检索结果-内蒙古大学图书馆

5th International Conference on computer engineering and Intelligent Control, ICCEIC 2024

作者： Xie, Xu Chen, Rongyuan College of Computer Science Hunan University of Technology and Business Hunan Changsha China School of Resource & Environment Hunan University of Technology and Business Hunan Changsha China

ISBN: (纸本)9798331507992

Sequential recommendation models the dynamic interest changes of users based on their interaction information with items, in order to predict the next interaction item for users. Existing sequential recommendation algorithms are susceptible to data sparsity issues. Contrastive learning sequential recommendation effectively alleviates data sparsity issues through construct samples and data enhancement methods, but it faces data noise problems. In response to the problem of introducing data noise in contrastive learning sequence recommendation, a graph attention mechanism-based contrastive learning sequential recommendation model (GACLRec) is proposed. This model uses the graph attention mechanism to dynamically evaluate and weight the importance of different neighboring nodes, effectively suppressing the interference of noise information and achieving interpretable aggregation of information from neighboring nodes. On this basis, in order to obtain richer node representations, the model further improved the multi-head graph attention mechanism to learn the diverse representations of nodes in multiple latent spaces. By integrating these representations from different spaces, a comprehensive node feature vector is finally obtained, enabling the model to comprehensively learn the actual preferences and behavior patterns of users. Compared with existing excellent algorithms on the real datasets, the beauty and yelp. The experiment proves that the model proposed in this paper has a certain improvement compared to the baseline method on the evaluation metrics HR@N and NDCG@N. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Publishing Mechanism for Real-Time Vehicle Trajectory in Vehicle-to-Grid Networks

Privacy-Preserving Publishing Mechanism for Real-Time Vehicl...

引用

Power Electronics, computer Applications (ICPECA), IEEE International Conference on

作者： Yulong Wang Jianbo Xu Bo Gong School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (数字)9798331533694

ISBN: (纸本)9798331533700

The Vehicle-to-Grid (V2G) network is a smart grid technology generated under the background of the rapid development of new energy technology, which allows mobile energy storage vehicles (MESVs) to realize bidirectional energy exchange with the grid system. As distributed energy storage units within the V2G network, MESVs help meet the grid's load-balancing demands. To accurately schedule grid loads, V2G networks rely on MESVs' real-time trajectory data. After collecting this data, the central authority (CA) publishes it to the grid enterprise (GM) for load-balancing decisions. However, before publication, the CA must process the data to protect the location privacy of MESVs and prevent GM from extracting sensitive information. To address this privacy protection challenge during data publication, we propose a differential privacy-based mechanism. Our mechanism uses the unscented Kalman filter to predict and correct the published data at the sampling point and intelligently adjusts the sampling interval. Additionally, we introduce a privacy budget allocation method based on regional access frequency and travel time, enhancing privacy protection of trajectory in high-access areas and peak hours. Through security analysis and experimental validation, our mechanism effectively preserves the privacy of real-time vehicle trajectory data while ensuring data validity.

关键词： Vehicle-to-grid Data privacy Privacy Publishing Real-time systems Trajectory Kalman filters Security Protection Radio spectrum management

来源：评论

学校读者我要写书评

暂无评论

Physical layer key negotiation attacks and detection under a static environment 4

Physical layer key negotiation attacks and detection under a...

引用

4th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2023

作者： Qi, Yuan Hu, Qiao College of Computer Science and Electronic Engineering Hunan University Changsha Hunan China

ISBN: (纸本)9798350314526

The existing physical layer key generation methods overly rely on the results of channel probing, which not only weakens the randomness of the key in a static environment but also makes the physical layer key vulnerable to active attacks. At the same time, in terms of defence technology, traditional physical layer intrusion detection methods mainly focus on the abnormal transmission of physical signals, making it difficult to identify potential key attack behaviours. This article proposes an attack method for the random operator-based key negotiation model in a static environment and then proposes a key attack detection scheme that utilizes the correlation between pilot signals and random signals for the above two attack behaviours. Under low false alarm rate conditions, this detection scheme has a higher detection rate compared to traditional physical layer intrusion detection methods. © 2023 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

A Progress Prediction Model Using Res-zLSTM for LOCA in Nuclear Power Plants

A Progress Prediction Model Using Res-zLSTM for LOCA in Nucl...

引用

2024 International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2024

作者： Liu, Liang She, Jingke Shu, Lingyu Zhao, Yizhong College of Computer Science & Electronic Engineering Hunan University Changsha China Hunan 6906 Information Technology Co. Ltd Yueyang China

ISBN: (纸本)9798350366075

Predicting the changes in various operation conditions following a loss of coolant accident (LOCA) in a nuclear power plant is of great significance. To enhance the accuracy of prediction, this paper proposes a novel prediction model called Res-zLSTM. The Res-zLSTM model incorporates residual structure and attention mechanisms to effectively mitigate the gradient vanishing problem in traditional Long Short-Term Memory (LSTM) models. Additionally, it maintains a low network complexity while simultaneously strengthening its ability to learn from long-term sequence data. This allows for accurate predictions of key parameter trends in LOCA conditions. In validation experiments, the Res-zLSTM model was used to predict multiple important operational parameters under different LOCA conditions. The experimental results demonstrate that the Res-zLSTM model exhibits superior prediction accuracy, achieving a maximum improvement of 54% compared to the zLSTM model. While the prediction accuracy of the Res-zLSTM model may be influenced by the changing rate of operation data, its outstanding performance in predicting LOCA conditions provides a novel approach for predicting operation conditions in complex systems. ©2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Multivariate Time Series Anomaly Detection in IoT

引用

computers, Materials & Continua 2023年第6期75卷 5027-5047页

作者： Shiming He Meng Guo Bo Yang Osama Alfarraj Amr Tolba Pradip Kumar Sharma Xi’ai Yan School of Computer&Communication Engineering Changsha University of Science&TechnologyChangsha410114China Computer Science Department Community CollegeKing Saud UniversityRiyadh11437Saudi Arabia Department of Computing Science University of AberdeenAberdeenAB243FXUK Hunan Provincial Key Laboratory of Network Investigational Technology Hunan Police AcademyChangsha410138China

Sensors produce a large amount of multivariate time series data to record the states of Internet of Things(IoT)*** time series timestamp anomaly detection(TSAD)can identify timestamps of attacks and ***,it is necessary to determine which sensor or indicator is abnormal to facilitate a more detailed diagnosis,a process referred to as fine-grained anomaly detection(FGAD).Although further FGAD can be extended based on TSAD methods,existing works do not provide a quantitative evaluation,and the performance is ***,to tackle the FGAD problem,this paper first verifies that the TSAD methods achieve low performance when applied to the FGAD task directly because of the excessive fusion of features and the ignoring of the relationship’s dynamic changes between ***,this paper proposes a mul-tivariate time series fine-grained anomaly detection(MFGAD)*** avoid excessive fusion of features,MFGAD constructs two sub-models to independently identify the abnormal timestamp and abnormal indicator instead of a single model and then combines the two kinds of abnormal results to detect the fine-grained *** on this framework,an algorithm based on Graph Attention Neural Network(GAT)and Attention Convolutional Long-Short Term Memory(A-ConvLSTM)is proposed,in which GAT learns temporal features of multiple indicators to detect abnormal timestamps and A-ConvLSTM captures the dynamic relationship between indicators to identify abnormal *** simulations on a real-world dataset demonstrate that the proposed algorithm can achieve a higher F1 score and hit rate than the extension of existing TSAD methods with the benefit of two independent sub-models for timestamp and indicator detection.

关键词： Multivariate time series graph attention neural network fine-grained anomaly detection

来源：评论

学校读者我要写书评

暂无评论

BeamCount: Indoor Crowd Counting Using Wi-Fi Beamforming Feedback Information 24

BeamCount: Indoor Crowd Counting Using Wi-Fi Beamforming Fee...

引用

2024 International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, MobiHoc 2024

作者： Chen, Siyu Jiang, Hongbo Xiong, Jie Hu, Jingyang Wang, Penghao Liu, Chao Xiao, Zhu Li, Bo College of Computer Science and Electronic Engineering Hunan University China Microsoft Research Asia University of Massachusetts Amherst United States Department of Computer Science and Technology Ocean University of China China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong

ISBN: (纸本)9798400705212

Real-time indoor crowd counting plays an important role in many applications such as crowd control, resource allocation and advertisement. Current research predominantly relies on camera-based methods. However, computer vision-based solutions raise severe privacy and ethical concerns. In this paper, we propose a privacy-preserving counting solution called BeamCount based on Wi-Fi sensing. Instead of using conventional Wi-Fi Channel State Information (CSI) readings, we utilize Wi-Fi Beamforming Feedback Information (BFI) for crowd counting estimation. Compared to CSI which can only be extracted from few commodity Wi-Fi cards (e.g., Intel 5300), BFI readings can be obtained from a large range of commodity Wi-Fi devices. We establish a mapping relationship between BFI and headcount and extract headcounts from BFI inputs through a carefully designed adversarial network. Owing to the adversarial network’s cross-domain capability, the proposed counting system can achieve high accuracy across different environments, demonstrating its generalization capability. To mitigate the effect of BFI compression on sensing performance, we adopt a novel time series prediction model. Extensive real-world experiments validate the effectiveness of BeamCount in various environments, achieving an average counting accuracy of 93.6%. © 2024 Copyright held by the owner/author(s).

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

FedHPM: Online Federated Learning via Heterogeneous Prediction Model

FedHPM: Online Federated Learning via Heterogeneous Predicti...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Zhi Zhang Shiwen Zhang Shuang Chen Wei Liang Hunan University of Science and Technology College of Computer Science and Technology Xiangtan China School of Computer Science and Engineering Hunan University of Science and Technology and Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

In the era of big data and growing privacy concerns, Federated Learning (FL) has emerged as a promising solution for collaborative model training while preserving user data privacy. However, FL faces challenges such as inconsistent data quality and frequent client dropouts, which hinder its performance. To address these challenges, we propose FedHPM, a novel framework that leverages the predictive capabilities of Long Short-Term Memory (LSTM) networks. FedHPM incorporates an intelligent client selection mechanism that utilizes LSTM-based analysis of historical data to forecast clients’ potential data quality and dropout likelihood. This mechanism enables efficient selection of the top best-performing clients for participation in each round of global model training. By mitigating the impact of dropouts and optimizing the composition of participating clients, FedHPM significantly improves both the convergence speed and final performance of the global model. Through extensive empirical evaluations, we demonstrate the superior performance of FedHPM in enhancing FL stability, accelerating the convergence rate, and maintaining model accuracy. The results highlight the effectiveness of our framework in addressing the challenges associated with data quality and dropouts, thereby advancing the field of federated learning.

关键词： Training Privacy Data privacy Accuracy Federated learning Data integrity Predictive models Data models Long short term memory Convergence

来源：评论

学校读者我要写书评

暂无评论

Secure Image Retrieval Based on Deep Learning in Cloud Computing 23

Secure Image Retrieval Based on Deep Learning in Cloud Compu...

引用

8th International Conference on Multimedia and Image Processing, ICMIP 2023

作者： Li, Sijie Li, Xiehua College of Computer Science and Electronic Engineering Hunan University China

ISBN: (纸本)9781450399586

The rapid growth of multimedia data and the limited storage and computing capacity of local devices motivate the outsourcing service of cloud storage. For the outsourced images, users usually encrypt them to protect their privacy and require the ability to retrieve them later. Therefore, how effectively managing and retrieving massive encrypted images in cloud servers becomes a challenging problem. In this paper, we propose a deep learning-based image retrieval scheme for cloud computing. Firstly, we use a Convolutional Neural Network (CNN) to extract feature descriptors and represent each image as two parts: image category and image feature. Then, we construct an encrypted tree-based index structure to improve retrieval efficiency. At the same time, we use the Learning With Errors (LWE)-based secure k-Nearest Neighbor (kNN) algorithm and random matrix to protect the security of two parts of the descriptors. The feasibility of our scheme is proved through security analysis. Finally, we conduct empirical experiments on the Caltech256 image dataset, and the results show that our scheme can achieve high retrieval efficiency and accuracy while ensuring image security. © 2023 ACM.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Identifying possible lncRNA-disease associations based on deep learning and positive-unlabeled learning

Identifying possible lncRNA-disease associations based on de...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Peng, Lihong Huang, Liangliang Lu, Yuankang Liu, Guangyi Chen, Min Han, Guosheng Hunan University of Technology School of Computer Science Zhuzhou China Xiangtan University Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan China

ISBN: (纸本)9781665468190

lncRNAs are involved in many biological processes, and their mutations and disorders are closely related to many diseases. Identification of LncRNA-Disease Associations (LDAs) helps us understand the pathogenesis of diseases and improve their diagnosis and treatment. However, experiments to determine LDAs are expensive, so it is essential to exploit effective computational methods to screen possible LDAs. In this study, we developed an LDA prediction model (LDA-DLPU) based on deep learning and positive-unlabeled (PU) learning. First, LDA-DLPU extracted features of lncRNAs and diseases based on singular value decomposition and regression model. Second, it selected negative LDAs based on PU learning and graph autoencoder. Finally, it classified unknown lncRNA-disease pairs based on deep neural network. LDA-DLPU obtained the best performance on two datasets. We predict that BCYRN1 and IFNG-AS1 may associate with leukemia. © 2022 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

DCSE: Domain Confusion with Self-Ensembling for Unsupervised Domain Adaptation

DCSE: Domain Confusion with Self-Ensembling for Unsupervised...

引用

2024 International Annual Conference on Complex Systems and Intelligent science, CSIS-IAC 2024

作者： Lin, Zhijie Wang, Jiawei He, Zhaoshui Liang, Hao An, Juan Su, Wenqing School of Automation Guangdong University of Technology GuangZhou China College of Computer Science and Electronic Engineering Hunan University Changsha China

ISBN: (纸本)9798331504755

Data collection and annotation are time-consuming in machine learning, especially for large-scale problems. A com-mon approach for these problems is to transfer knowledge from the related labeled domain to the target one. There are two pop-ular ways to achieve this: adversariallearning and self-training. In this paper, we first analyze the training instability problem and feature-conditional distribution misalignment problem in adversariallearning process. Then, inspired by domain confusion and self-ensembling methods, we propose a combined model for unsupervised domain adaptation, Domain Confusion with Self-Ensembling (DCSE), to learn joint invariant representations of features and classes. Experimental results show that the proposed DCSE achieves better performance than the existing methods on various unsupervised domain adaptation benchmarks. © 2024 IEEE.

关键词： Adversarial machine learning

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：