Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things最新文献_第3页

Base Station Traffic Prediction based on Feature Selection and Stacking Ensemble Learning 基于特征选择和叠加集成学习的基站流量预测

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603800

Long Zhao, Youzhi Huang, Yanyan Wang, Yin Xu, Qiangzhong Feng, Enhong Chen

{"title":"Base Station Traffic Prediction based on Feature Selection and Stacking Ensemble Learning","authors":"Long Zhao, Youzhi Huang, Yanyan Wang, Yin Xu, Qiangzhong Feng, Enhong Chen","doi":"10.1145/3603781.3603800","DOIUrl":"https://doi.org/10.1145/3603781.3603800","url":null,"abstract":"Accurately predicting base station network traffic is of great significance to improve network service quality and reduce base station operating costs. Aiming at the problem of low prediction accuracy of single model in the existing base station traffic prediction methods, a multi-model fusion prediction method based on feature selection and stacking ensemble learning is proposed. Firstly, a large number of features are constructed on the historical data, and then feature selection and correlation verification are carried out based on the tree model, and the features with high correlation are retained as the input of the predictive model to improve the performance and interpretability of the model. On this basis, a stacking ensemble learning prediction model with GDBT, XGBoost, LightGBM as the base learner and MLP as the meta-learner is established, and finally experimental verification is carried out on the real 1731 base stations. The results show that the mean squared error (MSE) and mean absolute error (MAE) of this method are reduced by 9.8% and 4.3%, respectively, compared with the single machine learning prediction model, and have better prediction accuracy and generalization ability.","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129549512","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

GPU Cluster RDMA communication technology and congestion control GPU集群RDMA通信技术及拥塞控制

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603876

Gui Liang, Siti Norbaya Daud, N. Ismail

{"title":"GPU Cluster RDMA communication technology and congestion control","authors":"Gui Liang, Siti Norbaya Daud, N. Ismail","doi":"10.1145/3603781.3603876","DOIUrl":"https://doi.org/10.1145/3603781.3603876","url":null,"abstract":"Abstract. This paper discusses Remote Direct Memory Access(RDMA) communication technology and the congestion control methods for Graphics Processing Unit(GPU) clusters. The implementation methods of RDMA networks widely used in GPU clusters are studied. Three implementation modes including InfiniBand, iWARP, and RoCE are analysed with comparison of their performance and applicable environments. Then, based on the analysis of a new congestion controls algorithm, DBCC & CBFC algorithm, is proposed. This algorithm based on delay feedback control and credit flow control prevents network congestion or increased latency in GPU cluster RDMA networks. The working principles of the algorithm are introduced including calculating the adjustment amount of the sending rate, initializing the sender and receiver and mechanisms to handle packet loss and timeout. Experimental results show that the algorithm optimizes network performance with RDMA communication in GPU clusters, while avoiding congestion and minimizing packet loss. However, due to the limitation of experimental conditions, it is not possible to conduct more environmental tests. In practical application, the applicability of the algorithm needs to be carefully evaluated and adjusted according to the specific situations.","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127522657","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

CryptMTD: Cryptography Based Moving Target Defense System for Mobile Application 基于密码学的移动目标防御系统

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603875

Yuehua Lv, Ting Tian, Huanyao Hu, Wei Kui, Dongchuan Lu, Zhengda Zhou

{"title":"CryptMTD: Cryptography Based Moving Target Defense System for Mobile Application","authors":"Yuehua Lv, Ting Tian, Huanyao Hu, Wei Kui, Dongchuan Lu, Zhengda Zhou","doi":"10.1145/3603781.3603875","DOIUrl":"https://doi.org/10.1145/3603781.3603875","url":null,"abstract":"Mobile applications are vulnerable to attacks and information leakage due to various unknown vulnerabilities in mobile channels, terminals, and programs. Moving target defense (MTD) has emerged as a proactive defense technology against unknown attacks. Previous work mainly focused on server-side protection, while ignoring information leakage due to mobile terminal vulnerabilities. In this paper, we construct an MTD system that applies to both servers and terminals. The proposed system uses cryptography to dynamically mask various resources of the system. Interactive supports are provided between those masked resources and the server or the users, thus allowing resources to remain masked during the whole trip. The status and information of the system can be effectively shielded, preventing the mobile application from being sniffed and information leakage. Evaluation is conducted on a DingTalk-based mobile office automation (OA) application. Application results show that the proposed system can thwarts attacks from both the server and the terminal. The response time of the protected system increases by less than 5.8%, compared with the original system, which is applicable for mobile applications.","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123029021","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

Long Text Relationship Extraction Method for Complex Productse 复杂产品的长文本关系提取方法

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603920

Huaijun Wang, Hangbo Quan, Junhuai Li, Miaomiao Chen, Jiang Xu

{"title":"Long Text Relationship Extraction Method for Complex Productse","authors":"Huaijun Wang, Hangbo Quan, Junhuai Li, Miaomiao Chen, Jiang Xu","doi":"10.1145/3603781.3603920","DOIUrl":"https://doi.org/10.1145/3603781.3603920","url":null,"abstract":"In the data management of complex products, relationship extraction of related texts can assist in constructing product data chains. This can realize the integration and fusion of data chains through nodes with relationships between different data chains. However, due to the complexity of complex products in terms of customer requirements, product technology, and manufacturing process, many related text data contain a large number of complex sentences, and a large amount of referential information is often lost in the relationship extraction of long text in these complex sentences, resulting in poor relationship extraction results. In this paper, we propose a long-text relationship extraction method for complex products, using a pre-trained language model to encode semantic information and obtain input text word vectors, then using a Gaussian graph generator (GGG) to construct potentially directed multi-views, learning graph features more deeply with the help of densely connected graph convolutional networks, and using dynamic time-regularized pooling operations to extract more relationship-dependent indicative words to assist the relationship. The extraction task is completed by combining the graph feature learning results with semantic information embedding representation for relationship extraction. Experiments are conducted on the DialogRE dataset, and the experimental results show that the F1 values reach 66.1% and 63.3% on the validation and test sets, respectively, and the F1 values still exceed 65% when the number of text words exceeds 400, which verifies the feasibility and effectiveness of the proposed method.","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126794220","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

Information extraction method of topic webpage based on multi-angle feature learning 基于多角度特征学习的主题网页信息提取方法

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603797

Lijuan Liu

引用次数: 0

Attentive Implicit Relation Embedding for Event Recommendation in Event-based Social Network 基于事件的社交网络中事件推荐的注意隐式关系嵌入

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603828

Yuan Liang

引用次数: 0

Blockchain-based Privacy-Preserving Reputation Management for Crowdsensing 基于区块链的众传感隐私保护声誉管理

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603929

Lei Xu, Yuewei Zhang, Shaorui Song, Liehuang Zhu

{"title":"Blockchain-based Privacy-Preserving Reputation Management for Crowdsensing","authors":"Lei Xu, Yuewei Zhang, Shaorui Song, Liehuang Zhu","doi":"10.1145/3603781.3603929","DOIUrl":"https://doi.org/10.1145/3603781.3603929","url":null,"abstract":"The performance of mobile crowdsensing systems heavily depends on individuals’ participation and the quality of sensing data, because of which the reputation mechanism is of great necessity. However, the mechanism cannot function well if the workers in a crowdsensing system do not behave properly. In this paper, we propose a blockchain-based crowdsensing framework that can resist against the threats to data quality without compromising workers’ privacy. In the proposed framework, a worker is allowed to use different pseudonyms to protect privacy. While the use of pseudonyms will obstruct service providers from evaluating the worker’s reputation. To deal with this issue, we treat reputation as a special type of token, and design a ring signature-based method to anonymously transfer a worker’s reputation score from one pseudonym to another. Moreover, to prevent a malicious worker from taking the advantage of pseudonyms to alter his reputation score, we propose two authentication methods that can verify the legitimacy of a worker’s pseudonym in a privacy-preserving way. The effectiveness of the proposed methods is analyzed theoretically and experimentally.","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126983185","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

CADCN: A click-through rate prediction model based on feature importance CADCN:一种基于特征重要性的点击率预测模型

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603822

Qi Wang, Yicheng Di, Yuan Liu

{"title":"CADCN: A click-through rate prediction model based on feature importance","authors":"Qi Wang, Yicheng Di, Yuan Liu","doi":"10.1145/3603781.3603822","DOIUrl":"https://doi.org/10.1145/3603781.3603822","url":null,"abstract":"Recommendation systems are widely used in real-world advertising recommendations. In traditional recommendation system prediction models, click-through rate plays a crucial role. However, traditional recommendation systems cross-combine original features to make the linear model memorable and generalizable while taking into account the importance of features requires a lot of computational cost, and it uses manual cross-combination of features on data, which requires a lot of time and effort. Traditional recommendation systems simply learn the relationship between features without considering the importance of features. We combine deep crossover network and AFM network, dynamically assign weights to different features prior to feature crossover using a synthetic incentive network, and introduce attention mechanism based on feature crossover explicitly. We then propose an advertisement click-through rate prediction based on feature importance model, and the experimental results demonstrate that the algorithm is superior to the deep crossover network in predicting the click-through rate of advertisements.","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121236861","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

Glucose Sensing Utilizing Complex-Valued Neural Networks 利用复值神经网络的葡萄糖传感

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603845

Yiqi Lv, X. Meng, Yong Luo, Yan Pei

引用次数: 0

Research on lightweight core network solutions for 5G private networks 5G专网轻量化核心网解决方案研究

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603843

Zhichao Zeng, Hong Zhang

{"title":"Research on lightweight core network solutions for 5G private networks","authors":"Zhichao Zeng, Hong Zhang","doi":"10.1145/3603781.3603843","DOIUrl":"https://doi.org/10.1145/3603781.3603843","url":null,"abstract":"Unlike traditional 5G public network services, 5G vertical industry applications have highly customized requirements in terms of coverage, latency, reliability and transmission bandwidth, which differ greatly from traditional public 5G networks, making it difficult to adopt a unified 5G public network architecture and performance requirements. Light-weight 5G Core network can provide a good solution. This paper proposes a lightweight 5G private network architecture design scheme, incorporating Mobile Edge Computing(MEC) architecture on a user side to achieve flexible and mobile rapid deployment of 5G private networks, and proposes a lightweight access authentication process applicable to 5G private networks, reducing redundant processes and improving the overall performance of the system. Through experimental verification, it can effectively reduce the access delay and end-to-end transmission delay of terminals. CCS CONCEPTS•Networks∼Network performance evaluation∼Network experimentation•Networks∼Network architectures∼Network design principles•Networks∼Network protocols∼Cross-layer protocols","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131858493","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