CN109308803A - Reliability Analysis of Path Travel Time Based on Stochastic Fluctuation Model - Google Patents
Reliability Analysis of Path Travel Time Based on Stochastic Fluctuation Model Download PDFInfo
- Publication number
- CN109308803A CN109308803A CN201810854868.6A CN201810854868A CN109308803A CN 109308803 A CN109308803 A CN 109308803A CN 201810854868 A CN201810854868 A CN 201810854868A CN 109308803 A CN109308803 A CN 109308803A
- Authority
- CN
- China
- Prior art keywords
- travel time
- model
- path
- time
- fluctuation
- 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.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000002688 persistence Effects 0.000 claims abstract description 3
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000013485 heteroscedasticity test Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005054 agglomeration Methods 0.000 claims 1
- 230000002776 aggregation Effects 0.000 claims 1
- 230000007246 mechanism Effects 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 abstract description 2
- 230000035939 shock Effects 0.000 abstract 1
- 230000008859 change Effects 0.000 description 7
- 241001493796 Paraboea crassifolia Species 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241001123248 Arma Species 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 241000287433 Turdus Species 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004925 denaturation Methods 0.000 description 1
- 230000036425 denaturation Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明公开了一种基于随机波动模型的行程时间可靠性分析方法，利用经过目标路径的历史行程时间信息，针对行程时间波动的尖峰后尾、集群性等特点，引入计量经济学中的随机波动(SV)模型及其扩展形式，利用模型参数从不同的角度来对行程时间的可靠性进行评价，通过模型，既对行程时间波动的时变性、持续性等做出评价，也对系统外部信息的分布进行描述，分析行程时间波动对外部信息冲击的反应机制，从而对路径行程时间的可靠性做出评价。本发明对于城市交通管理者而言，可以帮助缓解交通拥堵、科学规划路网，而且对于出行者的路径规划，优化路线决策提供信息参考。本发明作为一种基于随机波动模型的行程时间预测方法可广泛应用于交通领域。
The invention discloses a travel time reliability analysis method based on a stochastic fluctuation model, which utilizes the historical travel time information passing through a target path, and introduces random fluctuations in econometrics according to the characteristics of travel time fluctuations such as spikes, tails and clusters. (SV) model and its extended form, use model parameters to evaluate the reliability of travel time from different perspectives. Through the model, it not only evaluates the time-varying, persistence, etc. of travel time fluctuations, but also evaluates the external information of the system. The distribution of the route is described, and the response mechanism of the travel time fluctuation to the shock of external information is analyzed, so as to evaluate the reliability of the travel time of the route. For urban traffic managers, the present invention can help relieve traffic congestion, plan road network scientifically, and provide information reference for traveler's route planning and route optimization decision. The present invention can be widely used in the traffic field as a travel time prediction method based on a random fluctuation model.
Description
Technical field
The present invention relates to path forms time reliabilities to evaluate field, specifically a kind of section based on Stochastic Volatility Model
Travel Time Reliability analysis method.
Background technique
Journey time reflects the Trip Costs from starting point to destination, due to exophytic demand and supply factor and
It interacts between endogenous Driver's Factors, traveler is caused to generate random fluctuation in the journey time in path.In road network
Path forms time change there is time variation, randomness and uncertainty, and show complicated wave characteristic.Existing
In numerous studies, establish the prediction model of journey time using mathematical statistics method, main method include: history averaging model,
Linear regression model (LRM), time series models, Kalman filter model, Markov prediction, Maximum-likelihood estimation model etc..
However, traffic system is the random process for obeying certain probability distribution, the fluctuation of journey time is then this random data
The uncertainty of the realization traffic system of generating process, so that the time series of path forms time change is advised in numerical value change
There are some unique features in rule, be mainly shown as that the heteroscedasticity heteroscedasticity of journey time variation violates linear return
Return model about homoscedasticity it is assumed that but also conventional Time series analysis method (such as arma modeling) is no longer applicable in,
The parameter Estimation amount that model obtains is no longer valid, and the Forecasting of Travel Time value obtained based on model can also generate deviation.
Travel Time Reliability refers to that under a certain road, traffic, environment, traveler is in certain a road section, OD pairs of stroke
Between be no more than specified time probability, describe the degree of journey time variability.Relative to average travel time, journey time
Reliability index reflects the randomness and fluctuation of section or road network operating status comprehensively.Because average travel time characterizes sample
This intensity, but has ignored the details and variation range of journey time, cannot comprehensively embody the change of Link Travel Time
Change the stable state in section and traffic circulation.
The present invention is based on the characteristics such as the spike thickness tail of path forms time fluctuation, sociability, are introduced into econometrics
Stochastic Volatility Model (Stochastic Volatility Model, SV) and its extension form, using model parameter from different
The reliability of path journey time is analyzed and evaluated in angle.By model, both to path journey time fluctuation time variation,
Duration is evaluated, and also the distribution of exterior information is described, and outside is believed in the fluctuation of analysis path journey time
Cease the reaction mechanism of impact.To realize the overall evaluation to path Travel Time Reliability.Compared to ARCH model cluster
(Autoregressive Conditional Heteroskedasticity Model, autoregressive conditional different Variance model), SV
Class model describes the time-varying fluctuation of variance using unobservable random process, can be more accurate when comprehensively portraying stroke
Between sequence fluctuation characteristic.
As the pith of traffic behavior evaluation, Travel Time Reliability is evaluated for urban traffic control person,
They are essential decision factors, and traffic congestion, planning of science activities road network are alleviated in help.In addition Travel Time Reliability can also
For traveler path planning, to improve trip quality, optimization route line decision provides information reference.
Summary of the invention
The path forms time reliability analysis method based on Stochastic Volatility Model that the invention proposes a kind of, with realization pair
Path forms time reliability carries out more comprehensive assay.Not only enable manager is more efficiently to manage and control road
The operating status of net, and necessary trip information reference can be provided for traveler.
The purpose of the present invention is what is be achieved through the following technical solutions: the path forms time reliability based on random fluctuation
Analysis method, it is as follows that the method comprising the steps of:
A kind of path forms time reliability analysis method based on Stochastic Volatility Model, which is characterized in that include with
Lower step:
(1) by the floating car data information obtained, the data information in each path is extracted；Each path is calculated in difference
The journey time of period.Path forms time calculation method are as follows:
In formula, ti(t) indicate path i in the path forms time of t moment；IiIndicate the section set of composition path i, lj
Indicate the length of section j, vj(t) the road-section average travel speed of section j is indicated.
(2) exceptional value and missing values processing, and successively sequence obtains path row sequentially in time with 5min time interval
The time series of journey time.
(3) stability bandwidth of journey time is calculated, and statistics is described to stability bandwidth sequence.Path forms time fluctuation rate
Method are as follows:
Vt=(lnTt-lnTt-1)×100
Wherein, TtFor in the path forms time of t moment.
(4) Stochastic Volatility Model in each path is established.
Essentially random volatility model is as follows:
Vt=exp (ht/2)εt
According to the journey time stability bandwidth sequence in each path establish Forecast Means, thickness tail SV model, mean value SV model with
And lever SV model, estimated using parameter of the WinBUGS software to each equation.
(5) overall evaluation is fluctuated to path journey time.The whole fluctuation of path forms time can be by the time variation that fluctuates
It is evaluated, i.e., is reflected by the heteroscedasticity of journey time stability bandwidth series error item.In addition journey time stability bandwidth
Spike Boea crassifolia, concentration, duration etc. can also carry out quantitative analysis by the estimation of model parameter.To obtain to path row
The fail-safe analysis of journey time.
The invention has the benefit that being introduced into the Stochastic Volatility Model of financial field to the reliable of path journey time
Property evaluation in, the fluctuation characteristic of journey time is accurately comprehensively obtained by the parameter Estimation of SV model, providing journey time can
By the analysis method of property, reference is provided for the evaluation of the traffic reliability in region and city, and provide better trip for traveler
Planning guidance.
Detailed description of the invention
Fig. 1 is path forms time reliability analysis flow chart diagram；
Fig. 2 is the flow chart that WinBUGS realizes SV modeling；
Fig. 3 is the code that WinBUGS realizes SV-N model；
Specific embodiment
The present invention provides a kind of path forms time reliability analysis method based on Stochastic Volatility Model, below with reference to attached
The present invention will be described in detail for figure, as shown in Figure 1, the specific steps of the present invention are as follows:
Step 1: by the floating car data information of acquisition, the data information in each path is extracted；Each path is calculated to exist
The journey time of different periods and matching road section length.Path forms time calculation method are as follows:
In formula, ti(t) indicate path i in the path forms time of t moment；IiIndicate the section set of composition path i, lj
Indicate the length of section j, vj(t) the road-section average travel speed of section j is indicated.
Step 2: exceptional value and missing values processing, and successively sequence obtains road sequentially in time with 5min time interval
The time series of diameter journey time, the average value polishing of the missing values journey time of surrounding time point.
Step 3: journey time sequence itself is a non-stable time series, and still, correlative study shows right
After journey time sequence carries out logarithmetics processing, obtained time series is the whole sequence of a single order list that is, logarithm
Change treated journey time sequence, first-order difference sequence is a stable time series.It is counted using the sequence
Analysis, can eliminate the heteroscedasticity of stochastic error in regression model, reduce the interference of uncertain factor, to guarantee to divide
Analysing result has good statistical property.
With reference to the definition in economics to earning rate etc., the first-order difference of journey time logarithm is defined as journey time
Stability bandwidth, i.e.,
Vt=(lnTt-lnTt-1)×100
Wherein, TtFor in the path forms time of t moment.
Step 4: journey time wave characteristic is divided according to obtained journey time stability bandwidth time series track
Analysis calculates the preliminary analysis that mean value, standard deviation, the degree of bias, kurtosis, JB statistic etc. carry out fluctuation.
Standard deviation
The degree of bias
Kurtosis
Jarque-Beta statistic
Wherein, n is sample size, and k is freedom degree.In each statistic, Jarque-Bera statistic is for examining one group
Can sample think the statistic from normal distribution totality.
Step 5: the Stochastic Volatility Model in each path is established.
(1) SV-N model
Taylor (1986) proposes standard SV model in the autoregression behavior for explaining financial income sequence volatility model, letter
Referred to as SV-N model, form are as follows:
yt=exp (θt/2)εt,εt~i.i.d N (0,1) t=1,2 ..., n
θt=μ+φ (θt-1-μ)+ηt,ηt~i.i.d N (0, τ2), t=1,2 ..., n
Wherein ytIndicate t days journey time stability bandwidths, εtFor independent identically distributed white noise acoustic jamming, obeying mean value is
0, the normal distribution that variance is 1；ηtHorizontal for the disturbance of independent identically distributed fluctuation, obeying mean value is 0, variance τ2Normal state
Distribution.Error term ηtWith εtIt is incoherent, is all unobservable.φ is persistence parameter, reflects current fluctuation to future
The influence of fluctuation, and for | φ | < 1, SV model are covariance stationaries.Potential fluctuation θtObey a duration ginseng
Number is Gauss AR (1) process of φ.
(2) SV-T model
SV-T model is a kind of thick tail SV model, has the ability for the spike rear molding for capturing journey time sequence.In SV-T
In model, ε is disturbedtThe t that freedom degree is ω is obeyed to be distributed:
yt=exp (θt/2)εt,εt~i.i.d t (0,1, ω)
θt=μ+φ (θt-1-μ)+ηt,ηt~i.i.d N (0, τ2), t=1,2 ..., n
(3) SV-MN model
It is generalized in SV model by the ARCH-M model that Engle, Lilien and Robins are proposed by Koopman (2002),
Propose SV-M model.Risk compensation is considered in SV-M model.The form of SV-MN model based on normal distribution is as follows:
yt=dexp (θt)+εtexp(θt/2),εt~i.i.d N (0,1) t=1,2 ..., n
θt=μ+φ (θt-1-μ)+ηt,ηt~i.i.d N (0, τ2) t=1,2 ..., n
Wherein dexp (θt) it is risk compensation, d refers to the regression coefficient of measurement mean value fluctuation effect.θtObedience mean value be μ+
φ(θt-1- μ), variance τ2Normal distribution, i.e. θt|μ,φ,θt-1~N (μ+φ (θt-1-μ),τ2)。
(4) Leverage SV model
If journey time changes same magnitude upward or downward, its fluctuation during slide downward wants high
Fluctuation in moving upwards, is referred to as leverage.It is compared with Forecast Means, leverage SV (Leverage SV)
Model has an additional parameter, is exactly correlation coefficient ρ.
yt|θt, ρ=exp (θt/2)εtεt~i.i.d tkT=1,2 ..., n
θt+1|θt,μ,φ,τ2, ρ=μ+φ (θt-μ)+τηtηt~i.i.d N (0, τ2) t=1,2 ..., n-1
According to the journey time stability bandwidth sequence in each path establish Forecast Means, thickness tail SV model, mean value SV model with
And the SV model containing external factor, estimated using parameter of the WinBUGS software to each equation.
By taking SV-N model as an example, code is as shown in figure 3, output parameter is respectively mu, phi, tau.Mu is used to investigate wave
Dynamic mean value is horizontal, and phi is used to investigate the duration of fluctuation, and the disturbance that tau is used to investigate fluctuation is horizontal.
Step 6: the overall evaluation is fluctuated to path journey time.The whole fluctuation of path forms time can by fluctuate when
Denaturation is evaluated, i.e., is reflected by the heteroscedasticity of journey time stability bandwidth series error item.In addition journey time fluctuates
The spike Boea crassifolia of rate, concentration, duration etc. can also pass through the estimation of model parameter and carry out quantitative analysis.To be satisfied the need
The fail-safe analysis of diameter journey time.
The technical concepts and features of above embodiment only to illustrate the invention, its object is to allow be familiar with technique
People can understand the contents of the present invention and be implemented, and it is not intended to limit the scope of the present invention, it is all according to the present invention
Equivalent change or modification made by Spirit Essence, should be covered by the scope of protection of the present invention.
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810854868.6A CN109308803A (en) | 2018-07-31 | 2018-07-31 | Reliability Analysis of Path Travel Time Based on Stochastic Fluctuation Model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810854868.6A CN109308803A (en) | 2018-07-31 | 2018-07-31 | Reliability Analysis of Path Travel Time Based on Stochastic Fluctuation Model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109308803A true CN109308803A (en) | 2019-02-05 |
Family
ID=65226060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810854868.6A Pending CN109308803A (en) | 2018-07-31 | 2018-07-31 | Reliability Analysis of Path Travel Time Based on Stochastic Fluctuation Model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109308803A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110634292A (en) * | 2019-09-19 | 2019-12-31 | 北京航空航天大学 | A Reliability Estimation Method of Travel Time Based on Road Resistance Performance Function |
| CN112270355A (en) * | 2020-10-28 | 2021-01-26 | 长沙理工大学 | Active safety prediction method based on big data technology and SAE-GRU |
| CN113379233A (en) * | 2021-06-08 | 2021-09-10 | 重庆大学 | Travel time reliability estimation method and device based on high-order moment |
| CN113554873A (en) * | 2021-07-20 | 2021-10-26 | 重庆大学 | Travel time volatility prediction method and device based on high-order moment |
| CN115759369A (en) * | 2022-11-03 | 2023-03-07 | 昆明理工大学 | Urban rail transit network travel time reliability prediction method |
| CN117130263A (en) * | 2023-10-26 | 2023-11-28 | 博创联动科技股份有限公司 | Intelligent control method and system for whole vehicle based on big data of Internet of vehicles |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105679021A (en) * | 2016-02-02 | 2016-06-15 | 重庆云途交通科技有限公司 | Travel time fusion prediction and query method based on traffic big data |
| CN106023588A (en) * | 2016-06-15 | 2016-10-12 | 重庆云途交通科技有限公司 | Traffic big data-based travel time extraction, prediction and query method |
| CN106384509A (en) * | 2016-10-08 | 2017-02-08 | 大连理工大学 | Urban road driving time distribution estimation method considering taxi operation states |
-
2018
- 2018-07-31 CN CN201810854868.6A patent/CN109308803A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105679021A (en) * | 2016-02-02 | 2016-06-15 | 重庆云途交通科技有限公司 | Travel time fusion prediction and query method based on traffic big data |
| CN106023588A (en) * | 2016-06-15 | 2016-10-12 | 重庆云途交通科技有限公司 | Traffic big data-based travel time extraction, prediction and query method |
| CN106384509A (en) * | 2016-10-08 | 2017-02-08 | 大连理工大学 | Urban road driving time distribution estimation method considering taxi operation states |
Non-Patent Citations (2)
| Title |
|---|
| 李玮峰 等: "基于ARCH模型簇的路径行程时间可靠性分析", 《交通运输系统工程与信息》 * |
| 陈杨林 等: "随机波动率模型分析与应用", 《九江职业技术学院学报》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110634292A (en) * | 2019-09-19 | 2019-12-31 | 北京航空航天大学 | A Reliability Estimation Method of Travel Time Based on Road Resistance Performance Function |
| CN110634292B (en) * | 2019-09-19 | 2020-10-16 | 北京航空航天大学 | A Reliability Estimation Method of Travel Time Based on Road Resistance Performance Function |
| CN112270355A (en) * | 2020-10-28 | 2021-01-26 | 长沙理工大学 | Active safety prediction method based on big data technology and SAE-GRU |
| CN112270355B (en) * | 2020-10-28 | 2023-12-05 | 长沙理工大学 | Active safety prediction method based on big data technology and SAE-GRU |
| CN113379233A (en) * | 2021-06-08 | 2021-09-10 | 重庆大学 | Travel time reliability estimation method and device based on high-order moment |
| CN113379233B (en) * | 2021-06-08 | 2023-02-28 | 重庆大学 | Travel time reliability estimation method and device based on high-order moment |
| CN113554873A (en) * | 2021-07-20 | 2021-10-26 | 重庆大学 | Travel time volatility prediction method and device based on high-order moment |
| CN115759369A (en) * | 2022-11-03 | 2023-03-07 | 昆明理工大学 | Urban rail transit network travel time reliability prediction method |
| CN115759369B (en) * | 2022-11-03 | 2025-01-17 | 昆明理工大学 | Urban rail transit network travel time reliability prediction method |
| CN117130263A (en) * | 2023-10-26 | 2023-11-28 | 博创联动科技股份有限公司 | Intelligent control method and system for whole vehicle based on big data of Internet of vehicles |
| CN117130263B (en) * | 2023-10-26 | 2024-01-16 | 博创联动科技股份有限公司 | Intelligent control method and system for whole vehicle based on big data of Internet of vehicles |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109308803A (en) | Reliability Analysis of Path Travel Time Based on Stochastic Fluctuation Model | |
| Anvari et al. | Automated Box–Jenkins forecasting tool with an application for passenger demand in urban rail systems | |
| CN109308343A (en) | A Travel Time Prediction and Reliability Measurement Method Based on Stochastic Fluctuation Model | |
| He et al. | Validating and calibrating a destination estimation algorithm for public transport smart card fare collection systems | |
| CN108197081A (en) | A kind of data actuarial model method for building up of flight delay danger | |
| Pasricha | Kalman filter and its economic applications | |
| Morikawa et al. | Preliminary analysis on dynamic route choice behavior: Using probe‐vehicle data | |
| Peng et al. | Demand modeling and forecasting | |
| Heidrich et al. | ProbPNN: Enhancing Deep Probabilistic Forecasting with Statistical Information | |
| Susilawati et al. | Modelling urban travel time variability with the Burr regression technique | |
| Estes et al. | Predicting performance of ground delay programs | |
| Zenkert | No-show forecast using passenger booking data | |
| Lin et al. | Robust model for estimating freeway dynamic origin–destination matrix | |
| CN112797994A (en) | Method and related apparatus and server for determining estimated time of arrival of a route | |
| Hu et al. | Applying svgd to bayesian neural networks for cyclical time-series prediction and inference | |
| Spanninger et al. | Quantifying the dynamic predictability of train delay with uncertainty-aware neural networks | |
| Timofeev et al. | Estimation of loan portfolio risk on the basis of Markov chain model | |
| Yamany et al. | Prediction of pavement performance using non-homogeneous Markov models: Incorporating the impact of preventive maintenance | |
| Yamamoto et al. | Updating dynamic origin-destination matrices using observed link travel speed by probe vehicles | |
| Rezazada et al. | What influences passenger’s arrival rate at stops in Melbourne: Wasea-Lstm, a novel deep learning model leveraging multi-source data fusion | |
| Sundqvist | Developing Markov chain models for train delay evolution in winter climate | |
| AYAR et al. | Long-term traffic flow estimation: a hybrid approach using location-basedtraffic characteristic | |
| Gao et al. | Performance modeling of infrastructure condition data with maintenance intervention | |
| Bhattacharjee et al. | Modeling the effects of traveler information on freeway origin–destination demand prediction | |
| Dunne et al. | Bus journey time prediction: a comparison of whole route and segment journey time predictions using machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190205 |
|
| WD01 | Invention patent application deemed withdrawn after publication |