The Experts below are selected from a list of 177 Experts worldwide ranked by ideXlab platform
Nikolaos Geroliminis - One of the best experts on this subject based on the ideXlab platform.
-
dynamic clustering and propagation of congestion in heterogeneously congested urban traffic networks
Transportation Research Part B-methodological, 2017Co-Authors: Mohammadreza Saeedmanesh, Nikolaos GeroliminisAbstract:The problem of clustering in urban traffic networks has been mainly studied in static framework by considering traffic conditions at a given time. Nevertheless, it is important to underline that traffic is a strongly time-variant process and it needs to be studied in the spatiotemporal dimension. Investigating the clustering problem over time in the dynamic domain is critical to better understand and reveal the hidden information during the process of congestion formation and dissolution. The primary motivation of the paper is to study the spatiotemporal relation of congested links, observing congestion propagation from a Macroscopic Perspective, and finally identifying critical pockets of congestion that can aid the design of peripheral control strategies. To achieve this, we first introduce a static clustering method to partition the heterogeneous network into homogeneous connected sub-regions. The proposed framework guarantees connectivity of the cluster in different steps, which eases the development of a dynamic framework. The proposed clustering approach has 3 steps; firstly, it obtains a set of homogeneous connected components in the network. Each component has a form of sequence which is built by sequentially adding neighboring links with similar level of congestion. Secondly, the major skeleton of clusters is obtained out of this feasible set by minimizing a heterogeneity index. Thirdly, a fine-tuning step is designed to complete the clustering task by assigning the unclustered links of the network to proper clusters while keeping the connectivity. The optimization problem in both second and third step is formulated as a mixed integer linear programming. The approach is also extended to capture spatiotemporal growth and formation of congestion. The dynamic clustering is based on an iterative and fast procedure that considers the spatiotemporal characteristics of congestion propagation and identifies the links with the highest degree of heterogeneity due to time dependent conditions and finally re-cluster them to guarantee connectivity and minimize heterogeneity. An implementation of the developed methodologies in a megacity based on more than 20,000 taxis with GPS highlights the quality of the method due to its fast computation and proper integration of physical properties of congestion.
-
empirical observations of congestion propagation and dynamic partitioning with probe data for large scale systems
Transportation Research Record, 2014Co-Authors: Jun Luo, Nikolaos GeroliminisAbstract:Research on congestion propagation in large urban networks has been based mainly on microsimulations of link-level traffic dynamics. However, both the unpredictability of travel behavior and the complexity of accurate physical modeling present challenges, and simulation results may be time-consuming and unrealistic. This paper explores empirical data from large-scale urban networks to identify hidden information in the process of congestion formation. Specifically, the spatiotemporal relation of congested links is studied, congestion propagation is observed from a Macroscopic Perspective, and critical congestion regimes are identified to aid in the design of peripheral control strategies. To achieve these goals, the maximum connected component of congested links is used to capture congestion propagation in the city. A data set of 20,000 taxis with global positioning system (GPS) data from Shenzhen, China, is used. Empirical Macroscopic fundamental diagrams of congested regions observed during propagation are presented, and the critical congestion regimes are quantified. The findings show that the proposed methodology can effectively distinguish congestion pockets from the rest of the network and efficiently track congestion evolution in linear time O(n).
Mena-yedra Rafael - One of the best experts on this subject based on the ideXlab platform.
-
An adaptive, fault-tolerant system for road network traffic prediction using machine learning
Universitat Politècnica de Catalunya, 2020Co-Authors: Mena-yedra RafaelAbstract:This thesis has addressed the design and development of an integrated system for real-time traffic forecasting based on machine learning methods. Although traffic prediction has been the driving motivation for the thesis development, a great part of the proposed ideas and scientific contributions in this thesis are generic enough to be applied in any other problem where, ideally, their definition is that of the flow of information in a graph-like structure. Such application is of special interest in environments susceptible to changes in the underlying data generation process. Moreover, the modular architecture of the proposed solution facilitates the adoption of small changes to the components that allow it to be adapted to a broader range of problems. On the other hand, certain specific parts of this thesis are strongly tied to the traffic flow theory. The focus in this thesis is on a Macroscopic Perspective of the traffic flow where the individual road traffic flows are correlated to the underlying traffic demand. These short-term forecasts include the road network characterization in terms of the corresponding traffic measurements –traffic flow, density and/or speed–, the traffic state –whether a road is congested or not, and its severity–, and anomalous road conditions –incidents or other non-recurrent events–. The main traffic data used in this thesis is data coming from detectors installed along the road networks. Nevertheless, other kinds of traffic data sources could be equally suitable with the appropriate preprocessing. This thesis has been developed in the context of Aimsun Live –a simulation-based traffic solution for real-time traffic prediction developed by Aimsun–. The methods proposed here is planned to be linked to it in a mutually beneficial relationship where they cooperate and assist each other. An example is when an incident or non-recurrent event is detected with the proposed methods in this thesis, then the simulation-based forecasting module can simulate different strategies to measure their impact. Part of this thesis has been also developed in the context of the EU research project "SETA" (H2020-ICT-2015). The main motivation that has guided the development of this thesis is enhancing those weak points and limitations previously identified in Aimsun Live, and whose research found in literature has not been especially extensive. These include: • Autonomy, both in the preparation and real-time stages. • Adaptation, to gradual or abrupt changes in traffic demand or supply. • Informativeness, about anomalous road conditions. • Forecasting accuracy improved with respect to previous methodology at Aimsun and a typical forecasting baseline. • Robustness, to deal with faulty or missing data in real-time. • Interpretability, adopting modelling choices towards a more transparent reasoning and understanding of the underlying data-driven decisions. • Scalable, using a modular architecture with emphasis on a parallelizable exploitation of large amounts of data. The result of this thesis is an integrated system –Adarules– for real-time forecasting which is able to make the best of the available historical data, while at the same time it also leverages the theoretical unbounded size of data in a continuously streaming scenario. This is achieved through the online learning and change detection features along with the automatic finding and maintenance of patterns in the network graph. In addition to the Adarules system, another result is a probabilistic model that characterizes a set of interpretable latent variables related to the traffic state based on the traffic data provided by the sensors along with optional prior knowledge provided by the traffic expert following a Bayesian approach. On top of this traffic state model, it is built the probabilistic spatiotemporal model that learns the dynamics of the transition of traffic states in the network, and whose objectives include the automatic incident detection.Esta tesis ha abordado el diseño y desarrollo de un sistema integrado para la predicción de tráfico en tiempo real basándose en métodos de aprendizaje automático. Aunque la predicción de tráfico ha sido la motivación que ha guiado el desarrollo de la tesis, gran parte de las ideas y aportaciones científicas propuestas en esta tesis son lo suficientemente genéricas como para ser aplicadas en cualquier otro problema en el que, idealmente, su definición sea la del flujo de información en una estructura de grafo. Esta aplicación es de especial interés en entornos susceptibles a cambios en el proceso de generación de datos. Además, la arquitectura modular facilita la adaptación a una gama más amplia de problemas. Por otra parte, ciertas partes específicas de esta tesis están fuertemente ligadas a la teoría del flujo de tráfico. El enfoque de esta tesis se centra en una perspectiva macroscópica del flujo de tráfico en la que los flujos individuales están ligados a la demanda de tráfico subyacente. Las predicciones a corto plazo incluyen la caracterización de las carreteras en base a las medidas de tráfico -flujo, densidad y/o velocidad-, el estado del tráfico -si la carretera está congestionada o no, y su severidad-, y la detección de condiciones anómalas -incidentes u otros eventos no recurrentes-. Los datos utilizados en esta tesis proceden de detectores instalados a lo largo de las redes de carreteras. No obstante, otros tipos de fuentes de datos podrían ser igualmente empleados con el preprocesamiento apropiado. Esta tesis ha sido desarrollada en el contexto de Aimsun Live -software desarrollado por Aimsun, basado en simulación para la predicción en tiempo real de tráfico-. Los métodos aquí propuestos cooperarán con este. Un ejemplo es cuando se detecta un incidente o un evento no recurrente, entonces pueden simularse diferentes estrategias para medir su impacto. Parte de esta tesis también ha sido desarrollada en el marco del proyecto de la UE "SETA" (H2020-ICT-2015). La principal motivación que ha guiado el desarrollo de esta tesis es mejorar aquellas limitaciones previamente identificadas en Aimsun Live, y cuya investigación encontrada en la literatura no ha sido muy extensa. Estos incluyen: -Autonomía, tanto en la etapa de preparación como en la de tiempo real. -Adaptación, a los cambios graduales o abruptos de la demanda u oferta de tráfico. -Sistema informativo, sobre las condiciones anómalas de la carretera. -Mejora en la precisión de las predicciones con respecto a la metodología anterior de Aimsun y a un método típico usado como referencia. -Robustez, para hacer frente a datos defectuosos o faltantes en tiempo real. -Interpretabilidad, adoptando criterios de modelización hacia un razonamiento más transparente para un humano. -Escalable, utilizando una arquitectura modular con énfasis en una explotación paralela de grandes cantidades de datos. El resultado de esta tesis es un sistema integrado –Adarules- para la predicción en tiempo real que sabe maximizar el provecho de los datos históricos disponibles, mientras que al mismo tiempo también sabe aprovechar el tamaño teórico ilimitado de los datos en un escenario de streaming. Esto se logra a través del aprendizaje en línea y la capacidad de detección de cambios junto con la búsqueda automática y el mantenimiento de los patrones en la estructura de grafo de la red. Además del sistema Adarules, otro resultado de la tesis es un modelo probabilístico que caracteriza un conjunto de variables latentes interpretables relacionadas con el estado del tráfico basado en los datos de sensores junto con el conocimiento previo –opcional- proporcionado por el experto en tráfico utilizando un planteamiento Bayesiano. Sobre este modelo de estados de tráfico se construye el modelo espacio-temporal probabilístico que aprende la dinámica de la transición de estado
-
An adaptive, fault-tolerant system for road network traffic prediction using machine learning
Universitat Politècnica de Catalunya, 2020Co-Authors: Mena-yedra RafaelAbstract:This thesis has addressed the design and development of an integrated system for real-time traffic forecasting based on machine learning methods. Although traffic prediction has been the driving motivation for the thesis development, a great part of the proposed ideas and scientific contributions in this thesis are generic enough to be applied in any other problem where, ideally, their definition is that of the flow of information in a graph-like structure. Such application is of special interest in environments susceptible to changes in the underlying data generation process. Moreover, the modular architecture of the proposed solution facilitates the adoption of small changes to the components that allow it to be adapted to a broader range of problems. On the other hand, certain specific parts of this thesis are strongly tied to the traffic flow theory. The focus in this thesis is on a Macroscopic Perspective of the traffic flow where the individual road traffic flows are correlated to the underlying traffic demand. These short-term forecasts include the road network characterization in terms of the corresponding traffic measurements –traffic flow, density and/or speed–, the traffic state –whether a road is congested or not, and its severity–, and anomalous road conditions –incidents or other non-recurrent events–. The main traffic data used in this thesis is data coming from detectors installed along the road networks. Nevertheless, other kinds of traffic data sources could be equally suitable with the appropriate preprocessing. This thesis has been developed in the context of Aimsun Live –a simulation-based traffic solution for real-time traffic prediction developed by Aimsun–. The methods proposed here is planned to be linked to it in a mutually beneficial relationship where they cooperate and assist each other. An example is when an incident or non-recurrent event is detected with the proposed methods in this thesis, then the simulation-based forecasting module can simulate different strategies to measure their impact. Part of this thesis has been also developed in the context of the EU research project "SETA" (H2020-ICT-2015). The main motivation that has guided the development of this thesis is enhancing those weak points and limitations previously identified in Aimsun Live, and whose research found in literature has not been especially extensive. These include: • Autonomy, both in the preparation and real-time stages. • Adaptation, to gradual or abrupt changes in traffic demand or supply. • Informativeness, about anomalous road conditions. • Forecasting accuracy improved with respect to previous methodology at Aimsun and a typical forecasting baseline. • Robustness, to deal with faulty or missing data in real-time. • Interpretability, adopting modelling choices towards a more transparent reasoning and understanding of the underlying data-driven decisions. • Scalable, using a modular architecture with emphasis on a parallelizable exploitation of large amounts of data. The result of this thesis is an integrated system –Adarules– for real-time forecasting which is able to make the best of the available historical data, while at the same time it also leverages the theoretical unbounded size of data in a continuously streaming scenario. This is achieved through the online learning and change detection features along with the automatic finding and maintenance of patterns in the network graph. In addition to the Adarules system, another result is a probabilistic model that characterizes a set of interpretable latent variables related to the traffic state based on the traffic data provided by the sensors along with optional prior knowledge provided by the traffic expert following a Bayesian approach. On top of this traffic state model, it is built the probabilistic spatiotemporal model that learns the dynamics of the transition of traffic states in the network, and whose objectives include the automatic incident detection.Esta tesis ha abordado el diseño y desarrollo de un sistema integrado para la predicción de tráfico en tiempo real basándose en métodos de aprendizaje automático. Aunque la predicción de tráfico ha sido la motivación que ha guiado el desarrollo de la tesis, gran parte de las ideas y aportaciones científicas propuestas en esta tesis son lo suficientemente genéricas como para ser aplicadas en cualquier otro problema en el que, idealmente, su definición sea la del flujo de información en una estructura de grafo. Esta aplicación es de especial interés en entornos susceptibles a cambios en el proceso de generación de datos. Además, la arquitectura modular facilita la adaptación a una gama más amplia de problemas. Por otra parte, ciertas partes específicas de esta tesis están fuertemente ligadas a la teoría del flujo de tráfico. El enfoque de esta tesis se centra en una perspectiva macroscópica del flujo de tráfico en la que los flujos individuales están ligados a la demanda de tráfico subyacente. Las predicciones a corto plazo incluyen la caracterización de las carreteras en base a las medidas de tráfico -flujo, densidad y/o velocidad-, el estado del tráfico -si la carretera está congestionada o no, y su severidad-, y la detección de condiciones anómalas -incidentes u otros eventos no recurrentes-. Los datos utilizados en esta tesis proceden de detectores instalados a lo largo de las redes de carreteras. No obstante, otros tipos de fuentes de datos podrían ser igualmente empleados con el preprocesamiento apropiado. Esta tesis ha sido desarrollada en el contexto de Aimsun Live -software desarrollado por Aimsun, basado en simulación para la predicción en tiempo real de tráfico-. Los métodos aquí propuestos cooperarán con este. Un ejemplo es cuando se detecta un incidente o un evento no recurrente, entonces pueden simularse diferentes estrategias para medir su impacto. Parte de esta tesis también ha sido desarrollada en el marco del proyecto de la UE "SETA" (H2020-ICT-2015). La principal motivación que ha guiado el desarrollo de esta tesis es mejorar aquellas limitaciones previamente identificadas en Aimsun Live, y cuya investigación encontrada en la literatura no ha sido muy extensa. Estos incluyen: -Autonomía, tanto en la etapa de preparación como en la de tiempo real. -Adaptación, a los cambios graduales o abruptos de la demanda u oferta de tráfico. -Sistema informativo, sobre las condiciones anómalas de la carretera. -Mejora en la precisión de las predicciones con respecto a la metodología anterior de Aimsun y a un método típico usado como referencia. -Robustez, para hacer frente a datos defectuosos o faltantes en tiempo real. -Interpretabilidad, adoptando criterios de modelización hacia un razonamiento más transparente para un humano. -Escalable, utilizando una arquitectura modular con énfasis en una explotación paralela de grandes cantidades de datos. El resultado de esta tesis es un sistema integrado –Adarules- para la predicción en tiempo real que sabe maximizar el provecho de los datos históricos disponibles, mientras que al mismo tiempo también sabe aprovechar el tamaño teórico ilimitado de los datos en un escenario de streaming. Esto se logra a través del aprendizaje en línea y la capacidad de detección de cambios junto con la búsqueda automática y el mantenimiento de los patrones en la estructura de grafo de la red. Además del sistema Adarules, otro resultado de la tesis es un modelo probabilístico que caracteriza un conjunto de variables latentes interpretables relacionadas con el estado del tráfico basado en los datos de sensores junto con el conocimiento previo –opcional- proporcionado por el experto en tráfico utilizando un planteamiento Bayesiano. Sobre este modelo de estados de tráfico se construye el modelo espacio-temporal probabilístico que aprende la dinámica de la transición de estadosPostprint (published version
P.h.a.j.m. Van Gelder - One of the best experts on this subject based on the ideXlab platform.
-
integration of individual encounter information into causation probability modelling of ship collision accidents
Safety Science, 2019Co-Authors: Pengfei Chen, Junmin Mou, P.h.a.j.m. Van GelderAbstract:Abstract Maritime accidents, especially ship collisions, have always been a threat to the safety of maritime transport industry, the regional and global economy, and societies, due to its dire consequences. In this paper, a novel method to model causational factors, one of the critical elements of probabilistic risk modelling of ship collision accidents, is proposed. A credal probabilistic graphical network model based on imprecise probabilities was established based on accident investigation reports and domain experts as the overall framework to represent expert knowledge and probabilistic inference under uncertainty. Causational probability is estimated from the micro-to-Macroscopic Perspective where information of ship encounters are integrated into the causational model to perform probabilistic inference on each encounter and to obtain collective results. The causation probability interval is obtained and compared between model with and without the availability of geometric encounter data. The results indicate that: (1) the encounter information (relative bearing, TCPA, and presence of other ship) has influence on causational probability of ship collision accident to certain extent; human and organisational factors play more significant role; and (2) with AIS data integration, causational probability analysis can be utilized to determine encounters with higher likelihood and obtain details of dangerous ship encounters in regional maritime traffic.
-
probabilistic risk analysis for ship ship collision state of the art
Safety Science, 2019Co-Authors: Pengfei Chen, Yamin Huang, Junmin Mou, P.h.a.j.m. Van GelderAbstract:Abstract Maritime transportation system has made a significant contribution to the development of the world economy. However, with the growth of quantity, scale, and speed of ships, maritime accidents still pose incrementing risk to individuals and societies in terms of multiple aspects, especially collision accidents between ships. Great effort is needed to prevent the occurrence of such accidents and to improve navigational safety and traffic efficiency. In this paper, extensive literature on probabilistic risk analysis on ship-ship collision was collected and reviewed focusing on the stakeholders which may benefit from the research and the methodologies and criteria adopted for collision risk. The paper identifies stakeholders, the modelling aspects (frequency estimation, causation analysis, etc.) in which the stakeholders are interested in. A classification system is presented based on the technical characteristics of the methods, followed by detailed descriptions of representative approaches and discussion. Areas for improvement of such risk analysis approaches are highlighted, i.e. identifying collision candidates, assessing the collision probability of multiple ships encounters, assessing the human and organizational factors. Three findings are concluded from this literature review: (1) Research on collision risk analysis and evaluation of ship encounters from individual ship Perspective have facilitated the research in Macroscopic Perspective, and in turn, results from Macroscopic research can also facilitate individual risk analysis by providing regional risk characteristics; (2) Current approaches usually estimate geometric probability by analysing data at certain intervals, which could lead to over/underestimation of the results; and (3) For causation probability induced by human and organisational factors in collision accidents, lack of data and uncertainty is still a problem to obtain accurate and reliable estimations. The paper also includes a discussion with respect to the applicability of the methods and outlines further work for improvement. The results in this paper are presented in a systematic structure and are formulated in a conclusive manner. This work can potentially contribute to developing better risk models and therefore better maritime transportation systems.
W. Ehlers - One of the best experts on this subject based on the ideXlab platform.
-
Dynamic wave propagation in infinite saturated porous media half spaces
Computational Mechanics, 2012Co-Authors: Y. Heider, B. Markert, W. EhlersAbstract:From a Macroscopic Perspective, saturated porous materials like soils represent volumetrically interacting solid–fluid aggregates. They can be properly modelled using continuum porous media theories accounting for both solid-matrix deformation and pore-fluid flow. The dynamic excitation of such multi-phase materials gives rise to different types of travelling waves, where it is of common interest to adequately describe their propagation through unbounded domains. This poses challenges for the numerical treatment and demands special solution strategies that avoid artificial and numerically-induced perturbations or interferences. The present paper is concerned with the accurate and stable numerical solution of dynamic wave propagation problems in infinite half spaces. Proceeding from an isothermal, biphasic, linear poroelasticity model with incompressible constituents, finite elements are used to discretise the near field and infinite elements to approximate the far field. The transient propagation of the poroacoustic body waves to the infinity is thereby modelled by a viscous damping boundary, which, for stability reasons, necessitates an appropriate treatment of the included velocity-dependent damping forces.
Youngjun Kweon - One of the best experts on this subject based on the ideXlab platform.
-
what affects annual changes in traffic safety a Macroscopic Perspective in virginia
Journal of Safety Research, 2015Co-Authors: Youngjun KweonAbstract:INTRODUCTION: Virginia saw a 20% reduction in traffic fatalities in 2008, an unprecedented annual reduction since 1950, and safety stakeholders in Virginia were intrigued about what caused such large a reduction and more generally what affects traffic safety from a Macroscopic Perspective. METHOD: This study attempted to find factors associated with such a reduction using historical data of Virginia. Specifically, the study related 18 factors to seven traffic safety measures. RESULTS: In terms of annual changes, the study found that typical crash exposures were not generally associated with the seven measures, while two economic indicators (unemployment rate and U.S. Consumer Price Index [CPI]) were strongly associated with most of them. CONCLUSIONS: Annual changes in the CPI and unemployment rate account for about half of the annual changes in total and fatal crash counts, respectively. On average, a 1 point increase in CPI and a 1% increase in the unemployment rate are associated with about 2,500 fewer traffic crashes and about 40 fewer fatal crashes annually in Virginia, respectively. Language: en
-
what affects annual changes in traffic safety measures in virginia a Macroscopic Perspective
Transportation Research Board 90th Annual MeetingTransportation Research Board, 2011Co-Authors: Youngjun KweonAbstract:In 2008, the United States saw a 9.7% reduction in traffic fatalities and a 3.5% reduction in total crashes while Virginia saw a 20% reduction in traffic fatalities. Such recent reductions lead to the question: What caused the reductions or what factors were associated with them? This study attempted to answer this question using historical annual data. Specifically, the study related 18 factors reflecting various aspects potentially relevant to traffic safety to seven traffic safety measures (e.g., the numbers of fatalities and fatal crashes) in terms of annual changes to find factors explaining fluctuations in the safety measures. Annual changes in typical crash exposures (e.g., vehicle miles traveled and population) were not generally associated with annual changes in the safety measures. Annual changes in two economic indicators (Virginia's unemployment rate and the U.S. Consumer Price Index [CPI]) were strongly associated with annual changes in most of the seven measures. Annual changes in the CPI and Virginia's unemployment rate explained about one half of the annual changes in total crash counts and fatal crash counts of Virginia, respectively. Changes in crash counts (e.g., fatal crash) were better explained than changes in victim counts (e.g., fatality) by relevant factors probably because victim counts are influenced by occupancy rates possibly varying over years.
