检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jingtao Tang Chun Sun Xinyu Zhang Shanghai Key Laboratory of Trustworthy Computing Engineering Research Center of Software/Hardware Co-Design Technology and Application (MoE) and School of Software Engineering East China Normal University Shanghai

For large-scale tasks, coverage path planning (CPP) can benefit greatly from multiple robots. In this paper, we present an efficient algorithm MSTC∗ for multi-robot coverage path planning (mCPP) based on spiral spanni... 详细信息

For large-scale tasks, coverage path planning (CPP) can benefit greatly from multiple robots. In this paper, we present an efficient algorithm MSTC^∗ for multi-robot coverage path planning (mCPP) based on spiral spanning tree coverage (Spiral-STC). Our algorithm incorporates strict physical constraints like terrain traversability and material load capacity. We compare our algorithm against the state-of-the-art in mCPP for regular grid maps and real field terrains in simulation environments. The experimental results show that our method significantly outperforms existing spiral-STC based mCPP methods. Our algorithm can find a set of well-balanced workload distributions for all robots and therefore, achieve the overall minimum time to complete the coverage.

关键词： Spirals Automation Conferences Path planning Task analysis Robots Load modeling

来源：评论

学校读者我要写书评

暂无评论

Password Guessing Attack Based on Probabilistic Context Free Algorithm

Password Guessing Attack Based on Probabilistic Context Free...

引用

International Conference on Computer and Communications (ICCC)

作者： Xuejing Jiang Xun Sun Qiuming Liu Jiangxi Vocational and Technical College of Information Application Nanchang China School of Software Engineering Jiangxi University of Science and Technology Nanchang China Nanchang Key laboratory of Virtual Digital Factory and Cultural Communications Nanchang China

Password is the primary way of identity authentication at present. The password security is closely related to more than 4 billion netizen all over the world. Password contains lots of semantic information, so how to extract the semantic of password and apply it to password guessing algorithm can further uncover the behavior preference of users in creating passwords, and improve the cracking rate of guessing attacks. We analyze the background and present situation of password security research, and determine the general steps and basic framework of password guessing algorithm based on natural language processing technology. We introduce the relevant preparatory knowledge and make statistical analysis on many password data sets. The popular password, password grammar, password pattern, character composition, length distribution, character distribution and semantic information of password data set are analyzed. We propose a password guessing algorithm based on probabilistic context free algorithm. The actual leaked password data set is selected for training and testing, and several groups of password guessing contrast experiments are set up. The results prove the effectiveness of proposed algorithm.

关键词： Training Statistical analysis Semantics Passwords Probabilistic logic Natural language processing Grammar

来源：评论

学校读者我要写书评

暂无评论

Federated Reinforcement Learning for Electric Vehicles Charging Control on Distribution Networks

arXiv

引用

arXiv 2023年

作者： Qian, Junkai Jiang, Yuning Liu, Xin Wang, Qiong Wang, Ting Shi, Yuanming Chen, Wei The MoE Engineering Research Center of Software/Hardware Co-design Technology and Application The Shanghai Key Lab. of Trustworthy Computing East China Normal University China The Automatic Control Laboratory EPFL Switzerland The School of Information Science and Technology ShanghaiTech University China The State Grid Beijing Electric Power Company China The Department of Electronic Engineering Tsinghua University China

With the growing popularity of electric vehicles (EVs), maintaining power grid stability has become a significant challenge. To address this issue, EV charging control strategies have been developed to manage the switch between vehicle-to-grid (V2G) and grid-to-vehicle (G2V) modes for EVs. In this context, multi-agent deep reinforcement learning (MADRL) has proven its effectiveness in EV charging control. However, existing MADRL-based approaches fail to consider the natural power flow of EV charging/discharging in the distribution network and ignore driver privacy. To deal with these problems, this paper proposes a novel approach that combines multi-EV charging/discharging with a radial distribution network (RDN) operating under optimal power flow (OPF) to distribute power flow in real time. A mathematical model is developed to describe the RDN load. The EV charging control problem is formulated as a Markov Decision Process (MDP) to find an optimal charging control strategy that balances V2G profits, RDN load, and driver anxiety. To effectively learn the optimal EV charging control strategy, a federated deep reinforcement learning algorithm named FedSAC is further proposed. Comprehensive simulation results demonstrate the effectiveness and superiority of our proposed algorithm in terms of the diversity of the charging control strategy, the power fluctuations on RDN, the convergence efficiency, and the generalization ability. © 2023, CC BY-NC-SA.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

SFedXL: Semi-Synchronous Federated Learning With Cross-Sharpness and Layer-Freezing

引用

IEEE Internet of Things Journal 2025年

作者： Zhao, Mingxiong Zhao, Shihao Feng, Chenyuan Yang, Howard H. Niyato, Dusit Quek, Tony Q. S. Yunnan University National Pilot School of Software Kunming650500 China Ministry of Education Engineering Research Center of Integration and Application of Digital Learning Technology Beijing100039 China Ministry of Education Engineering Research Center of Cyberspace Kunming650504 China Yunnan University of Finance and Economics Yunnan Key Laboratory of Service Computing Kunming650221 China EURECOM Sophia Antipolis06410 France Zhejiang University University of Illinois Urbana-Champaign Institute Zhejiang University Haining314400 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore

Federated learning (FL) emerges as a potential solution for enabling multiple terminal devices to collaboratively accomplish computational tasks within an Unmanned Aerial Vehicle (UAV) swarm. However, traditional FL approaches, predicated on synchronous data aggregation, are not feasible for a UAV swarm owing to the inherently variable and dynamic nature of their communication networks compared with terrestrial systems. Furthermore, the data procured by UAVs is often highly heterogeneous, attributable to disparities in deployment environments and device attributes. Considering the distinct flight paths and unique operational conditions encountered by different UAVs, a considerable amount of data remains unlabeled. To tackle the challenges associated with asynchronous operations and the prevalence of unlabeled data, we introduce a novel framework termed Semi-synchronous FL with Cross-Sharpness and Layer-Freezing (SFedXL), tailored for a UAV swarm. In particular, we devise a cross-sharpness model training strategy aimed at optimizing the utilization of both labeled and unlabeled datasets. Additionally, we propose an innovative semi-synchronous model aggregation protocol, complemented by client-specific layer-freezing and client cluster scheduling, designed to expedite the training process. Our simulation results indicate that the proposed algorithm surpasses current FL methods in terms of object recognition accuracy and communication efficiency, albeit with a trade-off of increased local computation latency. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Using surrounding text of formula towards more accurate mathematical information retrieval 33

Using surrounding text of formula towards more accurate math...

引用

33rd International Conference on software engineering and Knowledge engineering, SEKE 2021

作者： Chen, Cheng Dai, Yifan Shen, Yuqi Cai, Jinfang Chen, Liangyu Engineering Research Center of Software Hardware Co-Design Technology and Application East China Normal University Shanghai China Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China Institute of Vocational and Adult Education East China Normal University Shanghai China

ISBN: (纸本)1891706527

Formula retrieval is an important research topic in Mathematical Information Retrieval (MIR). Most studies have focused on comparing formulae to determine the similarity between mathematical documents. However, two similar formulae may appear in completely different knowledge domains and have different meanings. Based on N-ary Tree-based Formula Embedding Model (NTFEM), we introduce a new hybrid retrieval model combining formula with its surrounding text for more accurate retrieval. Using keywords extraction technology, we extract keywords from text around the formula which can supplement the semantic information of formula. Then we get the representation vectors of keywords by FastText N-gram embedding model, and the representation vectors of formulae by NTFEM. Finally, documents are first sorted according to the similarity of keywords, and then the ranking results are optimized by formula similarity. Experimental results show that the accuracy of top-10 results is at least 20% higher than that of NTFEM and can be 50% in some specific topics. © 2021 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Model-enhanced vector index 23

Model-enhanced vector index

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Hailin Zhang Yujing Wang Qi Chen Ruiheng Chang Ting Zhang Ziming Miao Yingyan Hou Yang Ding Xupeng Miao Haonan Wang Bochen Pang Yuefeng Zhan Hao Sun Weiwei Deng Qi Zhang Fan Yang Xing Xie Mao Yang Bin Cui School of Computer Science & Key Lab of High Confidence Software Technologies Peking University and Microsoft Microsoft Microsoft and Aerospace Information Research Institute & Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences Microsoft and Institute of Information Engineering Chinese Academy of Sciences Carnegie Mellon University National University of Singapore School of Computer Science & Key Lab of High Confidence Software Technologies Peking University and National Engineering Laboratory for Big Data Analysis and Applications Peking University

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with end-to-end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Model-enhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embedding-based models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the Current State of Privacy Risks in Children’s Mobile applications

Research on the Current State of Privacy Risks in Children’...

引用

Computer technology and Information Science (ISCTIS), International Symposium on

作者： Xinrui Geng Tao Liu Chong Shang Jianxiang Chen Yueran Lu Yan Zhang Lifeng Wang School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou China Key Laboratory of Mobile Application Innovation and Governance Technology MIIT Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Agricultural Engineering Shanxi Agricultural University China School of Software Engineering Tianjin Normal University Tianjin China Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences Beijing China Shandong Yeda Smart City Operation Technology Co. Ltd. Shandong China

ISBN: (数字)9798350354560

ISBN: (纸本)9798350354577

In the digital age, children increasingly access a vast world of information through mobile applications. Despite global regulations and protective measures by app stores, privacy breaches in these apps persist. This study investigates privacy issues and threats in children’s mobile applications by comparing APKs and legal provisions across different countries. It examines 70 representative children’s apps from China, Europe, the U.S., and Japan through static code analysis and dynamic runtime testing. Using a mixed-methods approach, the research identifies integrated third-party services, data transmission protocols, permission requests, and conducts code audits to assess privacy compliance. It also simulates real usage scenarios to track data flow and detect unauthorized data collection and sharing practices. Furthermore, the study compares national privacy laws, focusing on data minimization, parental consent mechanisms, data encryption, and storage duration regulations. The goal is to provide empirical evidence and recommendations for optimizing global children’s online privacy protection policies.

关键词： Pediatrics Data privacy Codes Law Europe Privacy breach Regulation Mobile applications Protection Testing

来源：评论

学校读者我要写书评

暂无评论

STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction

arXiv

引用

arXiv 2022年

作者： Ji, Jiahao Wang, Jingyuan Jiang, Zhe Jiang, Jiawei Zhang, Hu State Key Laboratory of Software Development Environment School of Computer Science & Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Department of Computer & Information Science & Engineering The University of Florida United States MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science & Engineering Beihang University Beijing China

High-performance traffic flow prediction model designing, a core technology of Intelligent Transportation System, is a long-standing but still challenging task for industrial and academic communities. The lack of integration between physical principles and data-driven models is an important reason for limiting the development of this field. In the literature, physics-based methods can usually provide a clear interpretation of the dynamic process of traffic flow systems but are with limited accuracy, while data-driven methods, especially deep learning with black-box structures, can achieve improved performance but can not be fully trusted due to lack of a reasonable physical basis. To bridge the gap between purely data-driven and physics-driven approaches, we propose a physics-guided deep learning model named Spatio- Temporal Differential Equation Network (STDEN), which casts the physical mechanism of traffic flow dynamics into a deep neural network framework. Specifically, we assume the traffic flow on road networks is driven by a latent potential energy field (like water flows are driven by the gravity field), and model the spatio-temporal dynamic process of the potential energy field as a differential equation network. STDEN absorbs both the performance advantage of data-driven models and the interpretability of physics-based models, so is named a physics-guided prediction model. Experiments on three real-world traffic datasets in Beijing show that our model outperforms state-of-the-art baselines by a significant margin. A case study further verifies that STDEN can capture the mechanism of urban traffic and generate accurate predictions with physical meaning. The proposed framework of differential equation network modeling may also cast light on other similar applications. Copyright © 2022, The Authors. All rights reserved.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

How to respond to emerging threats of cyberspace security via social engineering? A novel paradigm to solve cyberspace security issues

TechRxiv

引用

TechRxiv 2022年

作者： Lin, Hao Wang, Chun-Dong Gao, Hao-Yu School of Computer Science and Engineering Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Intelligence Computing Novel Software Technology Ministry of Education Tianjin China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China College of Data Science and Application Inner Mongolia University of Technology Hohhot China

Cybersecurity researchers always ignore the "people" behind the issues when dealing with cyberspace security issues. The human and technological aspects of cyberspace security must be simultaneously addressed to enable a secure cyber environment. Social engineering is a discipline whose research object is people, and the combination of social engineering and cyberspace security can provide new solution ideas for lots of cyberspace security issues. This paper attempts to answer the question —— "How to solve cyberspace security issues via social engineering?" We briefly review existing frameworks for social engineering attacks and propose a novel, recursive, and iterative framework for social engineering attacks in cyberspace. The existing research achievements of combination of social engineering and cyberspace security were reviewed in the order of cyber personality, hacker psychology, human flesh search, and social engineering defense. To answer this question, we summarized four "guidelines" for using social engineering. Finally, we look ahead, give our thoughts, and discuss answers of the question and future research. It is aimed at getting more researchers of cyberspace security and social science to pay attention to this field. © 2022, CC BY.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A Facial Expression Recognition Method based on Residual Separable Convolutional Neural Network

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第1期7卷 59-69页

作者： Xu, Xiaoyu Cui, Jianfeng Chen, Xuhui Chen, Chin-Ling College of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China College of Software Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Internet of things application technology Xiamen361024 China Xiamen City University of Technology Xiamen361024 China School of Computer and Information Engineering Xiamen City University of Technology Xiamen361024 China School of Information Engineering Changchun Sci-Tech University Changchun130600 China Department of Computer Science and Information Engineering Chaoyang University of Technology Taichung41349 Taiwan

Facial expression recognition is a typical application of artificial intelligence. It has practical value and commercial prospects in application scenarios such as safe driving, medical assistance, online classrooms, and human-computer interaction. Traditional convolutional neural networks have low accuracy in facial expression recognition. To solve this problem, we propose a residual separable convolutional neural network, which combines depth-wise separable convolution with an improved residual network. When transmitting feature information, it fuses facial expression features through skip connection and utilizes global average pooling to reduce dimension, thus preventing gradient disappearance. We conduct experiments based on the data set FER2013. The results show that it can improve the accuracy of facial expression recognition, reduce model parameters and raise the utilization efficiency of the parameters effectively. © The Authors.

关键词： Convolution

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：