检索结果-内蒙古大学图书馆

4th Annual International Conference on Data Science and Business Analytics, ICDSBA 2020

作者： Hou, Zhansheng Sun, Shijun Peng, Lin Yu, Zhen Song, Jinyin Wang, He Xu, Min Wang, Gang Bao, Xingchuan Yu, Hai He, Zhimin Zhu, Liang Xu, Xiyuan Zhang, Zehao Tang, Shiyang Global Energy Interconnection Research Institute State Grid Key Laboratory of Information Network Security Nanjing China State Grid ZheJiang Electric Power Co. Ltd Hangzhou China

ISBN: (纸本)9781728181646

At present domestic emergency information interaction lack of flexibility, after a natural disaster, on-site rescue workers with the rescue headquarters, emergency command center, sharing of information between were studied based on the scene of the electric power emergency mobile information real-time interactive methods, design a kind of power at the scene of the emergency mobile friendly each other, are at the scene of the emergency and emergency command center cluster information real-time interactive technology, gives the power emergency field information real-time interactive system prototype and power at the scene of the emergency information real-time interactive software and hardware integration solutions, to build the efficient method of multi-type information submitted by emergency disposal across departments and information interaction ability. © 2020 IEEE.

关键词： Disasters

来源：评论

学校读者我要写书评

暂无评论

Data Access Control Method of power Terminal Based on Trust and Reputation

Data Access Control Method of Power Terminal Based on Trust ...

引用

International Symposium on Computer Science and Intelligent Controls (ISCSIC)

作者： Sheng Wang JuLing Zhang Yong Li LingHao Zhang Qing Zhang Jian Zhou Electric Power Research Institute of State Grid Sichuan Electric Power Company Chengdu China Grid Digitizing Technology Department State Grid Smart Grid Research Institute Co. Ltd. State Grid Key Laboratory of Information & Network Security Nanjing State Grid Sichuan Electric Power Company Chengdu China

Aiming at the problems of poor data confidentiality, complex communication overhead and large amount of computation in traditional power terminal data access control, a data access control method of power terminal based on trust and reputation was proposed. Firstly, a flexible data access control system of power terminal was designed based on cloud computing technology, and key generation, key segmentation, proxy re-encryption and decryption were adopted to obtain the trust level and user reputation of the end users. Then, the data access of power terminal was controlled. Finally, the security analysis and performance analysis of the user’s trust and reputation evaluation results were carried out through the encryption system. Experimental results showed that the proposed method can effectively reduce the communication overhead and computational complexity of data access, improve data confidentiality, and reduce the application cost of power terminal equipment, and has stability and effectiveness.

关键词： Access control Data privacy Costs Scalability Public key Stability analysis Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Channel Drop Out:A Simple Way to Prevent CNN from Overfitting in Motor Imagery Based BCI

Channel Drop Out:A Simple Way to Prevent CNN from Overfittin...

引用

2021国际计算机前沿大会

作者： Jing Luo Yaojie Wang Rong Xu Guangming Liu Xiaofan Wang Yijing Gong Shaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and EngineeringXi'an University of Technology Shaanxi Province Institute of Water Resources and Electric Power Investigation and Design

With the development of deep learning,many motor imagery brain-computer interfaces based on convolutional neural networks(CNNs) show outstanding ***,the trial number of EEG in the training set is usually limited,and redundancy extensively exists in multiple channel ***,overfitting often appears in CNN based motor imagery recognition model and greatly affects the performances of *** this paper,channel drop out is proposed to address this problem by data augmentation and ensemble ***,one of all EEG channels will be dropped and replaced by the mean signal of all EEG *** this way,the trial number in the training set was enlarged by channel drop *** at the testing stage,all the EEG trials processed by channel drop out were fed to the CNN model and the average output probabilities of them were applied to determine the *** experiments were conducted on two popular CNN models applied in motor imagery BCI and BCI Competition IV datasets 2 a to verify the performances of the proposed channel drop out *** results show that average improvements provided by channel drop out in two-category or four-category motor imagery classification are 2.83%and 2.65% compared with the original CNN *** the channel drop out approach significantly improves the performances of motor imagery based BCI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SCARE of Secret Ciphers under Rough Leakage Model

引用

security and Communication networks 2023年第1期2023卷

作者： Wang, Mengxing Tang, Ming Zhang, Xige Chen, Qi Ding, Haili Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Hubei Wuhan430000 China Beijing Smartchip Microelectronics Technology Co. Ltd. Beijing100192 China Marketing Service Center State Grid Electric Power Co. Ltd. Ningxia750002 China

Most previousside-channel analysis-based reverse engineering (SCARE) methods were based on collision attack. However, the collision-based methods generally need noise-free traces and can hardly be verified by realistic implementations. This paper proposes a novel SCARE, which is named as OSHDG-SCARE, targeting on secret S-box. We define a graph as OSHDG (one-step HD graph) to recover the parameters of any secret S-box. Due to the redundancy of OSHDG, the multiple paths can filter the correct results and improve the success rate of the reverse method even when the samples deviate from leakage model. We classify the deviation of side channel signal as two types, which are the gap between real leakage and leakage model, and measurement noise. Experiments are performed on real power traces satisfying the inaccurate HW (Hamming Weight) leakage model from a software implementation of AES-like cipher. OSHDG-SCARE recovers the secret S-box when the deviation rate of traces is 1.45%. © 2023 Mengxing Wang et al.

关键词： Side channel attack

来源：评论

学校读者我要写书评

暂无评论

Social-enhanced recommendation using graph-based contrastive learning

Social-enhanced recommendation using graph-based contrastive...

引用

IEEE International Conference on High Performance computing and Communications (HPCC)

作者： Peng Xue Qian Gao Jun Fan Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan Shandong China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan Shandong China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan Shandong China China Telecom Digital Intelligence Techonology Co Ltd Jinan Shandong China

The social network-based recommendation model use social network information to mitigate data sparsity issues and improve the accuracy of recommendation models. However, In most social network-based recommendation algorithms, the social neighbors' contributions are difficult to distinguish from the central user's, neglecting hidden correlations in social infor-mation. In order to solve this problem, this paper presents a graph-based contrastive learning framework for social-enhanced recommendation (SoGCLR) that utilizes implicit social information captured by a new social relation attention mechanism, en-rich user representations, and improve model robustness through graph-based contrastive learning. Specifically, the paper captures the degree of contribution of each neighbor in the social graph to the central user through a social relation attention layer, thus obtaining hidden correlations in social information, and further integrates this with user information in the user-item interaction graph to enrich user representations. In addition, the paper incorporates graph-based contrastive learning into the recommendation task using cross-layer contrastive learning, calculating contrastive loss and mapping nodes with similar but different exposure rates to nearby regions to mitigate exposure bias issues. Results from Ciao and Epinions demonstrate that SoGCLR reduces RMSE and MAE by 1.33% to 1.84% compared with baseline models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Load-Balancing Algorithm for power Internet of Things Resources Based on the Improved Weighted Minimum Number of Connections 7th

A Load-Balancing Algorithm for Power Internet of Things Reso...

引用

7th International Conference on Artificial Intelligence and security, ICAIS 2021

作者： Zhang, Mingming Mao, Jiaming Chen, Lu Li, Nige Fan, Lei Shuang, Leshan State Grid Jiangsu Electric Power Co. Ltd. Information and Telecommunication Branch Nanjing Jiangsu210003 China Institute of Information and Communication Global Energy Interconnection Research Institute State Grid Key Laboratory of Information and Network Security Nanjing Jiangsu210003 China Broadband Wireless Communication Technology Engineering Research Center of the Ministry of Education Nanjing University of Posts and Telecommunications Nanjing Jiangsu210003 China

ISBN: (纸本)9783030786113

With the gradual increase of user visits in the power Internet of Things, load imbalances often appear, affecting server operation efficiency. This article is an improvement based on the weighted minimum number of connections algorithm. It sets weights for a group of servers and proposes two reference values: range and variance, and sets corresponding thresholds. Only the servers that exceed the threshold are used for the following operations. All data use re-hashing to deal with conflicts, and this process is repeated until an idle server is found to process the data. The simulation results show that the improved algorithm can effectively balance the user's task requests, realize the entire system's load balance, have good stability, and achieve the expected effect. © 2021, Springer Nature Switzerland AG.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

LI-FPN: Depression and Anxiety Detection from Learning and Imitation

LI-FPN: Depression and Anxiety Detection from Learning and I...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xingyun Li Lin Lu Xinyu Yi Hao Wang Yunshao Zheng Yanhong Yu Qingxiang Wang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Mental Health Center Jinan China Shandong University of Traditional Chinese Medicine Jinan China

With the rise in societal pressures, depression and anxiety have increasingly become prominent mental health conditions impacting people’s lives. To enhance the efficacy of automatic detection for these disorders, we have developed an experimental framework called the Voluntary Facial Expression Mimicry(VFEM). This framework led to the creation of the VFEM Dataset, which supports related research endeavors. Subsequently, we introduce the LI-FPN designed specifically for the automatic identification of depression and anxiety disorders. The LI-FPN comprises two core components: the Learning and Imitation Module(LIM) and the Spatio-temporal Feature Pyramid network(STFPN). Within the LIM, we leverage sequence features to facilitate comprehensive feature extraction through learning and imitation steps. The STFPN is designed to focus on outliers in multi-scale features for further screening. Compared with traditional attention methods, LI-FPN is more suitable for processing sequence data features and small sample datasets. Upon training using the VFEM Dataset, the LI-FPN achieves impressive accuracies: 0.850 for depression detection, 0.835 for anxiety detection, and 0.786 for co-occurrence detection of depression and anxiety. Meanwhile, LI-FPN also achieves SOAT results on AVEC2014 dataset. The source code for LI-FPN is accessible at https://***/muzixingyun/LI-FPN

关键词：

来源：评论

学校读者我要写书评

暂无评论

Auction Theory and Game Theory Based Pricing of Edge computing Resources: A Survey

引用

IEEE Internet of Things Journal 2025年

作者： Yu, Jiguo Liu, Shun Zou, Yifei Wang, Guijuan Hu, Chunqiang University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China Qilu University of Technology Big Data Institute Jinan250353 China Qufu Normal University School of Computer Science Shandong Rizhao China Shandong University School of Computer Science and Technology Shandong Qingdao266237 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250353 China Chongqing University School of Big Data and Software Engineering Chongqing400044 China

The proliferation of Internet of Things (IoT) devices and edge computing applications has heightened the demand for efficient resource allocation and pricing mechanisms. Effective pricing strategies play a crucial role in optimizing resource utilization, reducing latency, and ensuring fair resource distribution among users. Both auction theory and game theory have emerged as fundamental economic frameworks for designing pricing mechanisms in edge computing. This paper presents a comprehensive survey of pricing strategies that leverage both auction and game theory, systematically categorizing existing research based on auction mechanisms and game-theoretic models. Unlike previous surveys that focus solely on auction-based pricing, this work integrates game-theoretic perspectives, providing a holistic analysis of strategic interactions in edge computing resource allocation. Furthermore, we discuss key challenges, emerging trends, and future research directions aimed at enhancing efficiency, fairness, and privacy protection in cloud-edge collaborative computing environments. © 2014 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

External Knowledge Is Not Always Needed: An Adaptive Retrieval Augmented Generation Method

External Knowledge Is Not Always Needed: An Adaptive Retriev...

引用

Artificial Intelligence and Intelligent Manufacturing (AIIM), International Symposium on

作者： Wenbo Guan Jiyu Lu Qinyu Feng Xiaoqian Li Jun Zhou Key Laboratory of Speech Acoustics and Content Understanding Institute of Acoustics Chinese Academy of Sciences Beijing China Chinese Academy of Sciences Institute of Information Engineering Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China China Southern Power Grid Artificial Intelligence Technology Co. Ltd Guangzhou China School of Computing Science and Engineering South China University of Technology Guangzhou China

ISBN: (数字)9798331541729

ISBN: (纸本)9798331541736

Retrieval augmented generation (RAG), by integrating external knowledge with large language models (LLMs), has become a common practice to alleviate LLMs’ hallucination problem. The performance of RAG, however, depends on the capability of the adopted information retriever to a large extent. Specifically, a good information retriever can manage to obtain the most useful information from the external knowledge, which will then enhance the quality of generated content from LLMs and vice versa. Since the vanilla RAG will always leverage the retrieved information to assist with LLMs’ content generation despite of its usefulness, when combined with a retriever of limited capacity, therefore, the vanilla RAG will not benefit LLMs’ content generation sometimes but introduce additional noise, having a negative impact on the final performance. To address this problem, this paper proposes a novel adaptive RAG method which first uses LLMs to determine the usefulness of the retrieved information and then let LLMs to generate content on their own without the retrieved information if it is useless. Experimental results on four datasets demonstrate the effectiveness of the proposed adaptive RAG method with information retrievers of various capabilities, improving the performance of the vanilla RAG by an obvious margin.

关键词： Large language models Retrieval augmented generation Noise Manufacturing

来源：评论

学校读者我要写书评

暂无评论

Multi-Channel Hypergraph Convolution Group Recommendation with Member information Enhancement

Multi-Channel Hypergraph Convolution Group Recommendation wi...

引用

IEEE International Conference on High Performance computing and Communications (HPCC)

作者： Tianhao Chen Qian Gao Jun Fan Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan Shandong China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan Shandong China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan Shandong China China Telecom Digital Intelligence Techonology Co Ltd Jinan Shandong China

Group recommendation involves comprehensively considering various aspects, including members and items, to predict the overall interests of a group and recommend suitable items through a recommendation system. With the rapid evolution of the Internet, online group activities have become increasingly prevalent, making group recommendation a highly discussed topic within the realm of recommendation systems. However, current research in group recommendation still confronts the following challenges. Firstly, a predominant portion of group recommendation research focuses solely on aggregating group-level information, neglecting the valuable contribution of higher-order member-level insights to group recommendation. Moreover, some aggregation strategies overly prioritize fairness, thereby disregarding common real-world patterns. Secondly, previous studies have primarily relied on aggregating individual member interests to establish group preferences, lacking a holistic consideration of group dynamics. To tackle these challenges, this study introduces an innovative approach by implementing multi-channel hypergraph convolution within the member perspective. This approach aims to effectively extract higher-order insights from members by utilizing a member information enhancement module. By establishing group interconnections based on similarity and employing an adaptive fusion network to amalgamate multiple viewpoints, a final representation is derived. Experimental results demonstrate that our proposed model surpasses baseline models by 3% to 4% in terms of hit rate and accuracy, validating the efficacy of our approach.

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：