In this paper, we investigate the day-to-day regularity of urban congestion patterns. We first partition link speed data every 10 min into 3D clusters that propose a parsimonious sketch of the congestion pulse. We then gather days with similar patterns and use consensus clustering methods to produce a unique global pattern that fits multiple days, uncovering the day-to-day regularity. We show that the network of Amsterdam over 35 days can be synthesized into only 4 consensual 3D speed maps with 9 clusters. This paves the way for a cutting-edge systematic method for travel time predictions in cities. By matching the current observation to historical consensual 3D speed maps, we design an efficient real-time method that successfully predicts 84% trips travel times with an error margin below 25%. The new concept of consensual 3D speed maps allows us to extract the essence out of large amounts of link speed observations and as a result reveals a global and previously mostly hidden picture of traffic dynamics at the whole city scale, which may be more regular and predictable than expected.

/pdf/revealing-the-day-to-day-regularity-of-urban-congestion-3vjrt3nh5t.pdf

Revealing the day-to-day regularity of urban congestion patterns with 3D speed maps.

Vehicular communications, referring to information exchange among vehicles, infrastructures, etc., have attracted a lot of attention recently due to great potential to support intelligent transportation, various safety applications, and on-road infotainment. In this paper, we provide a comprehensive overview of a recent research on enabling efficient and reliable vehicular communications from the network layer perspective. First, we introduce general applications and unique characteristics of vehicular communication networks and the corresponding classifications. Based on different driving patterns, we categorize vehicular networks into manual driving vehicular networks and automated driving vehicular networks, and then discuss the available communication techniques, network structures, routing protocols, and handoff strategies applied in these vehicular networks. Finally, we identify the challenges confronted by the current vehicular networks and present the corresponding research opportunities.

https://ieeexplore.ieee.org/ielaam/25/8640274/8354811-aam.pdf

Vehicular Communications: A Network Layer Perspective

Smart card data gathered by automated fare collection (AFC) systems are valuable resources for studying urban mobility. In this paper, we propose two approaches to cluster smart card data, which can be used to extract mobility patterns in a public transportation system. Two complementary standpoints are considered: a station-oriented operational point of view and a passenger-focused one. The first approach clusters stations based on when their activity occurs, i.e., how trips made at the stations are distributed over time. The second approach makes it possible to identify groups of passengers that have similar boarding times aggregated into weekly profiles. By applying our approaches to a real data set issued from the metropolitan area of Rennes, France, we illustrate how they can help reveal valuable insights about urban mobility, such as the presence of different station key roles, including residential stations used mostly in the mornings and work stations used only in the evening and almost exclusively during weekdays, as well as different passenger behaviors ranging from the sporadic and diffuse usage to typical commute practices. By cross comparing passenger clusters with fare types, we also highlight how certain usages are more specific to particular types of passengers.

Clustering Smart Card Data for Urban Mobility Analysis

Intelligent transportation systems (ITSs) gather information about traffic conditions by collecting data from a wide range of on-ground sensors. The collected data usually suffer from irregular spatial and temporal resolution. Consequently, missing data is a common problem faced by ITSs. In this paper, we consider the problem of missing data in large and diverse road networks. We propose various matrix and tensor based methods to estimate these missing values by extracting common traffic patterns in large road networks. To obtain these traffic patterns in the presence of missing data, we apply fixed-point continuation with approximate singular value decomposition, canonical polyadic decomposition, least squares, and variational Bayesian principal component analysis. For analysis, we consider different road networks, each of which is composed of around 1500 road segments. We evaluate the performance of these methods in terms of estimation accuracy, variance of the data set, and the bias imparted by these methods.

Matrix and Tensor Based Methods for Missing Data Estimation in Large Traffic Networks

Many cities and countries are now striving to create intelligent transportation systems that utilize the current abundance of multisource and multiform data related to the functionality and the use of transportation infrastructure to better support human mobility, interests, and lifestyles. Such intelligent transportation systems aim to provide novel services that can enable transportation consumers and managers to be better informed and make safer and more efficient use of the infrastructure. However, the transportation domain is characterized by both complex data and complex problems, which calls for visual analytics approaches. The science of visual analytics is continuing to develop principles, methods, and tools to enable synergistic work between humans and computers through interactive visual interfaces. Such interfaces support the unique capabilities of humans (such as the flexible application of prior knowledge and experiences, creative thinking, and insight) and couple these abilities with machines’ computational strengths, enabling the generation of new knowledge from large and complex data. In this paper, we describe recent developments in visual analytics that are related to the study of movement and transportation systems and discuss how visual analytics can enable and improve the intelligent transportation systems of the future. We provide a survey of literature from the visual analytics domain and organize the survey with respect to the different types of transportation data, movement and its relationship to infrastructure and behavior, and modeling and planning. We conclude with lessons learned and future directions, including social transportation, recommender systems, and policy implications.

Visual Analytics of Mobility and Transportation: State of the Art and Further Research Directions

The emergence of new technologies allows better monitoring of traffic conditions and understanding of urban network dynamics. Bluetooth technology is becoming widespread, as it represents a cost-effective means for capturing road traffic in both arterials and motorways. Although the extraction of travel time from Bluetooth data is fairly straightforward, data reliability and processing is still challenging with the issues of penetration rate, mode discrimination, and detection quality. This paper presents a methodological contribution to the use of Bluetooth data for the spatiotemporal analysis of a large urban network (Brisbane, Australia). It introduces the concept of the Bluetooth origin–destination (B-OD) matrix, which is built from a network of 79 Bluetooth detectors located within the Brisbane urban area. The B-OD matrix describes the dynamics of a subpopulation of vehicles, between pairs of detectors. The results show that the characteristics of urban networks can be effectively represented through B-OD matrices. A comparison with loop detector data enables an assessment of the results' significance. Then, the spatiotemporal structure of the network is analyzed with two different clustering analyses, namely, latent Dirichlet allocation (LDA) and $K$ -means. While LDA is used to detect a temporal pattern, the $K$ -means algorithm highlights Bluetooth fundamental diagram (BFD) classes. The results show that Bluetooth data has the potential to be a reliable data source for traffic monitoring. By highlighting hidden structures of a large area, the algorithm outputs allow us to provide the road operators with a fine spatiotemporal analysis of their network, in terms of traffic conditions.

Spatiotemporal Analysis of Bluetooth Data: Application to a Large Urban Network

This paper contributes to traffic state prediction at a network scale. The prediction methodology relies on pattern recognition methods with the adaptation of a k-nearest-neighbors technique. The originality of the contribution is its ability to predict network-wide traffic states as time-dependent maps snapshots, hence keeping all the information and the spatial correlations between links at each time step. This non parametric process is trained and tested on the Brisbane network equipped with 79 bluetooth detectors. Bluetooth data are preprocessed and prepared for the prediction step. The results highlight the performances of the network global approach in terms of prediction error and computational complexity, making it suitable for an application at a large scale.

Network-Wide Traffic State Prediction Using Bluetooth Data

La maturite de la telematique et des technologies de l’information et la communication (TIC), ainsi que l’avenement du big data dans le transport ont conduit a des developpements foisonnants dans le domaine des systemes de transports intelligents (ITS), aussi bien sur le plan des technologies de recueil que du traitement innovant de l’information. Il est desormais possible de connaitre les conditions de circulation et les etats de trafic sur la plupart des sections d’un reseau routier sans avoir recours a des infrastructures intrusives de collecte de donnees, de transmettre l’information resultante via des reseaux sans fil et de traiter rapidement toutes ces donnees multi-sources disponibles. La constitution de grandes bases de donnees a naturellement fait evoluer la pratique de gestion du trafic et plus particulierement les methodes de prevision. Ces methodes ont connu un renouveau en s’inspirant des travaux produits en apprentissage statistique. Neanmoins, la facon d’apprehender le probleme de la prevision est restee a une echelle locale. Pour chaque section de route, un modele de prevision est adapte et optimise. Notre travail de these presente un cadre de prevision du trafic routier qui aborde la question a l’echelle du reseau. L’etude menee au sein de ces travaux de these vise a exposer et evaluer cette nouvelle approche, dite globale, au regard d’approches usuelles, puis a analyser sa sensibilite vis-a-vis de divers facteurs. Apres un positionnement par rapport a l’etat de l’art en theorie du trafic, le cadre predictif fonde sur des methodes de prevision multi-variees par apprentissage est detaille. Une version multidimensionnelle des k plus proches voisins, modele parcimonieux et simple, est evaluee sur divers cas d’etudes. L’originalite reside dans l’exploitation de donnees issues de methodes innovantes de collecte (e.g. Bluetooth, vehicules traceurs, vehicules connectes). Par la suite, les performances de l’approche initiale sont comparees a d’autres methodes d’apprentissage. Un effort particulier est porte sur l’adaptation de methodes a noyaux au cadre predictif global. Les performances obtenues laissent entrevoir une typologie des methodes en fonction des caracteristiques spatiotemporelles du reseau. Afin d’ameliorer les performances en prevision et de reduire les temps de calcul, une methode d’identification et de selection des sections critiques du reseau est proposee. Les resultats prouvent qu’un sous-ensemble restreint de sections est en effet suffisant pour garantir des performances satisfaisantes en generalisation. Enfin, la resilience du cadre predictif est evaluee au regard des evenements non recurrents affectant le fonctionnement nominal du reseau, comme des incidents ou des conditions meteorologiques degradees. Les resultats soulignent l’impact de ces conditions non recurrentes sur la prevision temps-reel de la dynamique court-terme d’un reseau et permettent de dresser une feuille de route pour l’elaboration d’un cadre predictif resilient et operationnel. Cette nouvelle vision de la prevision s’inscrit dans les perspectives actuelles en termes d’applications sur les modules embarques et les objectifs des gestionnaires d’infrastructures.

Contributions à la prévision court-terme, multi-échelle et multi-variée, par apprentissage statistique du trafic routier

Based on a clustering indicator, an alteration of the classical road traffic indicators is proposed for incident detection. The resulting filter method reduces the inaccuracies of comparable detection method and enables to better separate usual traffic patterns from non-recurrent situations. Three alternative detection approaches are considered as baseline comparison for performance estimation.

Pierre-Antoine Laharotte

Papers

Spatiotemporal Analysis of Bluetooth Data: Application to a Large Urban Network

Network-Wide Traffic State Prediction Using Bluetooth Data

Contributions à la prévision court-terme, multi-échelle et multi-variée, par apprentissage statistique du trafic routier

Detection of non-recurrent road traffic events based on clustering indicators

Distributed Signal Control for Multi-Modal Traffic Network: A Deep Reinforcement Learning Approach