CN102157075A - Method for predicting bus arrivals - Google Patents
Method for predicting bus arrivals Download PDFInfo
- Publication number
- CN102157075A CN102157075A CN 201110060991 CN201110060991A CN102157075A CN 102157075 A CN102157075 A CN 102157075A CN 201110060991 CN201110060991 CN 201110060991 CN 201110060991 A CN201110060991 A CN 201110060991A CN 102157075 A CN102157075 A CN 102157075A
- Authority
- CN
- China
- Prior art keywords
- data
- time
- bus
- real
- station
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for predicting bus arrivals in the technical field of information processing. The method comprises the following steps of: firstly, judging running stability through analyzing historical running data of buses and dividing into periods suitable for different predicating manners; secondly, analyzing real-time GPS (Global Positioning System) data by adopting a Kalman filtering method to predict an arrival time in a prediction period; and finally, synthesizing two predicted results of the historical data and the real-time data into final release information by weighting errors. The method disclosed by the invention has better accuracy and rapid computing speed, and is easy for physical realization and popularization.
Description
Technical field
What the present invention relates to is a kind of method of technical field of information processing, specifically is the Forecasting Methodology that a kind of public transport is arrived at a station.
Background technology
Public transport arrival time forecasting techniques is the difficult point and the emphasis of Bus information issue in the municipal intelligent traffic system.Urban public transport is being carried forward vigorously in Shanghai City at present, has formed the information-based blank of urban transportation operation management and service.As the traffic information distribution system of the important component part of municipal intelligent traffic system (ITS), fast-developing in recent years.But the construction relative orbit traffic information distribution system of conventional Bus information delivery system is also relatively backward, and the passenger is occurred repeatedly to the complaint of public transit vehicle operation conditions.
Present Forecasting Methodology, the source difference of selecting according to data can be divided into based on the arrival time Forecasting Methodology of historical data with based on the arrival time Forecasting Methodology of real time data.Can be divided into again according to highway section running time computing method difference: time series analysis, Kalman filtering, artificial neural network, etc. several different methods.
Above-mentioned forecast model respectively has characteristics in precision of prediction and practical application.Find by literature search,, suppose that the actual travel situation of bus centers on historical travel situations fluctuation within a narrow range based on time of arrival of historical data in the forecast model.Model is based on a large amount of historical datas, and such modular concept is understandable, simple to operate, uses extensively, but when accident causes the actual travel situation of bus to depart from account of the history significantly, prediction effect can be undesirable, and its precision of prediction is limited, and practicality is not strong.Artificial nerve network model has absolute advantage on precision of prediction, it is current a kind of bus forecast model time of arrival of extremely praising highly.But the selection of training function, learning function and some parameters of neural network but needs experience or examination to get, and net training time is longer.Therefore, realize that online real-time training and performance prediction are by no means easy.The mode that the utilization of Kalman filter model constantly approaches obtains higher forecast precision, and especially when shifting to an earlier date the one-step prediction journey time, this model has good estimated performance.But, the but constantly decline of its ability with the increase of step.
Summary of the invention
The present invention is directed to the prior art above shortcomings, the Forecasting Methodology that provides a kind of public transport to arrive at a station, the better and fast operation of accuracy is easy to physics realization and popularization.
The present invention is achieved by the following technical solutions, and the present invention judges operation stability by analyzing the public transport operation historical data, marks off the period that is fit to different prediction mode.In predetermined period, adopt Kalman filtering method to analyze real-time GPS data prediction arrival time, finally by the error weighting historical data and real time data being predicted the outcome for two kinds integrates as final releasing news.
The present invention specifically may further comprise the steps:
1) data acquisition: gather the bus running data by three kinds of methods, bus real time execution condition information is provided.
2) data processing: use the ArcGIS Geographic Information System (GIS) software, reject misdata, determine the moment of the real time position and the data return of bus.
3) public transport operation stability analysis: gather the public transport operation historical data in half a year, be divided into 18 kinds of situations, every kind of situation is carried out stability analysis respectively.
4) the bus arrival prediction mode is selected: according to the stability analysis result, select the suitable prediction mode of arriving at a station.
5) set up the time prediction model that arrives at a station: take all factors into consideration bus running historical data and real-time GPS data, the time prediction of arriving at a station respectively, according to the error in the forecasting process two kinds being predicted the outcome is weighted on average, is distributed on electronic stop plate for passenger's reference as final arrival time.
The inventive method on the basis of analyzing bus running stability, is selected different prediction mode according to the bus history data.In the period of isolating the time prediction that is fit to arrive at a station, adopt historical data and real-time GPS data to predict respectively, carry out the method for error weighting at last, the prediction bus arrival time.Take all factors into consideration bus running historical law and real-time road and telecommunication flow information thus, can predict the bus arrival time more accurately.
Description of drawings
Fig. 1 is the bus GPS data result.
Fig. 2 and Fig. 3 are the bus running stability analysis, and wherein website is selected the Xujiahui, and the public transport operation direction is descending, and the date is Saturday, day.
Fig. 4 is the bus arrival Forecasting Methodology process flow diagram based on historical and the weighting of real time data error.
Fig. 5 is the data acquisition synoptic diagram.
Fig. 6 is the data transmission synoptic diagram.
Fig. 7 and Fig. 8 report the some distribution schematic diagram for real-time GPS data.
Embodiment
Below embodiments of the invention are elaborated, present embodiment is being to implement under the prerequisite with the technical solution of the present invention, provided detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following embodiment.
Embodiment
As shown in Figure 4, be present embodiment prediction flow process, specific implementation roughly is divided into 5 parts: by vehicle-mounted RFID beacon equipment/card reader, annular electro magnetic induction coil and three kinds of modes of vehicle GPS transceiver terminal, gather the bus running data, bus real time execution condition information is provided; Use the ArcGIS Geographic Information System (GIS) software, reject misdata, determine the moment of the real time position and the data return of bus; According to gathering gained public transport operation historical data, the bus running of shunt piecewise analysis at times stability; Select corresponding bus arrival prediction mode according to the stability analysis result; To the highway section and the period of the time prediction that is fit to arrive at a station, the foundation time prediction model that arrives at a station, take all factors into consideration bus running historical data and real-time GPS data, the time prediction of arriving at a station respectively, according to the error in the forecasting process two kinds being predicted the outcome is weighted on average, is distributed on electronic stop plate for passenger's reference as final arrival time.
Specifically describe as follows:
Data acquisition: by vehicle-mounted RFID beacon equipment/card reader, electromagnetic induction coil and three kinds of modes of vehicle GPS transceiver terminal, gather the bus running data, bus real time execution condition information is provided.Wherein, vehicle-mounted RFID beacon equipment triggers place, station entrance-exit card reader in the turnover bus stop, and downstream station obtains the real-time position information of this bus, thereby this site location is presented on the electronic stop plate; Electromagnetic induction coil is gathered the positional information of bus, is used for the distance of real-time estimate bus distance objective website; The vehicle GPS transceiver terminal provides real-time GPS data, is used to analyze the moment and the real-time speed of bus at reward data point place, calculates the time that bus arrives targeted sites in conjunction with vehicle-mounted mileometer simultaneously.Bus data acquisition synoptic diagram as shown in Figure 5.
Data processing: mainly the real-time GPS data of bus vehicle GPS transceiver terminal record is handled, so that analyze the bus arrival time.Use the ArcGIS Geographic Information System (GIS) software, reject misdata, comprise the point that the gps data error is excessive, GPS repayment point and the interior cyclometer of bus that bus passes in and out the garage sooner or later are that zero GPS repays point etc., determine the moment of the real time position and the data return of bus.Time according to gps data repayment is divided into following several situation, i.e. Monday on working day, five, Tuesday on working day, three, four, Saturday on off-day, day.In each date, divide the period to repaying the moment of putting according to hourage, so that analyze the ruuning situation in each period.
The public transport operation stability analysis: the bus history data that is used for stability analysis is not that the long-acting more fruit of time span is good more, gathers the public transport operation historical data in half a year, is divided into 18 kinds of situations, i.e. (i) bus travel direction: up, descending; (ii) date: Monday, five, Tuesday, three, four, Saturday, day; (iii) period every day: morning peak, Wu Pingfeng, evening peak, every kind of situation is carried out stability analysis respectively.For the bus running situation, the variance of working time and standard deviation all are to weigh the index of its operation stability between average operating time between standing, average running speed and station.The unified form that adopts trimmed mean during computation of mean values is removed 10% minimum and maximum GPS repayment point data, and remaining data are asked arithmetic mean again, so can effectively avoid the influence of misdata to result of calculation.According to statistics and take all factors into consideration the passenger for the patient degree of stand-by period, with working time standard deviation be set at 1 minute, when promptly finally predicting arrival time, the historical data deviation that allows institute's reference is within 1 minute.
The bus arrival prediction mode is selected: according to the stability analysis result, select the suitable prediction mode of arriving at a station.(i) predict bus which station forwardly.This prediction mode is suitable for least stable period of bus running situation or highway section, in the forecasting process, use hardware device to gather the information of bus, for example enter the station and set off, be directly passed to the electronic stop plate of targeted sites by the information transmission path at highway section, upstream key position.(ii) predict the distance of bus distance objective website.Be applicable to close together between the website, the metastable highway section of bus running.Adopt sensor technology, wireless beacon in conjunction with the GPS technology, can know the distance of bus in the targeted sites upstream.Along with bus more and more near targeted sites, the range information issued on the electronic stop plate is brought in constant renewal in, the passenger can be known the actual range between bus and the targeted sites.Predict that (iii) bus arrives targeted sites and how long also needs.This prediction mode is the most directly perceived, and being applicable to has certain distance between the website, and the road traffic delay complexity is low, the situation that bus running is stable.Adopt bus running historical data or real-time GPS data, set up the model of bus running state, and calculate the time that bus arrives targeted sites by setting up forecast model and prediction algorithm.
The foundation time prediction model that arrives at a station: take all factors into consideration bus running historical data and real-time GPS data, the time prediction of arriving at a station respectively, according to the error in the forecasting process two kinds being predicted the outcome is weighted on average, is distributed on electronic stop plate for passenger's reference as final arrival time.Wherein according to historical data prediction arrival time, according to up-downgoing real site series arrangement, subtract each other the distance that can obtain between adjacent two stations with the mileometer numerical value of back one website and the mileometer numerical value of adjacent last website, calculate average operating time and the average overall travel speed of bus between website.For error is reduced as far as possible, the process of computation of mean values all adopts the form of trimmed mean.It is 30 meters that drift in the GPS measuring process causes the error of distance between adjacent two stations, the variance of working time and travelling speed between statistics is stood in the computation process.According to real-time GPS data prediction arrival time, adopt two kinds of data return modes, promptly by time interval reward data with by distance interval reward data, shown in accompanying drawing 7 and accompanying drawing 8, set up Kalman's iterative model respectively, the bus that Kalman's iterative algorithm prediction is obtained at the real-time speed at next data return point place and constantly is converted into the time that bus arrives targeted sites, and according to the working time that produces in the error correlation matrix statistical forecast process and the variance of travelling speed.At last, two kinds of Data Sources predicting the outcome that time prediction obtains of arriving at a station respectively, according to variance working time that produces in the forecasting process, be weighted average, as finally being distributed on predicting the outcome on the electronic stop plate.Because during final arrival time predicted the outcome, with each renewal of real time data, the historical data predicted portions also will be brought in constant renewal in.To be bus remain a constant speed between the station hypothesis prerequisite of historical data renewal process travels.Because the Kalman filtering iterative algorithm requires original state is set, so this paper all is set to historical statistics mean value with original state, and promptly historical data and real-time GPS data are impartial to the influence that finally predicts the outcome.The data return mode difference of employing also can be different according to the shared proportion variation of arrival time difference in final issue predicts the outcome of historical data and real-time GPS data prediction.
Claims (2)
1. Forecasting Methodology that public transport is arrived at a station, it is characterized in that, judge operation stability by analyzing the public transport operation historical data, mark off the period that is fit to different prediction mode, in predetermined period, adopt Kalman filtering method to analyze real-time GPS data prediction arrival time, finally by the error weighting historical data and real time data being predicted the outcome for two kinds integrates as final releasing news.
2. the Forecasting Methodology that public transport according to claim 1 is arrived at a station is characterized in that, described method specifically may further comprise the steps:
The first step, data acquisition: gather the bus running data by three kinds of methods, bus real time execution condition information is provided;
Second step, data processing: use the ArcGIS Geographic Information System (GIS) software, reject misdata, determine the moment of the real time position and the data return of bus;
The 3rd step, public transport operation stability analysis: gather the public transport operation historical data in half a year, be divided into 18 kinds of situations, every kind of situation is carried out stability analysis respectively;
The 4th step, bus arrival prediction mode are selected: according to the stability analysis result, select the suitable prediction mode of arriving at a station;
The 5th step, set up the time prediction model that arrives at a station: take all factors into consideration bus running historical data and real-time GPS data, the time prediction of arriving at a station respectively, according to the error in the forecasting process two kinds being predicted the outcome is weighted on average, is distributed on electronic stop plate for passenger's reference as final arrival time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110060991 CN102157075B (en) | 2011-03-15 | 2011-03-15 | Method for predicting bus arrivals |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201110060991 CN102157075B (en) | 2011-03-15 | 2011-03-15 | Method for predicting bus arrivals |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102157075A true CN102157075A (en) | 2011-08-17 |
CN102157075B CN102157075B (en) | 2013-07-03 |
Family
ID=44438550
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201110060991 Expired - Fee Related CN102157075B (en) | 2011-03-15 | 2011-03-15 | Method for predicting bus arrivals |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102157075B (en) |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103247173A (en) * | 2013-05-27 | 2013-08-14 | 苏州洁祥电子有限公司 | Bus arrival time prompt system |
CN103310651A (en) * | 2013-05-24 | 2013-09-18 | 北京市交通信息中心 | Bus arrival prediction method based on real-time traffic status information |
CN104064024A (en) * | 2014-06-23 | 2014-09-24 | 银江股份有限公司 | Public transport vehicle arrival time prediction method based on history data |
WO2014146812A1 (en) * | 2013-03-22 | 2014-09-25 | Here Global B.V. | Vehicle arrival prediction |
CN104123841A (en) * | 2014-08-14 | 2014-10-29 | 苏州大学 | Method and system for acquiring arrival time of vehicle |
CN104217605A (en) * | 2013-05-31 | 2014-12-17 | 张伟伟 | Bus arrival time estimation method and device |
CN104376716A (en) * | 2014-11-28 | 2015-02-25 | 南通大学 | Method for dynamically generating bus timetables on basis of Bayesian network models |
CN104424811A (en) * | 2013-08-26 | 2015-03-18 | 北大方正集团有限公司 | Prompting method for bus arrival, and mobile terminal |
CN105224992A (en) * | 2014-05-28 | 2016-01-06 | 国际商业机器公司 | To waiting for the method and system predicted of ridership and evaluation method and system |
CN105390013A (en) * | 2015-11-18 | 2016-03-09 | 北京工业大学 | Method for predicting bus arrival time based on bus IC card |
CN107798865A (en) * | 2016-09-07 | 2018-03-13 | 高德信息技术有限公司 | A kind of public bus network running time predictor method and device |
CN107945560A (en) * | 2017-12-21 | 2018-04-20 | 大连海事大学 | A kind of public transport smart electronics stop sign information display control method and system |
CN108898872A (en) * | 2018-09-12 | 2018-11-27 | 南京行者易智能交通科技有限公司 | Shift method of adjustment based on vehicle intelligent terminal equipment and history passenger flow big data |
CN109191845A (en) * | 2018-09-28 | 2019-01-11 | 吉林大学 | A kind of public transit vehicle arrival time prediction technique |
CN109409598A (en) * | 2018-10-23 | 2019-03-01 | 河南工业大学 | Link travel time prediction method and device based on SVM and Kalman filtering |
CN109637178A (en) * | 2018-11-29 | 2019-04-16 | 北京依途网络科技有限公司 | Vehicle arrival time determines method and apparatus |
CN109920248A (en) * | 2019-03-05 | 2019-06-21 | 南通大学 | A kind of public transport arrival time prediction technique based on GRU neural network |
CN109993959A (en) * | 2017-12-29 | 2019-07-09 | 中国移动通信集团辽宁有限公司 | Method, apparatus, equipment and the computer storage medium of positioning regular bus in real time |
CN110361019A (en) * | 2018-04-11 | 2019-10-22 | 北京搜狗科技发展有限公司 | For predicting method, apparatus, electronic equipment and the readable medium of navigation time |
CN110459056A (en) * | 2019-08-26 | 2019-11-15 | 南通大学 | A kind of public transport arrival time prediction technique based on LSTM neural network |
CN110610016A (en) * | 2019-07-15 | 2019-12-24 | 广东毓秀科技有限公司 | Method for predicting rail transit stopping problem based on big data machine learning |
CN110767285A (en) * | 2019-09-27 | 2020-02-07 | 维沃移动通信有限公司 | Reminding method and terminal equipment |
CN111091231A (en) * | 2019-11-25 | 2020-05-01 | 珠海格力电器股份有限公司 | Prediction model training method, time prediction method, training device and terminal |
CN111554118A (en) * | 2020-04-24 | 2020-08-18 | 深圳职业技术学院 | Dynamic prediction method and system for bus arrival time |
CN112015778A (en) * | 2020-08-19 | 2020-12-01 | 上海满盛信息技术有限公司 | Water fingerprint prediction algorithm |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006093682A2 (en) * | 2005-02-25 | 2006-09-08 | Mci, Inc. | Method and apparatus for data filtering in a tracking system |
CN1963847A (en) * | 2005-11-07 | 2007-05-16 | 同济大学 | Method for forecasting reaching station of bus |
-
2011
- 2011-03-15 CN CN 201110060991 patent/CN102157075B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006093682A2 (en) * | 2005-02-25 | 2006-09-08 | Mci, Inc. | Method and apparatus for data filtering in a tracking system |
CN1963847A (en) * | 2005-11-07 | 2007-05-16 | 同济大学 | Method for forecasting reaching station of bus |
Non-Patent Citations (2)
Title |
---|
《交通与计算机》 20060430 江丽炜 等 智能公交电子站牌显示时间预测方法研究 第31-34页 第24卷, 第2期 * |
《公路交通科技》 20091231 黄正东 等 基于GIS 可达性模型的公交出行预测 第138-141页 第26卷, * |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9020754B2 (en) | 2013-03-22 | 2015-04-28 | Here Global B.V. | Vehicle arrival prediction |
EP2976762B1 (en) * | 2013-03-22 | 2022-11-30 | HERE Global B.V. | Vehicle arrival prediction |
WO2014146812A1 (en) * | 2013-03-22 | 2014-09-25 | Here Global B.V. | Vehicle arrival prediction |
CN103310651A (en) * | 2013-05-24 | 2013-09-18 | 北京市交通信息中心 | Bus arrival prediction method based on real-time traffic status information |
CN103310651B (en) * | 2013-05-24 | 2016-03-02 | 北京市交通信息中心 | A kind of public transport based on real-time road condition information is arrived at a station Forecasting Methodology |
CN103247173A (en) * | 2013-05-27 | 2013-08-14 | 苏州洁祥电子有限公司 | Bus arrival time prompt system |
CN104217605A (en) * | 2013-05-31 | 2014-12-17 | 张伟伟 | Bus arrival time estimation method and device |
CN104424811A (en) * | 2013-08-26 | 2015-03-18 | 北大方正集团有限公司 | Prompting method for bus arrival, and mobile terminal |
CN105224992A (en) * | 2014-05-28 | 2016-01-06 | 国际商业机器公司 | To waiting for the method and system predicted of ridership and evaluation method and system |
CN104064024A (en) * | 2014-06-23 | 2014-09-24 | 银江股份有限公司 | Public transport vehicle arrival time prediction method based on history data |
CN104123841A (en) * | 2014-08-14 | 2014-10-29 | 苏州大学 | Method and system for acquiring arrival time of vehicle |
CN104376716A (en) * | 2014-11-28 | 2015-02-25 | 南通大学 | Method for dynamically generating bus timetables on basis of Bayesian network models |
CN105390013B (en) * | 2015-11-18 | 2018-12-18 | 北京工业大学 | A method of public transport arrival time is predicted using bus IC card |
CN105390013A (en) * | 2015-11-18 | 2016-03-09 | 北京工业大学 | Method for predicting bus arrival time based on bus IC card |
CN107798865A (en) * | 2016-09-07 | 2018-03-13 | 高德信息技术有限公司 | A kind of public bus network running time predictor method and device |
CN107945560A (en) * | 2017-12-21 | 2018-04-20 | 大连海事大学 | A kind of public transport smart electronics stop sign information display control method and system |
CN109993959A (en) * | 2017-12-29 | 2019-07-09 | 中国移动通信集团辽宁有限公司 | Method, apparatus, equipment and the computer storage medium of positioning regular bus in real time |
CN110361019B (en) * | 2018-04-11 | 2022-01-11 | 北京搜狗科技发展有限公司 | Method, device, electronic equipment and readable medium for predicting navigation time |
CN110361019A (en) * | 2018-04-11 | 2019-10-22 | 北京搜狗科技发展有限公司 | For predicting method, apparatus, electronic equipment and the readable medium of navigation time |
CN108898872A (en) * | 2018-09-12 | 2018-11-27 | 南京行者易智能交通科技有限公司 | Shift method of adjustment based on vehicle intelligent terminal equipment and history passenger flow big data |
CN108898872B (en) * | 2018-09-12 | 2019-06-14 | 南京行者易智能交通科技有限公司 | Shift method of adjustment based on vehicle intelligent terminal equipment and history passenger flow big data |
CN109191845A (en) * | 2018-09-28 | 2019-01-11 | 吉林大学 | A kind of public transit vehicle arrival time prediction technique |
CN109409598A (en) * | 2018-10-23 | 2019-03-01 | 河南工业大学 | Link travel time prediction method and device based on SVM and Kalman filtering |
CN109637178A (en) * | 2018-11-29 | 2019-04-16 | 北京依途网络科技有限公司 | Vehicle arrival time determines method and apparatus |
CN109920248A (en) * | 2019-03-05 | 2019-06-21 | 南通大学 | A kind of public transport arrival time prediction technique based on GRU neural network |
CN109920248B (en) * | 2019-03-05 | 2021-09-17 | 南通大学 | Bus arrival time prediction method based on GRU neural network |
CN110610016A (en) * | 2019-07-15 | 2019-12-24 | 广东毓秀科技有限公司 | Method for predicting rail transit stopping problem based on big data machine learning |
CN110459056A (en) * | 2019-08-26 | 2019-11-15 | 南通大学 | A kind of public transport arrival time prediction technique based on LSTM neural network |
CN110767285A (en) * | 2019-09-27 | 2020-02-07 | 维沃移动通信有限公司 | Reminding method and terminal equipment |
CN111091231A (en) * | 2019-11-25 | 2020-05-01 | 珠海格力电器股份有限公司 | Prediction model training method, time prediction method, training device and terminal |
CN111091231B (en) * | 2019-11-25 | 2022-04-15 | 珠海格力电器股份有限公司 | Prediction model training method, time prediction method, training device and terminal |
CN111554118A (en) * | 2020-04-24 | 2020-08-18 | 深圳职业技术学院 | Dynamic prediction method and system for bus arrival time |
CN111554118B (en) * | 2020-04-24 | 2022-01-25 | 深圳职业技术学院 | Dynamic prediction method and system for bus arrival time |
CN112015778A (en) * | 2020-08-19 | 2020-12-01 | 上海满盛信息技术有限公司 | Water fingerprint prediction algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN102157075B (en) | 2013-07-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102157075B (en) | Method for predicting bus arrivals | |
CN103810851B (en) | A kind of traffic trip mode identification method based on mobile phone location | |
De Fabritiis et al. | Traffic estimation and prediction based on real time floating car data | |
CN111653088B (en) | Vehicle driving quantity prediction model construction method, prediction method and system | |
CN105550789A (en) | Method for predicting bus taking passenger flow | |
CN101751777B (en) | Dynamic urban road network traffic zone partitioning method based on space cluster analysis | |
Wang et al. | Estimating dynamic origin-destination data and travel demand using cell phone network data | |
CN102708698B (en) | Vehicle optimal-path navigation method based on vehicle internet | |
CN101908270B (en) | Event judging apparatus | |
Gong et al. | Hybrid dynamic prediction model of bus arrival time based on weighted of historical and real-time GPS data | |
CN102460534A (en) | Predicting expected road traffic conditions based on historical and current data | |
KR20140128063A (en) | Traffic prediction system | |
Xinghao et al. | Predicting bus real-time travel time basing on both GPS and RFID data | |
Hu et al. | Simulation-assignment-based travel time prediction model for traffic corridors | |
CN109637134A (en) | A kind of public transport device matching process | |
Habtie et al. | Artificial neural network based real-time urban road traffic state estimation framework | |
Ozbay et al. | Big data and the calibration and validation of traffic simulation models | |
Anusha et al. | Dynamical systems approach for queue and delay estimation at signalized intersections under mixed traffic conditions | |
CN103854479A (en) | Method and device for measuring traffic flow data of road segment without detector | |
CN104835321A (en) | Lane vehicle flow statistical system and lane vehicle flow statistical method | |
CN109754606A (en) | A method of based on taxi location prediction congestion in road situation | |
Chang et al. | Traffic congestion identification method based on GPS equipped floating car | |
Raiyn | Speed adaptation in urban road network management | |
Sharmila et al. | Bus arrival time prediction and measure of uncertainties using survival models | |
Chen et al. | Historical travel time based bus-arrival-time prediction model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130703 Termination date: 20180315 |