2022 International Conference on Networking and Network Applications (NaNA)最新文献_第5页

An optimized prediction algorithm based on XGBoost 基于XGBoost的优化预测算法

2022 International Conference on Networking and Network Applications (NaNA) Pub Date : 2022-12-01 DOI: 10.1109/NaNA56854.2022.00082

Cheng Sheng, Haizheng Yu

{"title":"An optimized prediction algorithm based on XGBoost","authors":"Cheng Sheng, Haizheng Yu","doi":"10.1109/NaNA56854.2022.00082","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00082","url":null,"abstract":"The real estate market is closely related to people's life. It is very important to accurately predict the future real estate price. Traditional methods are difficult to describe the nonlinear characteristics of house price prediction. XGBoost algorithm can effectively represent the nonlinear relationship in house price prediction. However, the selection of parameters determines the learning and generalization ability of XGBoost, and it is very important to determine the parameters of XGBoost. Particle swarm optimization algorithm can select the training parameters of XGBoost more quickly and accurately. Therefore, this paper studies the house price prediction based on the hybrid model of particle swarm optimization XGBoost algorithm, namely PSO-XGBoost model. Using the collected sample data of houses in Ames, Iowa, five different machine learning algorithms including PSO-XGBoost are used to predict house prices. Finally, the results of five algorithms are compared and analyzed. The experimental results show that PSO-XGBoost model has the highest prediction accuracy and the best effect, and the prediction effect of integrated learning algorithm is better than that of linear regression model.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"102 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125971038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

The test and evaluation method for the effect of WLAN network quality on hosted services 无线局域网网络质量对承载业务影响的测试与评价方法

2022 International Conference on Networking and Network Applications (NaNA) Pub Date : 2022-12-01 DOI: 10.1109/NaNA56854.2022.00025

Yiming Pan, Zhen Shao, Goujin Huang, Yiming Li, Fangfang Zuo

引用次数: 0

Rotation Model Enhancement for Adversarial Attack 对抗性攻击的旋转模型增强

2022 International Conference on Networking and Network Applications (NaNA) Pub Date : 2022-12-01 DOI: 10.1109/NaNA56854.2022.00080

Hengwei Zhang, Zheming Li, Haowen Liu, Bo Yang, Chenwei Li, Jin-dong Wang

引用次数: 0

Ciphertext storage scheme supporting data hierarchical management and control 密文存储方案支持数据分层管理和控制

2022 International Conference on Networking and Network Applications (NaNA) Pub Date : 2022-12-01 DOI: 10.1109/NaNA56854.2022.00042

Yuxiang Chen, Yao Hao, Zhongqiang Yi, Xiaoyu Guo, Chunxiang Xu

{"title":"Ciphertext storage scheme supporting data hierarchical management and control","authors":"Yuxiang Chen, Yao Hao, Zhongqiang Yi, Xiaoyu Guo, Chunxiang Xu","doi":"10.1109/NaNA56854.2022.00042","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00042","url":null,"abstract":"As file management is widely used in e-government and enterprise office, the file exchange, as the main means of sharing and collaborating in office, has been far from able to meet the needs of data security. Encrypted Storage with its highly security, controllability, can be an effective solution to the limitations of existing authority control services. However, during the data sharing and exchange, the file is separated from the owner, which has the problem of insufficient or over -authorization, thus needs fine-grained hierarchical control and cooperation. In this article, we propose a hierarchical management and control scheme for encrypted storage combined with ciphertext retrieval. The proposed scheme supports top-down privilege division without increasing the number of managed keys, all the data are processed and authorized strictly, the high-level user can deduce the keys of lower authorized users, but not vice versa, thus solving data leakage caused by over-authorization. Through performance and security analysis, we demonstrate that the scheme can better meet the data security and precise authorization requirements.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128535385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Track Irregularity Prediction Based on DWT-DLSTM Model 基于DWT-DLSTM模型的航迹不规则性预测

2022 International Conference on Networking and Network Applications (NaNA) Pub Date : 2022-12-01 DOI: 10.1109/NaNA56854.2022.00095

Haining Meng, Jia-wan Zhang, Y. Zheng, Wenjiang Ji, Xinyu Tong, Xinhong Hei

引用次数: 0

Secure Distributed Processing of NG with Updatable Decomposition Data and Parameters 具有可更新分解数据和参数的NG安全分布式处理

2022 International Conference on Networking and Network Applications (NaNA) Pub Date : 2022-12-01 DOI: 10.1109/NaNA56854.2022.00067

H. Miyajima, Noritaka Shigei, H. Miyajima, N. Shiratori

{"title":"Secure Distributed Processing of NG with Updatable Decomposition Data and Parameters","authors":"H. Miyajima, Noritaka Shigei, H. Miyajima, N. Shiratori","doi":"10.1109/NaNA56854.2022.00067","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00067","url":null,"abstract":"Machine learning using distributed data, such as federative learning (FL) and secure multiparty computation (SMC), is demanded to achieve both utility and confidentiality when using confidential data. There is a trade-off between utility and confidentiality, and in general, SMC can offer better confidentiality than FL and better utility than homomorphic encryption. In machine learning with SMC, confidentiality is improved by decomposing individual data and parameters into multiple pieces, storing each piece on each server, and learning without restoring the data or parameters themselves. However, once the conventional methods randomly decompose data and parameters, the decomposition remains permanently fixed. The fixed decomposition is considered undesirable because it gives malicious attackers more opportunities to attack the data and model. In this paper, we propose a secure distributed processing of neural gas (NG), which is one of unsupervised machine learning. In addition to the decomposition of data, the proposed method can update the decomposition of parameters during learning. Each server can independently update the decomposition of both data and parameters in the proposed method, and the data and parameters are never restored during learning. Our simulation result shows that it can achieve the same level of learning accuracy as the conventional methods.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128954584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Object detection algorithm based on cosine similarity IoU 基于余弦相似度IoU的目标检测算法

2022 International Conference on Networking and Network Applications (NaNA) Pub Date : 2022-12-01 DOI: 10.1109/NaNA56854.2022.00077

Sugang Ma, Ningbo Li, Peng Guansheng, Yanping Chen, Wang Ying, Zhiqiang Hou

引用次数: 0

An Optimized Key-Value Raft Algorithm for Satisfying Linearizable Consistency 满足线性一致性的优化键值筏算法

2022 International Conference on Networking and Network Applications (NaNA) Pub Date : 2022-12-01 DOI: 10.1109/NaNA56854.2022.00096

Xiao Liu, Zhao Huang, Quan Wang, Nan Luo

引用次数: 0

Secure YOLOv3-SPP: Edge-Cooperative Privacy-preserving Object Detection for Connected Autonomous Vehicles 安全YOLOv3-SPP:面向互联自动驾驶汽车的边缘协同隐私保护目标检测

2022 International Conference on Networking and Network Applications (NaNA) Pub Date : 2022-12-01 DOI: 10.1109/NaNA56854.2022.00022

Yongjie Zhou, Jinbo Xiong, Renwan Bi, Youliang Tian

{"title":"Secure YOLOv3-SPP: Edge-Cooperative Privacy-preserving Object Detection for Connected Autonomous Vehicles","authors":"Yongjie Zhou, Jinbo Xiong, Renwan Bi, Youliang Tian","doi":"10.1109/NaNA56854.2022.00022","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00022","url":null,"abstract":"The connected autonomous vehicles (CAVs) are a key component of intelligent transportation systems (ITS) where vehicles communicate with each other to exchange sensing data from on-board sensors (e.g., high-definition cameras and lidar). For the sake of the category and location privacy leakage of sensing images shared by CAVs and computational inefficiency of privacy-preserving object detection framework in edge computing environment, we propose a lightweight and privacy-preserving detection framework (PPDF) to support secure extraction, classification and detection of image features, and achieve the goal of data transmission and computing security under the collaborative detection process of edge nodes. Particularly, we design a secure clustering prediction protocol of object anchors, a secure object classification and regression protocol, secure object upsampling and secure feature fusion protocols. Finally, PPDF based on edge-cooperation was constructed and two non-collusive edge servers were used to perform PPDF. Theoretical analysis of correctness, security and complexity indicate that PPDF can not only realize correctness of object detection, but also let category and location privacy of images are protected effectively and have excellent accuracy. Actual performance evaluation shows that PPDF can achieve the same detection accuracy as original YOLOv3-SPP model. At the same time, compared with homomorphic encryption and multi-round iterative calculation schemes, PPDF has obvious advantages in terms of computational cost and communication overhead.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115343135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Resource Allocation Scheme Based on Memetic Algorithm for D2D Communication 基于模因算法的D2D通信资源分配方案

2022 International Conference on Networking and Network Applications (NaNA) Pub Date : 2022-12-01 DOI: 10.1109/NaNA56854.2022.00008

Yongqiang Xia, Luping Tang, Hairui Wang, Yijun Wang, Jialong Hou

引用次数: 0