Posts tagged Big Data
Supervised learning: Predicting passenger load in public transport
For many Public Transport (PT) users, overcrowding in PT vehicles has a major decreasing effect on the comfort experience. However, most online routing applications still not take comfort regarding to crowdedness into account, but provide recommendations based on shortest distance, shortest travel-time, or number of interchanges.
Being able to include certain information on crowdedness, requires knowledge about the current and future level of passenger load. Increasing amount and complexity of data describing public transport services allows us to better explore the detection methods and analysis of different phenomena of PT operations. Some countries or operators provide the possibility to use Smart Card (SC) data for occupancy prediction. However, SC data is not available in real time, which makes it hard to incorporate it into real time recommendation models. In this work, we show that it is possible to predict the passenger load via supervised learning, eliminating the need for fare collection data beyond the set needed for training.
Find the CASPT presentation by Léonie Heydenrijk-Ottens HERE
Assessing disruption management strategies in rail-bound urban public transport from a passenger perspective
This paper provides a framework for generating and assessing alternatives
in case of disruptions in rail-bound urban public transport systems,. The proposed
framework considers the passenger perspective as well as the operator perspective,
for the often-used measures of detouring and short-turning. An application of the
framework demonstrates that currently used disruption management protocols often
do not lead to the optimal solution from the passenger perspective. Furthermore, the
optimal choice between alternatives from passenger perspective shows to be
dependent on the passenger flows.
Assessing and improving operational strategies for the benefit of passengers in rail-bound urban transport systems
Unplanned disruptions in transit can have consequent impacts on passengers. The more inconvenienced passengers are, the more likely operators will be negatively impacted. Yet so far, operators and researchers have addressed the rescheduling problem during disruptions mainly with a supply-side focus – timetable, crews and vehicles – and not with a passenger perspective. Urban rail transit particularly lacks insights in terms of passenger- focused rescheduling. Being able to assess the inconvenience experienced by passengers during disruptions compared with what they normally experience, and being able to compare how different rescheduling strategies affect them are therefore two major challenges.
The framework developed in this study precisely aims at tackling 8 these challenges. A case study of the metro of Rotterdam is used to test the framework developed in this paper. Alternative strategies are developed focusing on the incident phase (from the beginning of the incident until its cause is resolved). The application of the framework reveals that a regularity-focused rescheduling strategy would be beneficial for high-frequency service users. Realistically, yearly savings could amount to around €900,000 in terms of societal passenger costs for the operator in the Rotterdam area alone. However, the omnipresence of the punctuality paradigm, through which most operators plan and analyze operations, makes the implementation of passenger-focused strategies a challenging task for traffic controllers. The results of the study are valuable for transit operators worldwide and the framework can provide insights to decision-makers on the performance of different strategies, bringing to light trade-offs between supply and passenger sides during disruptions.
Read more of this research by Anne Durand: Paper TRB and Poster TRB
Nieuwe lessen over de potentie van Fiets en OV
Het combineren van fiets en openbaar vervoer is een duurzame oplossing voor de (mobiliteits)uitdagingen in zowel stedelijke gebieden als daarbuiten. Er is een revival van de fiets gaande en ook hoogwaardig openbaar vervoer rukt op. De keten van fiets mét openbaar vervoer combineert de voordelen van beide systemen: De fiets zorgt voor fijnmazige ontsluitingen van herkomst en bestemmingen, is milieuvriendelijk en stimuleert een gezonde leefstijl. Voor wat betreft OV neemt de kwaliteit de laatste jaren sterk toe door de introductie van hoogwaardig OV (HOV): snelle, frequente en betrouwbare bus- tram- en metrolijnen met een hoog comfortniveau. Voorbeelden zijn R-Net, Randstadrail en Q-Link. De halteafstanden van deze systemen zijn relatief hoog, waardoor de fiets een belangrijke rol speelt in de gebiedsontsluiting.
Om het succes van de fiets en OV verder uit te bouwen is kennis nodig over hoe de mobilist zich nu en in de toekomst beweegt: Wat zijn de succesfactoren, welke voorwaarden spelen een rol en waarom worden bepaalde keuzes gemaakt, bijvoorbeeld. Dit paper laat de resultaten zien van vier TU Delft onderzoeken op dit gebied. Belangrijkste, nieuwe inzichten zijn bijvoorbeeld dat het invloedsgebied van HOV haltes tot 4x groter is ten opzichte van “gewoon’’ OV. Verder blijkt dat treinreizigers bereid zijn ca. 6 min. extra te fietsen naar een station waar ze een directe trein kunnen nemen naar hun bestemming (in plaats van met een overstap). Tot slot blijkt dat de huidige groep fiets-OV’ers in te delen is in 7 groepen, waarvan de middle-aged male professionals de grootste zijn en de gepensioneerden de kleinste. De resultaten zijn de basis voor verder onderzoek en toepassing om te komen tot een optimaal Fiets-OV netwerk.
Lees het hele CVS paper HIER
De presentatie is HIER beschikbaar
Opportunities for the Combined Bicycle and Transit Mode
Around the world cities face negative effects generated by increasing mobility needs. To tackle these issues, mobility should be environmental and spatial friendly. Combining bicycle and public transport into a ‘bicycle + transit mode’ will create a synergy with the best of both worlds: superb door-to-door accessibility offered by the bicycle and a large spatial reach from transit modes. These complemented modes combined easily challenge private carsin terms of speed as well accessibility.
Research regarding the users and trip types of the bicycle and transit mode is largely missing. This is unfortunate, since understanding both user and trip characteristics is of the utmost importance to improve the share of the bicycle and transit mode. Policy-makers can make concrete decisions on infrastructure and service investments only when the gap between the aforementioned societal need and scientific knowledge is filled.
The main analysis in the study is based on data from the Netherlands. The Netherlands is one of the countries with a head start regarding the use of the bicycle + transit mode. A one-day trip diary survey, representative of the population of the Netherlands, with more than 250,000 respondents who made nearly 700,000 trips over the course of 6 years (2010-2015), is used to derive important trip and user characteristics of the bicycle + transit mode. Finally, latent class cluster analysis is applied to find prototypical users of this mode on the basis of their socio-demographic attributes.
It is, for example, found that the most important purposes of the bicycle and transit mode are work or education, typically involving relatively long distances. Bicycle and transit-potential for other transit network levels, such as metros and bus rapid transit can be found. Moreover, seven unique user groups – from middle-aged professionals to school children – are identified, and their different travel behaviour is discussed.
Data-driven transfer inference for public transport journeys during disruptions
Disruptions in public transport have major impact on passengers and disproportional effects on passenger satisfaction. The availability of smart card data gives opportunities to better quantify disruption impacts on passengers’ experienced journey travel time and comfort. For this, accurate journey inference from raw transaction data is required. Several rule-based algorithms exist to infer whether a passenger alighting and subsequent boarding is categorized as transfer or final destination where an activity is performed. Although this logic can infer transfers during undisrupted public transport operations, these algorithms have limitations during disruptions: disruptions and subsequent operational rescheduling measures can force passengers to travel via routes which would be non-optimal or illogical during undisrupted operations. Therefore, applying existing algorithms can lead to biased journey inference and biased disruption impact quantification. We develop and apply a new transfer inference algorithm which infers journeys from raw smart card transactions in an accurate way during both disrupted and undisrupted operations. In this algorithm we incorporate the effects of denied boarding, transferring to a vehicle of the same line (due to operator rescheduling measures as short-turning), and the use of public transport services of another operator on another network level as intermediate journey stage during disruptions. This results in an algorithm with an improved transfer inference performance compared to existing algorithms.
Find the paper HERE
Understanding the trip and user characteristics of the combined bicycle and transit mode
Several cities around the world are facing mobility related problems such as traffic congestion and air pollution. Although limited individually, the combination of bicycle and transit offers speed and accessibility; by complementing each other’s characteristics the bicycle and transit combination can compete with automobiles. Recognising this, several studies have investigated policies that encourage integration of these modes. However, empirical analysis of the actual users and trips of the combined mode is largely missing. This study addresses this gap by (i) reviewing empirical findings on related modes, (ii) deriving user and trip characteristics of the bicycle and transit mode in the Netherlands, and (iii) applying latent class cluster analysis to discover prototypical users based on their socio-demographic attributes. Most trips by this mode are found to be for relatively long commutes where transit is in the form of trains, and bicycle and walking are access and egress modes respectively. Furthermore, seven user groups are identified and their spatial and temporal travel behaviour is discussed. Transport authorities may use the empirical results in this study to further streamline integration of bicycle and transit for its largest users as well as to tailor policies to attract more travellers.
Find our Thredbo conference presentation HERE
Read our paper HERE
Modelling Multimodal Transit Networks: Integration of bus networks with walking and cycling
Demand for (public) transportation is subject to dynamics affected by technological, spatial, societal and demographic aspects. The political environment, together with financial and spatial constraints limit the possibilities to address transit issues arising from growing demand through the construction of new infrastructure. Upgrading of existing services and improving integration over the entire trip chain (including cycling) are two options that can address these transport issues. However, transport planners and transport service operators often fail to include the entire trip when improving services, as improvement is normally achieved through the adaptations of characteristics (e.g. speeds, stop distances) of the services.
Our developed framework consists of two parts: one to assess the characteristics of the different bus services and their access and egress modes, and one to assess the effects of integration of these services, which includes the modelling and analysis in a regional transit model. The framework has successfully been applied to a case study showing that bus systems with higher frequencies and speeds can attract twice the amount of cyclists on the access and egress sides. It also shows that passengers accept longer access and egress distances with more positive characteristics of the bus service (higher speeds, higher frequencies).
Find the presentation of Judith Brand at MT-ITS in Napoli HERE
Find our paper HERE
A data-driven approach to infer spatial characteristics and service reliability of public transport hubs
Public transport hubs play an important and a central role in public transport networks by connecting several public transport lines from one or multiple network levels. Hubs can be characterized by a large relative and absolute number of transferring passengers between public transport services within the same network level and/or between different network levels. Hubs are especially important with respect to service reliability of passenger journeys, since missing connections at hubs can substantially increase the nominal and perceived passenger journey travel time. The availability of AFC and AVL data allows an in-depth analysis of hub definition, identification, characterization and reliability performance evaluation. Such analysis enables optimisation of synchronisation of schedules, thereby increase the level of service reliability.
Find our TransitData2017 presentation HERE
Insights into door-to-door travel patterns of public transport passengers
Public transport enables fast and reliable station to station journeys. To assess passenger travel patterns and to infer actual quality of service, smartcard and AVL data offer great opportunities. There is, however, an increasing interest in insights into access and egress dynamics of public transport riders as well. What is the size of a stop’s catchment area, which modes are used, and how long and reliable are access and egress times? The answers to these and other questions enable optimization of the total mobility system, thereby also increasing public transport ridership and efficiency. Sufficient biking access of public transport stops (routes and parking), for instance, offer opportunities to increase public transport stopping distances, thereby increasing operational speed and reliability, without compromising accessibility of service areas. We developed a methodology to calculate and demonstrate these dynamics by using new and existing data technologies, namely AVL, survey and new promising app.
Find the Transit Data Conference abstract HERE and our presentation HERE