Joint Feature Selection and Parameter Tuning for Short-Term Traffic Flow Forecasting Based on Heuristically Optimized Multi-layer Neural Networks

Laña, Ibai; Ser, Javier Del; Vélez, Manuel; Oregi, Izaskun

doi:10.1007/978-981-10-3728-3_10

Cited by 11 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similar to the case of single step literature, TF problems with more than one time horizon in the future are quite welldocumented in the literature [4], [50], [65], [88], [88], [97], [126], [127], [131], [132]. However, in contrast to single time step problems, multiple steps provide a stronger ground for decision makers during traffic flow management [56], [115].…”

Section: Multiplementioning

confidence: 73%

See 1 more Smart Citation

A Taxonomy of Traffic Forecasting Regression Problems From a Supervised Learning Perspective

2019

View full text Add to dashboard Cite

One contemporary policy to deal with traffic congestion is the design and implementation of forecasting methods that allow users to plan ahead of time and decision makers to improve traffic management. Current data availability and growing computational capacities have increased the use of machine learning (ML) to address traffic prediction, which is mostly modeled as a supervised regression problem. Although some studies have presented taxonomies to sort the literature in this field, they are mostly oriented to classify the ML methods applied and a little effort has been directed to categorize the traffic forecasting problems approached by them. As far as we know, there is no comprehensive taxonomy that classifies these problems from the point of view of both traffic and ML. In this paper, we propose a taxonomy to categorize the aforementioned problems from both traffic and a supervised regression learning perspective. The taxonomy aims at unifying and consolidating categorization criteria related to traffic and it introduces new criteria to classify the problems in terms of how they are modeled from a supervised regression approach. The traffic forecasting literature, from 2000 to 2019, is categorized using this taxonomy to illustrate its descriptive power. From this categorization, different remarks are discussed regarding the current gaps and trends in the addressed traffic forecasting area.

show abstract

Section: Multiplementioning

confidence: 73%

“…It does generate, however, issues related to the selection of the proper data-driven method. The overall experience in multi-target modelling points out the use of non-parametric techniques, such as NNs [56], [115], to predict fundamental macroscopic traffic variables together with travel time [5], [102], [128].…”

Section: Multi-targetmentioning

confidence: 99%

A Taxonomy of Traffic Forecasting Regression Problems From a Supervised Learning Perspective

2019

View full text Add to dashboard Cite

show abstract

“…2. Непараметрические методы [2], включая модели искусственных нейронных сетей [14,15], метод k ближайших соседей (kNN) [16,17], метод опорных векторов [18,19], модель байесовской сети [20,21].…”

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

“…In [18], authors proposed an online traffic prediction algorithm that predicts with real time readings leaning on ensembles of weak predictors. In the wide range of machine learning techniques, neural networks and their variations are particularly popular [4,19] for traffic forecasting; however, finding works that make use of the potential of the so-called third generation of neural networks is challenging.…”

Section: Introductionmentioning

confidence: 99%

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

Joint Feature Selection and Parameter Tuning for Short-Term Traffic Flow Forecasting Based on Heuristically Optimized Multi-layer Neural Networks

Cited by 11 publications

References 17 publications

A Taxonomy of Traffic Forecasting Regression Problems From a Supervised Learning Perspective

A Taxonomy of Traffic Forecasting Regression Problems From a Supervised Learning Perspective

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

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

Contact Info

Product

Resources

About