Understanding daily mobility patterns in urban road networks using traffic flow analytics

Laña, Ibai; Ser, Javier Del; Olabarrieta, Ignacio

doi:10.1109/noms.2016.7502980

Cited by 25 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A closer look at this pattern is provided in Figure 4 for the traffic captured in the RS-EA location. This traffic characterization is usual in the literature related to traffic modeling [53,54] and temporal features were found to have a decisive relevance in long-term traffic forecasting [55]. Based on this rationale, temporal features are subsequently incorporated to the dataset in order to improve the performance of the regression techniques, as previously explained in Section 2.5.…”

Section: Traffic Characteristics In Selected Zonesmentioning

confidence: 99%

The role of local urban traffic and meteorological conditions in air pollution: A data-based case study in Madrid, Spain

Laña

Ser

Padró

et al. 2016

Atmospheric Environment

Self Cite

View full text Add to dashboard Cite

Urban air pollution is a matter of growing concern for both public administrations and citizens. Road traffic is one of the main sources of air pollutants, though topography characteristics and meteorological conditions can make pollution levels increase or diminish dramatically. In this context an upsurge of research has been conducted towards functionally linking variables of such domains to measured pollution data, with studies dealing with up to one-hour resolution meteorological data. However, the majority of such reported contributions do not deal with traffic data or, at most, simulate traffic conditions jointly with the consideration of different topographical features. The aim of this study is to further explore this relationship by using highresolution real traffic data. This paper describes a methodology based on the construction of regression models to predict levels of different pollutants (i.e. CO, NO, NO 2 , O 3 and PM 10 ) based on traffic data and meteorological conditions, from which an estimation of the predictive relevance (importance) of each utilized feature can be estimated by virtue of their particular training procedure. The study was made with one hour resolution meteorological,

show abstract

Section: Traffic Characteristics In Selected Zonesmentioning

confidence: 99%

The role of local urban traffic and meteorological conditions in air pollution: A data-based case study in Madrid, Spain

Laña

Ser

Padró

et al. 2016

Atmospheric Environment

Self Cite

View full text Add to dashboard Cite

show abstract

“…In previous research [13,37], we have successfully performed traffic pattern discovery and classification with different purposes. The initial processing phase of our proposed model builds upon these previous works, introducing further changes that allow for a fast online classification and improvements in the modeling of a dataset with features not based in traffic data.…”

Section: Offline Processing: Clustering Traffic Data and Building A Cmentioning

confidence: 99%

“…Predictions obtained in the offline phase, with the discovery of patterns and assignment of new days to them are assumed to be representative of the diversity of traffic profiles in the data of the loop under study to the moment a prediction is queried. After the pattern clustering and classification procedure is executed, most future days will be classified accurately and the assigned traffic profile will match the actual one within a certain tolerance [13]. However, there are circumstances for which this condition is not satisfied.…”

Section: Online Processing: Classification and Adaptation To Changementioning

confidence: 99%

See 1 more Smart Citation

Adaptive long-term traffic state estimation with evolving spiking neural networks

Laña

Lobo

Capecci

et al. 2019

Transportation Research Part C: Emerging Technologies

Self Cite

View full text Add to dashboard Cite

Road traffic management is a critical aspect for the design and planning of complex urban transport networks for which vehicle flow forecasting is an essential component. Due to the nature of traffic itself, specially in urban contexts, most predictive models reported in literature aim for short-term forecasts, and their performance degrades when the prediction horizon is increased. Long term forecasting strategies are more scarce, and commonly based on the detection and assignment to patterns. These approaches can perform reasonably well unless an unexpected event provokes non predictable changes, or if the allocation to a pattern is inaccurate. This work introduces a method to obtain long-term pattern forecasts and adapt them to real-time circumstances. The method takes advantage of the architecture of evolving Spiking Neural Networks (eSNN) to perform online adaptations without retraining the model. Its performance is assessed over a real scenario with 5 minute data of a 6 month span of traffic in the centre of Madrid (Spain). Significant accuracy gains are obtained when applying the proposed online adaptation mechanism on days with special, non-predictable events that degrade the quality of their long-term traffic forecasts.

show abstract

“…3. Гибридные методы, сочетающие параметрические и непараметрические методы [22,23], например, комбинация модели ARIMA с другими моделями для повышения точности прогноза [24], объединение статистических методов и моделей нейронных сетей [25], а также комбинация моделей прогнозирования с методами предобработки данных [26,27].…”

Section: обзор литературы краткосрочное прогнозирование трафикаunclassified

Big data analysis in a geoinformatic problem of short-term traffic flow forecasting based on a k nearest neighbors method

Agafonov¹,

Yumaganov²,

Myasnikov³

2018

Computer Optics

View full text Add to dashboard Cite

Аннотация Точная и своевременная информация о текущем и прогнозном распределении транспортных потоков является важным фактором функционирования интеллектуальных транспортных систем. Использование этих данных позволит транспортным агентствам эффективнее решать задачу управления трафиком, участникам дорожного движения точнее планировать маршрут поездки и снизить время движения, и в целом повысит эффективность использования транспортной инфраструктуры. В данной статье представлена модель краткосрочного прогнозирования трафика, основанная на методе k ближайших соседей, которая учитывает пространственное и временное распределение транспортных потоков. Разработанная модель реализована с помощью фреймворка Apache Spark на основе модели распределённых вычислений MapReduce. Экспериментальные исследования представленной модели по данным о распределении транспортных потоков в транспортной сети города Самары позволяет сделать вывод, что предлагаемая модель обладает высокой точностью прогнозирования и временем работы, достаточным для прогнозирования в режиме реального времени. Ключевые слова: транспортный поток, краткосрочное прогнозирование, k ближайших соседей, MapReduce. Цитирование: Агафонов, А.А. Анализ больших данных в геоинформационной задаче краткосрочного прогнозирования параметров транспортного потока на базе метода k ближайших соседей / А.А.

show abstract

Understanding daily mobility patterns in urban road networks using traffic flow analytics

Cited by 25 publications

References 16 publications

The role of local urban traffic and meteorological conditions in air pollution: A data-based case study in Madrid, Spain

The role of local urban traffic and meteorological conditions in air pollution: A data-based case study in Madrid, Spain

Adaptive long-term traffic state estimation with evolving spiking neural networks

Big data analysis in a geoinformatic problem of short-term traffic flow forecasting based on a k nearest neighbors method

Contact Info

Product

Resources

About