Improving alighting stop inference accuracy in the trip chaining method using neural networks

Assemi, Behrang; Alsger, Azalden; Moghaddam, Mahboobeh; Hickman, Mark; Mesbah, Mahmoud

doi:10.1007/s12469-019-00218-9

Cited by 22 publications

(11 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, a study estimated alighting stops by applying a three-dimensional latent Dirichlet allocation model [21], and another study analyzed major trip origins, destinations, and transfer locations by spatially clustering the locations of the stops and estimated alighting stops [20]. On the other hand, some studies estimated alighting stops by training models based on various parameters of trips [23][24][25].…”

Section: Methodology For Estimating Destination Based On Patternmentioning

confidence: 99%

Estimating Destination of Bus Trips Considering Trip Type Characteristics

Lee¹,

Lee²,

Bae³

et al. 2021

Preprint

View full text Add to dashboard Cite

In recent years, local governments have been using transportation card data to monitor the use of public transport and improve the service. However, local governments that are applying a single-fare scheme are experiencing difficulties in using data for accurate identification of real travel patterns, policy decision support, etc. because the information on alighting stops of users is missing. This policy limits its functionality of utilizing data such as accurate identification of real travel patterns, policy decision support, etc. Various studies to overcome this limitation have been conducted in South Korea and other countries to develop es-timation methodologies of alighting stops. Even existing studies introduce an advanced method, we found the margin for better accuracy by combining various estimation methodologies for estimating alighting stops. This study reviewed previously conducted studies to classify data with missing alighting stop information into trip types and then applied an appropriate alighting stop estimation methodology for the characteristics of each trip type by stage. The proposed method is evaluated by utilizing transportation card data of the Seoul metropolitan area and checked the accuracy for each standard of allowable error for sensitivity analysis. Furthermore, the number of trips, accuracy, and valid tag rate were checked for each type to examine the need for classifying the trip types. Finally, our evaluation also examines the impact of classifying trip types on estimation accuracy. The evaluation criteria are accuracy of the number of trips and valid tag rate. The analysis shows that the stage-by-stage estimation methodology based on the trip type proposed in this study can es-timate users’ destinations more accurately than previous studies. Furthermore, based on the construction of nearly 100% valid tag data, this study differs from prior studies.

show abstract

Section: Methodology For Estimating Destination Based On Patternmentioning

confidence: 99%

Estimating Destination of Bus Trips Considering Trip Type Characteristics

Lee¹,

Lee²,

Bae³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Moreover, a study estimated alighting stops by applying a three-dimensional latent Dirichlet allocation model [21], and another study analyzed major trip origins, destinations, and transfer locations by spatially clustering the locations of the stops and estimated alighting stops [20]. Other studies estimated alighting stops by developing machine learning models and deep learning models [22][23][24][25].…”

Section: Methodology For Estimating Destination Based On Pattern Using Historical Datamentioning

confidence: 99%

“…In particular, in order to implement MaaS (Mobility as a Service) through connection with parking and bike sharing systems, it is essential to estimate accurate alighting stops for public transportation. Within 400 m from actual destination [24] Note: The accuracy of trip destination inference refers to the percentage of trips where the inferred destination matches the actual destination.…”

Section: Implicationmentioning

confidence: 99%

Estimating Destination of Bus Trips Considering Trip Type Characteristics

Lee

Bae

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Recently, local governments have been using transportation card data to monitor the use of public transport and improve the service. However, local governments that are applying a single-fare scheme are experiencing difficulties in using data for accurate identification of real travel patterns or policy decision support due to missing information on alighting stops of users. This policy limits its functionality of utilizing data such as accurate identification of real travel patterns, policy decision support, etc. In order to overcome these limitations, various methods for estimating alighting stops have been developed. This study classifies trips with missing alighting stop information into trip four types and then applies appropriate alighting stop estimation methodology for each trip type in stages. The proposed method is evaluated by utilizing transportation card data of the Seoul metropolitan area and checking the accuracy for each standard of allowable error for sensitivity analysis. The analysis shows that the stage-by-stage estimation methodology based on the trip type proposed in this study can estimate users’ destinations more accurately than the methodologies of previous studies. Furthermore, based on the construction of nearly 100% valid tag data, this study differs from prior studies.

show abstract

“…The assessment of candidate alighting stops depends on a suitable distance equation. For our problem, the haversine distance is used, since it expresses more accurately the walking distance and is widely used in recent studies [8,40]. The candidate stop θ that minimises transfer distance, along a given route, is chosen.…”

Section: Alighting Estimation Of a Stage Tripmentioning

confidence: 99%

Inference of dynamic origin–destination matrices with trip and transfer status from individual smart card data

Cerqueira

Arsénio

Henriques

2022

Eur. Transp. Res. Rev.

View full text Add to dashboard Cite

Background The provision of seamless public transport supply requires a complete understanding of the real traffic dynamics, comprising origin-to-destination multimodal mobility patterns along the transport network. However, most current solutions are centred on the volumetric analysis of passengers’ flows, generally neglecting transfer, walking, and waiting needs, as well as the changes in the mobility patterns with the calendar and user profile. These challenges prevent a comprehensive assessment of the routing and scheduling vulnerabilities of (multimodal) public transport networks. Research aims/questions The research presented in this paper aims at addressing the above challenges by proposing a novel approach that extends dynamic Origin-Destination (OD) matrix inference to dynamic OD matrix inference with aggregated statistics, highlighting vulnerabilities and multimodal mobility patterns from individual trip record data. Methodology Given specific spatial and temporal criteria, the proposed methodology extends dynamic Origin-Destination (OD) matrices with aggregated statistics, using smart-card validations gathered from (multimodal) public transport networks. More specifically, three major contributions are tackled; i) the data enrichment in the OD matrices with statistical information besides trip volume (e.g., transfer and trip features); ii) the detection of vulnerabilities on the network pertaining to walking distances and trip durations in a user-centric way and iii) the decomposition of traffic flows in accordance with calendrical rules and user (passenger) profiles. The set of contributions are validated on the bus-and-metro public transport network in the city of Lisbon. Results The proposed approach for inferring OD matrices yields four unique contributions. First, we allow inference to consider multimodal commuting patterns, detecting individual trips undertaken along with different operators. Second, we support dynamic matrices’ OD inference along with parameterizable time intervals and calendrical rules, and further support the decomposition of traffic flows according to the user profile. Third, we allow parameterization of the desirable spatial granularity and visualisation preferences. Fourth, our solution efficiently computes several statistics that support OD matrix analysis, helping with the detection of vulnerabilities throughout the transport network. More specifically, statistical indicators related to travellers’ functional mobility needs (commuters for working purposes, etc.), walking distances and trip durations are supported. The inferred dynamic OD matrices are the outcome of a developed software with strict guarantees of usability. Results from the case study using data gathered from the two main public transport operators (Bus and Metro) in the city of Lisbon show that 77.3% of alighting stops can be estimated with a high confidence degree from bus smart-card data. The inferred OD matrices (Bus and Metro) in the city of Lisbon reveal vulnerabilities along specific OD pairs, offering the bus public operators in Lisbon new knowledge and a means to better understand dynamics and validate OD assumptions.

show abstract

Improving alighting stop inference accuracy in the trip chaining method using neural networks

Cited by 22 publications

References 21 publications

Estimating Destination of Bus Trips Considering Trip Type Characteristics

Estimating Destination of Bus Trips Considering Trip Type Characteristics

Estimating Destination of Bus Trips Considering Trip Type Characteristics

Inference of dynamic origin–destination matrices with trip and transfer status from individual smart card data

Contact Info

Product

Resources

About