Pub Date : 2020-10-01DOI: 10.1109/SmartBlock52591.2020.00016
Zhihan Wang
Since railway traffic has come into people's life, it has been acting as a very important role in people's daily living. The major content of this research is to build a railway accident analysis system based on Artificial Intelligence (aliased as AI) and blockchain technology, which have the function of railway accident reproduction and traffic data analysis, taking the train crash happened on June 29, 2009 in Chenzhou for case study. This research reproduces the environment scenes simulating the accident happened in Chenzhou with the help of MSTS, including the longitude, the latitude, the landform, the buildings, the platforms, the traffic and the track installment of that time, and represents the real situation taking a driver's field of view. Besides, the research also builds a railway traffic data collecting and analyzing system based on C#, with the help of Cheat Engine, Microsoft Access and Visual Studio 2010. The system can automatically track and analyze the traffic data from Microsoft Train Simulator. This reproduction procedure is with great significance for analyzing the real accident in an Artificial Intelligence way, as well as providing a broad prospect for the practical application of blockchain technology.
自从铁路交通进入人们的生活以来，它就在人们的日常生活中扮演着非常重要的角色。本研究的主要内容是以2009年6月29日发生在郴州的动车事故为例，构建一个基于人工智能(Artificial Intelligence，简称AI)和区块链技术的具有铁路事故再现和交通数据分析功能的铁路事故分析系统。本研究利用MSTS对郴州发生事故的环境场景进行模拟，包括当时的经度、纬度、地形、建筑物、站台、交通、轨道装置等，以驾驶员的视角再现真实情况。此外，本研究还借助Cheat Engine、Microsoft Access和Visual Studio 2010，基于c#语言构建了一个铁路交通数据采集与分析系统。该系统可以自动跟踪和分析来自Microsoft Train Simulator的交通数据。这一复制过程对于用人工智能的方式分析真实事故具有重要意义，也为区块链技术的实际应用提供了广阔的前景。
{"title":"Design of Railway Accident Analysis System Based on Artificial Intelligence","authors":"Zhihan Wang","doi":"10.1109/SmartBlock52591.2020.00016","DOIUrl":"https://doi.org/10.1109/SmartBlock52591.2020.00016","url":null,"abstract":"Since railway traffic has come into people's life, it has been acting as a very important role in people's daily living. The major content of this research is to build a railway accident analysis system based on Artificial Intelligence (aliased as AI) and blockchain technology, which have the function of railway accident reproduction and traffic data analysis, taking the train crash happened on June 29, 2009 in Chenzhou for case study. This research reproduces the environment scenes simulating the accident happened in Chenzhou with the help of MSTS, including the longitude, the latitude, the landform, the buildings, the platforms, the traffic and the track installment of that time, and represents the real situation taking a driver's field of view. Besides, the research also builds a railway traffic data collecting and analyzing system based on C#, with the help of Cheat Engine, Microsoft Access and Visual Studio 2010. The system can automatically track and analyze the traffic data from Microsoft Train Simulator. This reproduction procedure is with great significance for analyzing the real accident in an Artificial Intelligence way, as well as providing a broad prospect for the practical application of blockchain technology.","PeriodicalId":443121,"journal":{"name":"2020 3rd International Conference on Smart BlockChain (SmartBlock)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127976128","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}
Pub Date : 2020-10-01DOI: 10.1109/SmartBlock52591.2020.00031
Yihang Gao, Hui Zhao, Qian Zhou, Meikang Qiu, Meiqin Liu
With the advent of the data age, the public has been facing the problem of information overload. Recommendation algorithms are an effective way to solve this problem. At present, a large number of recommended algorithms adopt the following two ideas: content-based text similarity algorithm and user-based collaborative filtering algorithm. Researchers have developed a distributed collaborative recommendation protocol based on blockchain. However, these algorithms ignore the characteristics of the news industry itself. Just adopting the above ideas will inevitably lead to many internet public opinion problems. Therefore, this paper proposes an improved N-TF-IDF algorithm, which is more suitable for the news industry, and can control the outbreak of negative public opinion, and has a positive effect on stabilizing internet public opinion. Through the verification of the experimental data set, the algorithm is superior to the traditional information retrieval and text mining technology TF-IDF in both the time dimension and the emotional dimension, and this algorithm is not affected by citizens' privacy rights.
{"title":"An Improved News Recommendation Algorithm Based on Text Similarity","authors":"Yihang Gao, Hui Zhao, Qian Zhou, Meikang Qiu, Meiqin Liu","doi":"10.1109/SmartBlock52591.2020.00031","DOIUrl":"https://doi.org/10.1109/SmartBlock52591.2020.00031","url":null,"abstract":"With the advent of the data age, the public has been facing the problem of information overload. Recommendation algorithms are an effective way to solve this problem. At present, a large number of recommended algorithms adopt the following two ideas: content-based text similarity algorithm and user-based collaborative filtering algorithm. Researchers have developed a distributed collaborative recommendation protocol based on blockchain. However, these algorithms ignore the characteristics of the news industry itself. Just adopting the above ideas will inevitably lead to many internet public opinion problems. Therefore, this paper proposes an improved N-TF-IDF algorithm, which is more suitable for the news industry, and can control the outbreak of negative public opinion, and has a positive effect on stabilizing internet public opinion. Through the verification of the experimental data set, the algorithm is superior to the traditional information retrieval and text mining technology TF-IDF in both the time dimension and the emotional dimension, and this algorithm is not affected by citizens' privacy rights.","PeriodicalId":443121,"journal":{"name":"2020 3rd International Conference on Smart BlockChain (SmartBlock)","volume":"7 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113990427","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}
Pub Date : 2020-10-01DOI: 10.1109/SmartBlock52591.2020.00015
Si Liu, Yunxia Liu, Cong Feng, Hongguo Zhao, Yu Huang
Blockchain is a shared digital public ledger that cannot be changed once transactions are recorded and verified. Since most blockchain nodes retain copies of the ledger, the blockchain brings the benefits of decentralization while also bringing privacy leakage issues. With the continuous development of blockchain applications, how to protect the privacy data on the blockchain platform is a very worthwhile research question. This paper first divides each blockchain transaction data into two parts: sensitive data and basic data, and then encrypts and hides the sensitive data into the HEVC video to protect the privacy transaction data of the blockchain. The experimental results show that this HEVC video steganography algorithm can effectively increase the privacy data embedding capacity and get good visual quality.
{"title":"Blockchain Privacy Data Protection Method Based on HEVC Video Steganography","authors":"Si Liu, Yunxia Liu, Cong Feng, Hongguo Zhao, Yu Huang","doi":"10.1109/SmartBlock52591.2020.00015","DOIUrl":"https://doi.org/10.1109/SmartBlock52591.2020.00015","url":null,"abstract":"Blockchain is a shared digital public ledger that cannot be changed once transactions are recorded and verified. Since most blockchain nodes retain copies of the ledger, the blockchain brings the benefits of decentralization while also bringing privacy leakage issues. With the continuous development of blockchain applications, how to protect the privacy data on the blockchain platform is a very worthwhile research question. This paper first divides each blockchain transaction data into two parts: sensitive data and basic data, and then encrypts and hides the sensitive data into the HEVC video to protect the privacy transaction data of the blockchain. The experimental results show that this HEVC video steganography algorithm can effectively increase the privacy data embedding capacity and get good visual quality.","PeriodicalId":443121,"journal":{"name":"2020 3rd International Conference on Smart BlockChain (SmartBlock)","volume":"16 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123264317","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}
Pub Date : 2020-10-01DOI: 10.1109/SmartBlock52591.2020.00021
Han Deng, Xiangwei Meng, Jun Guo, Erhui Xi, Hui Zhao
Purposed to collect and store human physiological data, WBANs as a telemedicine system play a significant role in sensor networks. The complex network environment presents a formidable challenge to the stability of the system and the security of the database. The traditional centralized architecture is to store the registration data of the sensor node and the patient's physiological data in the hub node. When the hub node is subjected to Denial of Service attacks (DoS) and Distributed Denial of Service attacks (DDoS), there will be a single point of failure, so that the sensor node cannot establish a communication connection with the hub node. In this paper, a cloud server layer architecture based on blockchain technology is proposed for WBNAs to ensure system stability and patient data security. Meanwhile, Ciphertext-Policy Attribute-Based Encryption (CP-ABE) scheme is used to ensure patient physiological data safety.
wban作为一种远程医疗系统，在传感器网络中发挥着重要的作用，其目的是收集和存储人体生理数据。复杂的网络环境对系统的稳定性和数据库的安全性提出了巨大的挑战。传统的集中式架构是将传感器节点的注册数据和患者的生理数据存储在hub节点中。当hub节点受到DoS (Denial of Service attack)和DDoS (Distributed Denial of Service attack)攻击时，会出现单点故障，传感器节点无法与hub节点建立通信连接。为了保证系统的稳定性和患者数据的安全性，本文提出了一种基于区块链技术的云服务器层架构。同时，采用cipher - policy Attribute-Based Encryption (CP-ABE)方案，确保患者生理数据的安全。
{"title":"A Framework of Blockchain-Based Security for WBANs","authors":"Han Deng, Xiangwei Meng, Jun Guo, Erhui Xi, Hui Zhao","doi":"10.1109/SmartBlock52591.2020.00021","DOIUrl":"https://doi.org/10.1109/SmartBlock52591.2020.00021","url":null,"abstract":"Purposed to collect and store human physiological data, WBANs as a telemedicine system play a significant role in sensor networks. The complex network environment presents a formidable challenge to the stability of the system and the security of the database. The traditional centralized architecture is to store the registration data of the sensor node and the patient's physiological data in the hub node. When the hub node is subjected to Denial of Service attacks (DoS) and Distributed Denial of Service attacks (DDoS), there will be a single point of failure, so that the sensor node cannot establish a communication connection with the hub node. In this paper, a cloud server layer architecture based on blockchain technology is proposed for WBNAs to ensure system stability and patient data security. Meanwhile, Ciphertext-Policy Attribute-Based Encryption (CP-ABE) scheme is used to ensure patient physiological data safety.","PeriodicalId":443121,"journal":{"name":"2020 3rd International Conference on Smart BlockChain (SmartBlock)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131117953","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}
Pub Date : 2020-10-01DOI: 10.1109/SmartBlock52591.2020.00029
Xiaoyu Liu, Xiaofu Liu, Zhenpeng Guo
Blockchain is the systematic integration innovation of distributed accounting, consensus mechanism, point-to-point transmission, encryption algorithm, intelligent contract and other technologies, providing a solution for information security and social trust in the Information Age. The principles, characteristics and deep thinking of Blockchain technology can promote the thinking innovation and solve the existing obstacles including the weak effectiveness of education activities, the burnout of education subjects and the lack of mutual trust in the field of ideological and political education. This paper focuses on analyzing the expanded application of Blockchain theory of ideological and political education. It is emphasized that we should build Learn Ledger, promote the participation degree of education subject, establish a new interactive trust mechanism and intensify endogenous incentives to promote the deep transformation of ideological and political education, enhance the effectiveness of educational content, expand the participation in educational activities, and strengthen the multi-subject trust-relationship reconstruction of ideological and political education.
{"title":"Analysis on the Thinking Innovation of Ideological and Political Education Based on the Theory of Blockchain in the Information Age","authors":"Xiaoyu Liu, Xiaofu Liu, Zhenpeng Guo","doi":"10.1109/SmartBlock52591.2020.00029","DOIUrl":"https://doi.org/10.1109/SmartBlock52591.2020.00029","url":null,"abstract":"Blockchain is the systematic integration innovation of distributed accounting, consensus mechanism, point-to-point transmission, encryption algorithm, intelligent contract and other technologies, providing a solution for information security and social trust in the Information Age. The principles, characteristics and deep thinking of Blockchain technology can promote the thinking innovation and solve the existing obstacles including the weak effectiveness of education activities, the burnout of education subjects and the lack of mutual trust in the field of ideological and political education. This paper focuses on analyzing the expanded application of Blockchain theory of ideological and political education. It is emphasized that we should build Learn Ledger, promote the participation degree of education subject, establish a new interactive trust mechanism and intensify endogenous incentives to promote the deep transformation of ideological and political education, enhance the effectiveness of educational content, expand the participation in educational activities, and strengthen the multi-subject trust-relationship reconstruction of ideological and political education.","PeriodicalId":443121,"journal":{"name":"2020 3rd International Conference on Smart BlockChain (SmartBlock)","volume":"421 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116003536","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}
Pub Date : 2020-10-01DOI: 10.1109/SmartBlock52591.2020.00044
Xiaoyan Chen, Yuliang Liu, Jiangling Ge
With the advent of the era of big data, data management technology has been applied in various important fields, and even become an important factor in the competitiveness of enterprises and even the country. Due to the problems of excessive concentration, data abuse, lack of trust and privacy leakage in the traditional data management mode, this paper proposes a data management method based on blockchain technology, which is decentralized, unforgeable and traceable, solve the bottleneck problem of traditional data management methods. Firstly, this paper analyzes and introduces the current development of blockchain technology, and describes the characteristics and architecture of blockchain technology in detail. Then, based on the analysis and comparison of the problems existing in the traditional data management methods, this paper summarizes the progress of the application of blockchain technology in data management methods. Finally, the shortcomings of the current research are analyzed and the future research direction is prospected.
{"title":"A Data Management Method Based on Blockchain Technology","authors":"Xiaoyan Chen, Yuliang Liu, Jiangling Ge","doi":"10.1109/SmartBlock52591.2020.00044","DOIUrl":"https://doi.org/10.1109/SmartBlock52591.2020.00044","url":null,"abstract":"With the advent of the era of big data, data management technology has been applied in various important fields, and even become an important factor in the competitiveness of enterprises and even the country. Due to the problems of excessive concentration, data abuse, lack of trust and privacy leakage in the traditional data management mode, this paper proposes a data management method based on blockchain technology, which is decentralized, unforgeable and traceable, solve the bottleneck problem of traditional data management methods. Firstly, this paper analyzes and introduces the current development of blockchain technology, and describes the characteristics and architecture of blockchain technology in detail. Then, based on the analysis and comparison of the problems existing in the traditional data management methods, this paper summarizes the progress of the application of blockchain technology in data management methods. Finally, the shortcomings of the current research are analyzed and the future research direction is prospected.","PeriodicalId":443121,"journal":{"name":"2020 3rd International Conference on Smart BlockChain (SmartBlock)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116483734","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}
Pub Date : 2020-10-01DOI: 10.1109/SmartBlock52591.2020.00009
Mengyi Xie, Zuobin Liao, Liting Huang
Blockchain is a distributed shared ledger and database. Because of its unforgeable, traceable, open, and transparent, and collective maintenance features, it has laid a solid foundation of “trust”. At the same time, the blockchain also brings hidden dangers of data security. How to protect the data security of digital currency in blockchain transactions is the direction of this article. This article first analyzes the basic structure of the blockchain, and then takes Bitcoin in the digital currency as an example to introduce its technical principles and implementation process. Finally, the PBFT algorithm is proposed, which can search for the application of encryption in the blockchain consensus mechanism. The experimental data verification proves the future application prospects of blockchain-based digital currency using PBFT algorithm to protect data security.
{"title":"Data Security Based on Blockchain Digital Currency","authors":"Mengyi Xie, Zuobin Liao, Liting Huang","doi":"10.1109/SmartBlock52591.2020.00009","DOIUrl":"https://doi.org/10.1109/SmartBlock52591.2020.00009","url":null,"abstract":"Blockchain is a distributed shared ledger and database. Because of its unforgeable, traceable, open, and transparent, and collective maintenance features, it has laid a solid foundation of “trust”. At the same time, the blockchain also brings hidden dangers of data security. How to protect the data security of digital currency in blockchain transactions is the direction of this article. This article first analyzes the basic structure of the blockchain, and then takes Bitcoin in the digital currency as an example to introduce its technical principles and implementation process. Finally, the PBFT algorithm is proposed, which can search for the application of encryption in the blockchain consensus mechanism. The experimental data verification proves the future application prospects of blockchain-based digital currency using PBFT algorithm to protect data security.","PeriodicalId":443121,"journal":{"name":"2020 3rd International Conference on Smart BlockChain (SmartBlock)","volume":"299302 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116581447","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}
Pub Date : 2020-10-01DOI: 10.1109/SmartBlock52591.2020.00032
Jiajia Duan, Hui Zhao, Wenshuai Qin, Meikang Qiu, Meiqin Liu
In the era of knowledge explosion, text classification is becoming increasingly crucial. At the same time, with the proposed Blockchain, it is of great research significance to actively explore the combination of Blockchain and AI, especially to apply text classification technology to the security classification of Blockchain technology. In this paper, we propose a hybrid neural network model (MLCNN & BiGRU-ATT) based on Multilayer Convolutional Neural Networks (MLCNN) and Bidirectional Gated Recurrent Unit (BiGRU) with Attention Mechanism in the news text classification field. GRU (Gate Recurrent Unit), a variant of LSTM (Long-Short Term Memory), has the natural advantages in processing time series tasks, which can readily capture the characteristics of text context information. Due to its prominent advantages in local feature extraction, CNN is also applied to NLP area, in which the researchers have made substantial progress. The experiment results reveal that our model has achieved higher accuracy on THUCNews dataset and Sougou news corpus classification.
{"title":"News Text Classification Based on MLCNN and BiGRU Hybrid Neural Network","authors":"Jiajia Duan, Hui Zhao, Wenshuai Qin, Meikang Qiu, Meiqin Liu","doi":"10.1109/SmartBlock52591.2020.00032","DOIUrl":"https://doi.org/10.1109/SmartBlock52591.2020.00032","url":null,"abstract":"In the era of knowledge explosion, text classification is becoming increasingly crucial. At the same time, with the proposed Blockchain, it is of great research significance to actively explore the combination of Blockchain and AI, especially to apply text classification technology to the security classification of Blockchain technology. In this paper, we propose a hybrid neural network model (MLCNN & BiGRU-ATT) based on Multilayer Convolutional Neural Networks (MLCNN) and Bidirectional Gated Recurrent Unit (BiGRU) with Attention Mechanism in the news text classification field. GRU (Gate Recurrent Unit), a variant of LSTM (Long-Short Term Memory), has the natural advantages in processing time series tasks, which can readily capture the characteristics of text context information. Due to its prominent advantages in local feature extraction, CNN is also applied to NLP area, in which the researchers have made substantial progress. The experiment results reveal that our model has achieved higher accuracy on THUCNews dataset and Sougou news corpus classification.","PeriodicalId":443121,"journal":{"name":"2020 3rd International Conference on Smart BlockChain (SmartBlock)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126388065","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}
Pub Date : 2020-10-01DOI: 10.1109/SmartBlock52591.2020.00038
Yuhui Li, Jianlong Xu, Wei Liang
Blockchain-as-a-service (BaaS) experienced a dramatical growth in recent years, making it a hot research topic. With the expanding scale of distributed services deployed on the blockchain system, it is increasingly urgent to evaluate quality of service (QoS) attributes of blockchain services and in-blockchain peers-clients connections. The complicated association of service invocation and network environment naturally form a graph, making it possible to extract features through graph neural networks (GNN). To incorporate graph-structured information in QoS prediction, we proposed a graph matrix factorization (GraphMF) take advantages of both GNNs and collaborative filtering to estimate missing QoS values in the data matrix. Experiment conducted on a real-world dataset demonstrated the effectiveness of our model.
{"title":"GraphMF: QoS Prediction for Large Scale Blockchain Service Selection","authors":"Yuhui Li, Jianlong Xu, Wei Liang","doi":"10.1109/SmartBlock52591.2020.00038","DOIUrl":"https://doi.org/10.1109/SmartBlock52591.2020.00038","url":null,"abstract":"Blockchain-as-a-service (BaaS) experienced a dramatical growth in recent years, making it a hot research topic. With the expanding scale of distributed services deployed on the blockchain system, it is increasingly urgent to evaluate quality of service (QoS) attributes of blockchain services and in-blockchain peers-clients connections. The complicated association of service invocation and network environment naturally form a graph, making it possible to extract features through graph neural networks (GNN). To incorporate graph-structured information in QoS prediction, we proposed a graph matrix factorization (GraphMF) take advantages of both GNNs and collaborative filtering to estimate missing QoS values in the data matrix. Experiment conducted on a real-world dataset demonstrated the effectiveness of our model.","PeriodicalId":443121,"journal":{"name":"2020 3rd International Conference on Smart BlockChain (SmartBlock)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127425911","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：