In road-based mass transit systems, travel time is a key factor in providing quality of service. This article proposes a method of predicting travel time for this type of transport system. This method estimates travel time by taking into account its historical behaviour, represented by historical profiles, and the current behaviour recorded on the public transport vehicle for which the prediction is to be made. The model uses the k-medoids clustering algorithm to obtain historical travel time profiles. A relevant feature of the model is that it does not require recent travel time data from other vehicles. For this reason, the proposed model may be used in intercity transport contexts in which service planning is carried out according to timetables. The proposed model has been tested with two real cases of intercity public transport routes and from the results obtained we may conclude that, in general, the average error of the predictions is around 13% compared to the observed travel time values.

This paper presents an architecture model for the development of intelligent systems for public passenger transport by road. The main objective of our proposal is to provide a framework for the systematic development and deployment of telematics systems to improve various aspects of this type of transport, such as efficiency, accessibility and safety. The architecture model presented herein is based on international standards on intelligent transport system architectures, ubiquitous computing and service-oriented architecture for distributed systems. To illustrate the utility of the model, we also present a use case of a monitoring system for stops on a public passenger road transport network.

Quality is an essential aspect of public transport. In the case of regular public passenger transport by road, punctuality and regularity are criteria used to assess quality of service. Calculating metrics related to these criteria continuously over time and comprehensively across the entire transport network requires the handling of large amounts of data. This article describes a system for continuously and comprehensively monitoring punctuality and regularity. The system uses location data acquired continuously in the vehicles and automatically transferred for analysis. These data are processed intelligently by elements that are commonly used by transport operators: GPS-based tracking system, onboard computer and wireless networks for mobile data communications. The system was tested on a transport company, for which we measured the punctuality of one of the routes that it operates; the results are presented in this article.

The development of efficient mass transit systems that provide quality of service is a major challenge for modern societies. To meet this challenge, it is essential to understand user demand. This article proposes using new time-dependent attributes to represent demand, attributes that differ from those that have traditionally been used in the design and planning of this type of transit system. Data mining was used to obtain these new attributes; they were created using clustering techniques, and their quality evaluated with the Shannon entropy function and with neural networks. The methodology was implemented on an intercity public transport company and the results demonstrate that the attributes obtained offer a more precise understanding of demand and enable predictions to be made with acceptable precision.

Travel Time plays a key role in the quality of service in road-based mass transit systems. In this type of mass transit systems, travel time of a public transport line is the sum of the dwell time at each bus stop and the nonstop running time between pair of consecutives bus stops of the line. The aim of the methodology presented in this paper is to obtain the behavior patterns of these times. Knowing these patterns, it would be possible to reduce travel time or its variability to make more reliable travel time predictions. To achieve this goal, the methodology uses data related to check-in and check-out movements of the passengers and vehicles GPS positions, processing this data by Data Mining techniques. To illustrate the validity of the proposal, the results obtained in a case of use in presented.

In road-based mass transit systems, the travel time is a key factor affecting quality of service. For this reason, to know the behavior of this time is a relevant challenge. Clustering methods are interesting tools for knowledge modeling because these are unsupervised techniques, allowing hidden behavior patterns in large data sets to be found. In this contribution, a study on the utility of different clustering techniques to obtain behavior pattern of travel time is presented. The study analyzed three clustering techniques: K-medoid, Diana, and Hclust, studying how two key factors of these techniques (distance metric and clusters number) affect the results obtained. The study was conducted using transport activity data provided by a public transport operator.