{"title":"基于时空图注意力网络的交通预测模型","authors":"Jing Chen, Linkai Wang, Wen Wang, Ruizhuo Song","doi":"10.1109/ICCR55715.2022.10053874","DOIUrl":null,"url":null,"abstract":"Smart transportation is an important part of building a smart city, and accurate traffic forecasting is crucial for citizen travel and urban construction. Aiming at the temporal and spatial dimensions in traffic forecasting, we focus on the extraction methods of the correlation between the two dimensions, and propose a new prediction model of the spatio-temporal graph attention network from the temporal correlation and the spatial correlation. The structure of the model is studied and analyzed. Finally, experiments are carried out on the mainstream traffic data sets, and by comparing with other prediction models, it is concluded that the evaluation indicators of the prediction model are better than other models.","PeriodicalId":441511,"journal":{"name":"2022 4th International Conference on Control and Robotics (ICCR)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Traffic Prediction Model Based on Spatio-temporal Graph Attention Network\",\"authors\":\"Jing Chen, Linkai Wang, Wen Wang, Ruizhuo Song\",\"doi\":\"10.1109/ICCR55715.2022.10053874\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Smart transportation is an important part of building a smart city, and accurate traffic forecasting is crucial for citizen travel and urban construction. Aiming at the temporal and spatial dimensions in traffic forecasting, we focus on the extraction methods of the correlation between the two dimensions, and propose a new prediction model of the spatio-temporal graph attention network from the temporal correlation and the spatial correlation. The structure of the model is studied and analyzed. Finally, experiments are carried out on the mainstream traffic data sets, and by comparing with other prediction models, it is concluded that the evaluation indicators of the prediction model are better than other models.\",\"PeriodicalId\":441511,\"journal\":{\"name\":\"2022 4th International Conference on Control and Robotics (ICCR)\",\"volume\":\"40 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-12-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 4th International Conference on Control and Robotics (ICCR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCR55715.2022.10053874\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 4th International Conference on Control and Robotics (ICCR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCR55715.2022.10053874","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Traffic Prediction Model Based on Spatio-temporal Graph Attention Network
Smart transportation is an important part of building a smart city, and accurate traffic forecasting is crucial for citizen travel and urban construction. Aiming at the temporal and spatial dimensions in traffic forecasting, we focus on the extraction methods of the correlation between the two dimensions, and propose a new prediction model of the spatio-temporal graph attention network from the temporal correlation and the spatial correlation. The structure of the model is studied and analyzed. Finally, experiments are carried out on the mainstream traffic data sets, and by comparing with other prediction models, it is concluded that the evaluation indicators of the prediction model are better than other models.