检索结果-内蒙古大学图书馆

Optimal Linear Crossover for Mitigating Negative Transfer in Evolutionary Multitasking

IEEE Transactions on Evolutionary Computation 2024年

作者： Liu, Zhaobo Yuan, Jianhua Zhang, Haili Zeng, Tao Zhu, Zexuan Shenzhen University Institute for Advanced Study Shenzhen518060 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Shenzhen Polytechnic University School of Undergraduate Education Shenzhen518055 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Shenzhen University Shenzhen City Key Laboratory of Embedded System Design Shenzhen518060 China Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education of China Chongqing400044 China

Evolutionary multitasking algorithms use information exchange among individuals in a population to solve multiple optimization problems simultaneously. Negative transfer is a critical factor that affects the performance of evolutionary multitasking algorithms. In this study, we propose an innovative approach to mitigate negative transfer in evolutionary multitasking algorithms. The proposed approach is grounded in rigorous theoretical analysis, which provides valuable theoretical insights into the design of an optimal linear crossover operator for mitigating negative transfer. By identifying interpretable conditions, we establish a solid theoretical foundation to prevent negative transfer in diverse scenarios. Building upon these findings, we theoretically derive a closed-form expression for the optimal crossover operator and propose practical design methods based on approximations. Furthermore, we integrate the proposed optimal crossover operator into a fundamental evolutionary multitasking algorithm framework. The resultant algorithm is comparable or superior to other state-of-the-art methods. Empirical validation through comprehensive experiments confirms the effectiveness of our theoretical findings. © 1997-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning Robust Travel Preferences Via Check-In Masking for Next Poi Recommendation

SSRN

引用

SSRN 2023年

作者： Duan, Chenghua Zhou, Wei Zeng, Jun Zhang, Yihao Wen, Junhao School of Bigdata and Software Engineering Chongqing University Daxuecheng South Rd. 55 Chognqing400044 China Key Laboratory of Dependable Service Computing in Cyber Physical Society Moe Chognqing400044 China School of Artificial Intelligence Chongqing University of Technology Chognqing401135 China

Next point-of-interest (POI) recommendation is a crucial part of many location-based service applications. It predicts users’ next visit based on their historical trajectories and current *** solutions primarily focus on sequential modeling of users’ check-in behavior. Unfortunately, most current research overlooks the fact that check-ins are implicit feedback, and inherent noise exists within them. To this end, we propose an approach to cope with noise-learning robust user travel preferences. Specifically, we design a masking strategy for check-ins, which masks the spatio-temporal information of some check-ins in users’ trajectories and forces our model to learn visit preferences without relying on individual inputs, thereby mitigating the bias caused by noisy check-ins. Then, we utilize multi-level geographical information to recommend the next POI more accurately. Additionally, we propose another masking strategy that considers users’ living area and automatically selects the proper strategy based on trajectory features. To the best of our knowledge, this is the first work that investigates the characteristics of noisy check-ins and performs denoising in next POI recommendation. Through extensive experiments, we demonstrate that our model outperforms state-of-the-art approaches and effectively handles data sparsity and noise issues. © 2023, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

ATHENA: An In-vehicle CAN Intrusion Detection Framework Based on Physical Characteristics of Vehicle Systems

arXiv

引用

arXiv 2025年

作者： Wang, Kai Sun, Zhen Wang, Bailing Fan, Qilin Li, Ming Zhang, Hongke School of Computer Science and Technology Harbin Institute of Technology Weihai China Shandong Key Laboratory of Industrial Network Security China School of Big Data and Software Engineering Chongqing University Chongqing China Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing University Chongqing China Jinan Key Laboratory of Distributed Databases Shandong Inspur Database Technology Co. Ltd Jinan China School of Electronic and Information Engineering Beijing Jiaotong University Beijing China

With the growing interconnection between In-Vehicle Networks (IVNs) and external environments, intelligent vehicles are increasingly vulnerable to sophisticated external network attacks. This paper proposes ATHENA, the first IVN intrusion detection framework that adopts a vehicle-cloud integrated architecture to achieve better security performance for the resource-constrained vehicular environment. Specifically, in the cloud with sufficient resources, ATHENA uses the clustering method of multi-distribution mixture model combined with deep data mining technology to generate the raw Payload Rule Bank of IVN CAN messages, and then improves the rule quality with the help of exploitation on the first-principled physical knowledge of the vehicle system, after which the payload rules are periodically sent to the vehicle terminal. At the vehicle terminal, a simple LSTM component is used to generate the Time Rule Bank representing the long-term time series dependencies and the periodic characteristics of CAN messages, but not for any detection tasks as in traditional usage scenarios, where only the generated time rules are the candidates for further IVN intrusion detection tasks. Based on both the payload and time rules generated from cloud and vehicle terminal, ATHENA can achieve efficient intrusion detection capability by simple rule-base matching operations, rather than using complex black-box reasoning of resource-intensive neural network models, which is in fact only used for rule logic generation phase instead of the actual intrusion detection phase in our framework. Comparative experimental results on the ROAD dataset, which is current the most outstanding real-world in-vehicle CAN dataset covering new instances of sophisticated and stealthy masquerade attacks, demonstrate ATHENA significantly outperforms the state-of-the-art IVN intrusion detection methods in detecting complex attacks. We make the code available at https://***/wangkai-tech23/ATHENA. Copyright

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

QDL: Quantitative Dynamic Latency Model in Permissioned Blockchain System 22

QDL: Quantitative Dynamic Latency Model in Permissioned Bloc...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Wei, Jiacheng Wang, Qingmei Wang, Zheng Beihang University School of Artificial Intelligence Beijing China Beihang University Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing China University of Science and Technology Beijing National Center for Materials Service Safety Beijing China Shanghai Jiao Tong University Institute of Cyber Science and Technology China Shanghai Key Laboratory of Integrated Administration Technologies for Information Security China

ISBN: (纸本)9798331509712

Latency, as a critical attribute influencing scalability and consistency in blockchain systems, has attracted significant research attention. This paper addresses the issue of latency evaluation by presenting a novel framework. We thoroughly analyze the factors affecting latency in blockchain system, including concurrency, consistency, and contention. To accurately model the correlation between latency and the quantity of nodes in permissioned blockchain setup, we introduce the Latency Regression Loss (LRL) function. By utilizing Newton's interpolation and least squares methods, we determine the hyperparameters. Subsequently, we devise the framework for the Quantitative Dynamic Latency (QDL) evaluation model, which accounts for both the growth rate and magnitude of latency. Utilizing the parameters derived from the LRL function facilitated the calculation of latency growth rate, allowing for a comprehensive evaluation of latency. Finally, we validated the accuracy of the LRL function through extensive experiments and simulated the adaptability of the QDL model in latency assessment. © 2024 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Anchor-Based Discriminative Dual Distribution Calibration for Transductive Zero-Shot Learning

SSRN

引用

SSRN 2023年

作者： Zhang, Yi Huang, Sheng Yang, Wanli Tang, Wenhao Zhang, Xiaohong Yang, Dan School of Big Data and Software Engineering Chongqing University No.55 Daxuecheng South Rd. Chongqing Shapingba401331 China Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University No.174 Shazhengjie Chongqing Shapingba400044 China

Zero-shot learning (ZSL) is machine learning task to recognize samples from classes that are not observed during training. Transductive ZSL (TZSL) is a more realistic and effective paradigm that leverages unlabeled unseen data during training to reduce the bias towards seen classes. However, most existing TZSL methods neglect the information gap between visual and semantic spaces, and thus fail to generate distribution-consistent unseen features. To address this issue, we propose a novel TZSL approach named Anchorbased Discriminative Dual Distribution Calibrated Feature Generative Network (AD3C-FGN), which performs anchor-based distribution calibration in both visual and semantic spaces for improving generalization ability of the model. In AD3C-FGN, we adopt conditional generative adversarial network with an unseen discriminator to construct a Y-shape generation model that mitigates the domain shift problem. Moreover, an AD3C module is elaborated for calibrating the distribution of generated and real samples in both visual and semantic spaces with real sample anchors, and also enhance the discriminability of the generated samples. AD3C enforces the generated sample to be closer to its homogenous anchor but farther away from inhomogeneous anchors in both spaces. Extensive experimental results on six popular ZSL benchmarks demonstrate that our method achieves promising performances in different settings. © 2023, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Push-Pull Method for Decentralized Optimization via State Decomposition

arXiv

引用

arXiv 2023年

作者： Cheng, Huqiang Liao, Xiaofeng Li, Huaqing Zhao, You Key Laboratory of Dependable Services Computing in Cyber Physical Society Ministry of Education College of Computer Science Chongqing University Chongqing400044 China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China

Distributed optimization is manifesting great potential in multiple fields, e.g., machine learning, control, and resource allocation. Existing decentralized optimization algorithms require sharing explicit state information among the agents, which raises the risk of private information leakage. To ensure privacy security, combining information security mechanisms, such as differential privacy and homomorphic encryption, with traditional decentralized optimization algorithms is a commonly used means. However, this would either sacrifice optimization accuracy or incur heavy computational burden. To overcome these shortcomings, we develop a novel privacy-preserving decentralized optimization algorithm, called PPSD, that combines gradient tracking with a state decomposition mechanism. Specifically, each agent decomposes its state associated with the gradient into two substates. One substate is used for interaction with neighboring agents, and the other substate containing private information acts only on the first substate and thus is entirely agnostic to other agents. For the strongly convex and smooth objective functions, PPSD attains a R-linear convergence rate. Moreover, the algorithm can preserve the agents’ private information from being leaked to honest-but-curious neighbors. Simulations further confirm the results. © 2023, CC BY.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

TKCA:a timely keystroke-based continuous user authentication with short keystroke sequence in uncontrolled settings

引用

cybersecurity 2021年第1期4卷 177-192页

作者： Lulu Yang Chen Li Ruibang You Bibo Tu Linghui Li Institute of Information Engineering Chinese Academy of Sciences100093 BeijingChina School of Cyber Security University of Chinese Academy of Sciences100049 BeijingChina Key Laboratory of Trustworthy Distributed Computing and Service Ministry of EducationBeijing University of Posts and Telecommunications100876 BeijingChina

keystroke-based behavioral biometrics have been proven effective for continuous user *** state-of-the-art algorithms have achieved outstanding results in long text or short text collected by doing some *** remains a considerable challenge to authenticate users continuously and accurately with short keystroke inputs collected in uncontrolled *** this work,we propose a Timely keystroke-based method for Continuous user Authentication,named *** integrates the key name and two kinds of timing features through an embedding *** it captures the relationship between context keystrokes by the Bidirectional Long Short-Term Memory(Bi-LSTM)*** conduct a series of experiments to validate it on a public dataset-the Clarkson II dataset collected in a completely uncontrolled and natural *** results show that the proposed TKCA achieves state-of-the-art performance with 8.28%of EER when using only 30 keystrokes and 2.78%of EER when using 190 keystrokes.

关键词： keystroke dynamics Continuous user authentication Embedding LSTM Bi-LSTM

来源：评论

学校读者我要写书评

暂无评论

TGCN-DA: A Temporal Graph Convolutional Network with Data Augmentation for High Accuracy Insider Threat Detection

TGCN-DA: A Temporal Graph Convolutional Network with Data Au...

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Ximing Li Linghui Li Xiaoyong Li Binsi Cai Bingyu Li Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China School of Cyber Science and Technology Beihang University Beijing China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Insider threats present a formidable challenge to cybersecurity, as insiders possess the privileges and information necessary to execute diverse attacks. A comprehensive analysis of user behavior, including behavioral features, sequences, and inter-user relationships, is required for effective insider threat detection. However, few existing methods consider these features in an integrated manner, which could result in high false positives. To further improve the accuracy of insider threat detection, we propose a novel framework for insider threat detection based on a temporal graph convolutional network with data augmentation (referred to as TGCN-DA), which integrates the exploration of structural information among users and simultaneously captures the behavior temporal dependencies. In particular, we introduce an edge predictor to encode user structural information and strengthen intra-class edges among users based on the representation of users’ behavior. Additionally, the GCN with temporal feature mechanism is leveraged to learn dynamic changes in users’ behavior to capture behavior temporal dependence. Extensive experiments demonstrate that our proposed TGCN-DA outperforms other state-of-the-art methods and achieves higher accuracy in the task of insider threat detection.

关键词： Data privacy Image edge detection Neural networks Data augmentation Feature extraction Threat assessment Task analysis

来源：评论

学校读者我要写书评

暂无评论

A Joint Framework for Knowledge Extraction from Flight Training Comments 17th

A Joint Framework for Knowledge Extraction from Flight Tra...

引用

17th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2022

作者： Zhang, Yuxuan Shang, Jiaxing Zheng, Linjiang Wu, Quanwang Cao, Weiwei Sun, Hong College of Computer Science Chongqing University Chongqing China Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing University Chongqing China Key Laboratory of Flight Techniques and Flight Safety Civil Aviation Flight University of China Guanghan China Flight Technology and Flight Safety Research Base Civil Aviation Flight University of China Guanghan China

ISBN: (纸本)9789819923557

The flight training comments are textual evaluation from the instructor to the flight training students. Extracting the assessment experience and knowledge from the flight training comments can help improve the flight training level. To this end, a joint extraction framework is proposed in this paper. For the model input, we use an end-to-end grid tagging scheme as the decoding algorithm to extract aspect terms, opinion terms and opinion pairs simultaneously. Considering the continuity of terms, we propose WoBERT as encoder, which modifies the pre-trained word segmentation based on BERT, and realizes Chinese word segmentation at word-level granularity. We conduct extensive experiments on a real flight training comments dataset. The results show that the model with WoBERT as the encoder achieves the best performance with a F1-score of 0.647, which can be used for the task of knowledge extraction from the flight training comments. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Modeling Method for Sampling Zeros of Sampled-data System with Time Delay in Generalized Sample Hold

引用

IFAC-PapersOnLine 2023年第2期56卷 9799-9805页

作者： Minghui Ou Shan Liang Zhiyong Yang Zhenjie Yan Zhiyong Li School of Big Data and Internet of Things Chongqing Vocational Institute of Engineering Chongqing 402260 PR China College of Automation Chongqing University Chongqing 400044 PR China Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing 400044 PR China. School of Electrical Engineering Southwest Jiaotong University Chengdu 611756 PR China

Unstable zeros are widely known to dramatically curb the performance of controllers and the direct applications of several control algorithms. Time delay is a crucial research topic due to the prevalence of communication and computational delays in the control process. In particular, time delay exacerbates the possibility of continuous-time systems with stable zeros transforming into discrete-time systems with unstable zeros. For continuous-time systems with a relative degree greater than or equal to two, at least one zero of the corresponding discrete-time system converges to either marginally stable or unstable locations as the sampling time approaches zero. This study investigates the sampling zeros of discrete-time systems in the case of a generalized sample hold function (GSHF) with time delay. Moreover, it presents a novel modeling method and stability conditions of the limiting zeros for the discrete-time system. The results demonstrate that the stable properties of zeros for the time delay systems can be preserved in the discretization process when GSHF is applied for signal reconstruction when zero-order hold fails to do so. Finally, numerical examples are provided to illustrate the effectiveness of the proposed method in this study.

关键词： Sampling zeros stability generalized sample hold function (GSHF) time delay. sampled-data system

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：