenses. Compromising the attack detection model itself can result in the breakdown of normal attack detection capabilities. Ensuring the security of the attack detection model during runtime presents a novel challenge. To address these shortcomings, we propose a novel attack detection model, termed Security within Security: Attack Detection Model with Defenses Against Attacks Capability for Zero-Trust Networks (SWS), aimed at enhancing the security of ZTN. SWS focuses on achieving attack detection in non-secure detection environments, to maintain its detection capability even when under attack. By employing a soft thresholding method, SWS adapts to the dynamic changes in network traffic, thus reducing the interference of attack signals. The incorporation of an attention mechanism enables SWS to concentrate on analyzing the most indicative traffic features of attack behavior. Additionally, we integrate Residual Networks (ResNet) and Bidirectional Long Short-Term Memory (BiLSTM) to enhance the robustness of identifying complex network attack behaviors. The effectiveness of the SWS is validated through ablation studies, model comparisons, experiments conducted over different training epochs, and experiments conducted on various components of the dataset. Experimental results demonstrate that compared to existing attack detection models, SWS achieves improvements in detection accuracy and recall rate by 13.4% and 10.6%, respectively, while reducing the False Positive Rate (FPR) by 16.9%. © 1983-2012 IEEE.

关键词： Economic and social effects

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：