{"title":"基于支持向量机的高方差公交出行时间预测","authors":"A. Bachu, Kranthi Kumar Reddy, L. Vanajakshi","doi":"10.3846/transport.2021.15220","DOIUrl":null,"url":null,"abstract":"Real-time bus travel time prediction has been an interesting problem since past decade, especially in India. Popular methods for travel time prediction include time series analysis, regression methods, Kalman filter method and Artificial Neural Network (ANN) method. Reported studies using these methods did not consider the high variance situations arising from the varying traffic and weather conditions, which is very common under heterogeneous and lane-less traffic conditions such as the one in India. The aim of the present study is to analyse the variance in bus travel time and predict the travel time accurately under such conditions. Literature shows that Support Vector Machines (SVM) technique is capable of performing well under such conditions and hence is used in this study. In the present study, nu-Support Vector Regression (SVR) using linear kernel function was selected. Two models were developed, namely spatial SVM and temporal SVM, to predict bus travel time. It was observed that in high mean and variance sections, temporal models are performing better than spatial. An algorithm to dynamically choose between the spatial and temporal SVM models, based on the current travel time, was also developed. The unique features of the present study are the traffic system under consideration having high variability and the variables used as input for prediction being obtained from Global Positioning System (GPS) units alone. The adopted scheme was implemented using data collected from GPS fitted public transport buses in Chennai (India). The performance of the proposed method was compared with available methods that were reported under similar traffic conditions and the results showed a clear improvement.","PeriodicalId":23260,"journal":{"name":"Transport","volume":"301 1","pages":""},"PeriodicalIF":1.3000,"publicationDate":"2021-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"BUS TRAVEL TIME PREDICTION USING SUPPORT VECTOR MACHINES FOR HIGH VARIANCE CONDITIONS\",\"authors\":\"A. Bachu, Kranthi Kumar Reddy, L. Vanajakshi\",\"doi\":\"10.3846/transport.2021.15220\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Real-time bus travel time prediction has been an interesting problem since past decade, especially in India. Popular methods for travel time prediction include time series analysis, regression methods, Kalman filter method and Artificial Neural Network (ANN) method. Reported studies using these methods did not consider the high variance situations arising from the varying traffic and weather conditions, which is very common under heterogeneous and lane-less traffic conditions such as the one in India. The aim of the present study is to analyse the variance in bus travel time and predict the travel time accurately under such conditions. Literature shows that Support Vector Machines (SVM) technique is capable of performing well under such conditions and hence is used in this study. In the present study, nu-Support Vector Regression (SVR) using linear kernel function was selected. Two models were developed, namely spatial SVM and temporal SVM, to predict bus travel time. It was observed that in high mean and variance sections, temporal models are performing better than spatial. An algorithm to dynamically choose between the spatial and temporal SVM models, based on the current travel time, was also developed. The unique features of the present study are the traffic system under consideration having high variability and the variables used as input for prediction being obtained from Global Positioning System (GPS) units alone. The adopted scheme was implemented using data collected from GPS fitted public transport buses in Chennai (India). The performance of the proposed method was compared with available methods that were reported under similar traffic conditions and the results showed a clear improvement.\",\"PeriodicalId\":23260,\"journal\":{\"name\":\"Transport\",\"volume\":\"301 1\",\"pages\":\"\"},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2021-08-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Transport\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.3846/transport.2021.15220\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"TRANSPORTATION SCIENCE & TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transport","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.3846/transport.2021.15220","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"TRANSPORTATION SCIENCE & TECHNOLOGY","Score":null,"Total":0}
BUS TRAVEL TIME PREDICTION USING SUPPORT VECTOR MACHINES FOR HIGH VARIANCE CONDITIONS
Real-time bus travel time prediction has been an interesting problem since past decade, especially in India. Popular methods for travel time prediction include time series analysis, regression methods, Kalman filter method and Artificial Neural Network (ANN) method. Reported studies using these methods did not consider the high variance situations arising from the varying traffic and weather conditions, which is very common under heterogeneous and lane-less traffic conditions such as the one in India. The aim of the present study is to analyse the variance in bus travel time and predict the travel time accurately under such conditions. Literature shows that Support Vector Machines (SVM) technique is capable of performing well under such conditions and hence is used in this study. In the present study, nu-Support Vector Regression (SVR) using linear kernel function was selected. Two models were developed, namely spatial SVM and temporal SVM, to predict bus travel time. It was observed that in high mean and variance sections, temporal models are performing better than spatial. An algorithm to dynamically choose between the spatial and temporal SVM models, based on the current travel time, was also developed. The unique features of the present study are the traffic system under consideration having high variability and the variables used as input for prediction being obtained from Global Positioning System (GPS) units alone. The adopted scheme was implemented using data collected from GPS fitted public transport buses in Chennai (India). The performance of the proposed method was compared with available methods that were reported under similar traffic conditions and the results showed a clear improvement.
期刊介绍:
At present, transport is one of the key branches playing a crucial role in the development of economy. Reliable and properly organized transport services are required for a professional performance of industry, construction and agriculture. The public mood and efficiency of work also largely depend on the valuable functions of a carefully chosen transport system. A steady increase in transportation is accompanied by growing demands for a higher quality of transport services and optimum efficiency of transport performance. Currently, joint efforts taken by the transport experts and governing institutions of the country are required to develop and enhance the performance of the national transport system conducting theoretical and empirical research.
TRANSPORT is an international peer-reviewed journal covering main aspects of transport and providing a source of information for the engineer and the applied scientist.
The journal TRANSPORT publishes articles in the fields of:
transport policy;
fundamentals of the transport system;
technology for carrying passengers and freight using road, railway, inland waterways, sea and air transport;
technology for multimodal transportation and logistics;
loading technology;
roads, railways;
airports, ports, transport terminals;
traffic safety and environment protection;
design, manufacture and exploitation of motor vehicles;
pipeline transport;
transport energetics;
fuels, lubricants and maintenance materials;
teamwork of customs and transport;
transport information technologies;
transport economics and management;
transport standards;
transport educology and history, etc.