Neural networks have been extensively applied to short-term traffic prediction in the past years. This study proposes a novel architecture of neural networks, Long Short-Term Neural Network (LSTM NN), to capture nonlinear traffic dynamic in an effective manner. The LSTM NN can overcome the issue of back-propagated error decay through memory blocks, and thus exhibits the superior capability for time series prediction with long temporal dependency. In addition, the LSTM NN can automatically determine the optimal time lags. To validate the effectiveness of LSTM NN, travel speed data from traffic microwave detectors in Beijing are used for model training and testing. A comparison with different topologies of dynamic neural networks as well as other prevailing parametric and nonparametric algorithms suggests that LSTM NN can achieve the best prediction performance in terms of both accuracy and stability.

Long short-term memory neural network for traffic speed prediction using remote microwave sensor data

This article presents the theoretical basis for modeling univariate traffic condition data streams as seasonal autoregressive integrated moving average processes. This foundation rests on the Wold decomposition theorem and on the assertion that a one-week lagged first seasonal difference applied to discrete interval traffic condition data will yield a weakly stationary transformation. Moreover, empirical results using actual intelligent transportation system data are presented and found to be consistent with the theoretical hypothesis. Conclusions are given on the implications of these assertions and findings relative to ongoing intelligent transportation systems research, deployment, and operations.

/pdf/modeling-and-forecasting-vehicular-traffic-flow-as-a-4l9jx8epis.pdf

Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results

For the last two decades, intelligent transportation systems (ITS) have emerged as an efficient way of improving the performance of transportation systems, enhancing travel security, and providing more choices to travelers. A significant change in ITS in recent years is that much more data are collected from a variety of sources and can be processed into various forms for different stakeholders. The availability of a large amount of data can potentially lead to a revolution in ITS development, changing an ITS from a conventional technology-driven system into a more powerful multifunctional data-driven intelligent transportation system (D2ITS) : a system that is vision, multisource, and learning algorithm driven to optimize its performance. Furthermore, D2ITS is trending to become a privacy-aware people-centric more intelligent system. In this paper, we provide a survey on the development of D2ITS, discussing the functionality of its key components and some deployment issues associated with D2ITS Future research directions for the development of D2ITS is also presented.

Data-Driven Intelligent Transportation Systems: A Survey

Traffic congestion in urban road and freeway networks leads to a strong degradation of the network infrastructure and accordingly reduced throughput, which can be countered via suitable control measures and strategies. After illustrating the main reasons for infrastructure deterioration due to traffic congestion, a comprehensive overview of proposed and implemented control strategies is provided for three areas: urban road networks, freeway networks, and route guidance. Selected application results, obtained from either simulation studies or field implementations, are briefly outlined to illustrate the impact of various control actions and strategies. The paper concludes with a brief discussion of future needs in this important technical area.

/pdf/review-of-road-traffic-control-strategies-2pzcx3izzi.pdf

Review of road traffic control strategies

Since the early 1980s, short-term traffic forecasting has been an integral part of most Intelligent Transportation Systems (ITS) research and applications; most effort has gone into developing methodologies that can be used to model traffic characteristics and produce anticipated traffic conditions. Existing literature is voluminous, and has largely used single point data from motorways and has employed univariate mathematical models to predict traffic volumes or travel times. Recent developments in technology and the widespread use of powerful computers and mathematical models allow researchers an unprecedented opportunity to expand horizons and direct work in 10 challenging, yet relatively under researched, directions. It is these existing challenges that we review in this paper and offer suggestions for future work.

Short-term traffic forecasting: Where we are and where we’re going

With the rapid development of autonomous vehicles, it is necessary to explore new business opportunities, especially under the assistance of internet of things, which accelerate the penetration in ...

https://journals.sagepub.com/doi/pdf/10.1177/0954407021994445

Business models and cost analysis of automated valet parking and shared autonomous vehicles assisted by internet of things

Reliability Equivalence in Public Transport Contexts

This paper presents the preliminary results of a two-year study on reducing urban pollution exposure from road transport (RUPERT). The main aim of this project is to develop a new modelling framework for nitrogen dioxide, carbon monoxide and particulate matter to simulate exposures of different population groups across a city, and to assess the impact of roadside concentrations on these exposures. This will be achieved by modelling the frequency distribution of personal exposures (PEFDs) as a function of urban background and roadside concentrations, under different traffic conditions. The modelling approach combines new and existing models relating traffic and air pollution data, with particular emphasis of the impact of congestion, and the probabilistic modelling framework of personal exposure. Modelling of roadside concentrations consists of two main elements, namely the analysis of concentrations patterns at different roadside sites and of the relationship between traffic conditions and added roadside pollution. Roadside concentrations are predicted using empirically derived relationships; statistical models, novel statistics and artificial neural networks namely feed forward neural network and radial basis neural network. The exposure modelling is carried out by linking two models: the INDAIR model, which is designed to simulate probabilistically diurnal profiles of air pollutant concentrations in a range of microenvironments, and the EXPAIR model, which is designed to simulate population exposure patterns based on population time-activity patterns and a library of micro-environmental concentrations derived from the INDAIR model.

/pdf/reducing-urban-pollution-exposure-from-road-transport-rupert-4lh7jnp18x.pdf

Reducing Urban Pollution Exposure from Road Transport (RUPERT)

Insight into the penalty of exhaust emissions and fuel consumption by DPF regeneration of a diesel passenger car.

Beijing is a city with a history of about 3,000 years. In the past several decades, pursuing to be industrialized used to be a main goal of the city which caused more and more serious pollution problems. Since the late of 1990s, actions have been taken to deal with the air pollution in Beijing in order to enhance living level of its residents. However, countermeasures taken firstly were almost on the adjustment of development routine of industry. Until recent years, especially approaching the 2008 Olympic Games, complicated schemes on green transport was concretely carried out. It was not only aiming for a currently clean air, but also a future sustainable development of transport and urbanization. Among the actions taken on green transport, there are exploration of low emission vehicles, priority to public transport, cycling and walking improvement and intelligent information techniques application. This paper summarizes these action schemes and what’s on now in Beijing.

Haibo Chen

Papers

Business models and cost analysis of automated valet parking and shared autonomous vehicles assisted by internet of things

Reliability Equivalence in Public Transport Contexts

Reducing Urban Pollution Exposure from Road Transport (RUPERT)

Insight into the penalty of exhaust emissions and fuel consumption by DPF regeneration of a diesel passenger car.

Actions Taken on Green Transport: Experiences of Beijing