Local online kernel ridge regression for forecasting of urban travel times

Accurate and reliable forecasting of traffic variables is one of the primary functions of Intelligent Transportation Systems. Reliable systems that are able to forecast traffic conditions accurately, multiple time steps into the future, are required for advanced traveller information systems. However, traffic forecasting is a difficult task because of the nonlinear and nonstationary properties of traffic series. Traditional linear models are incapable of modelling such properties, and typically perform poorly, particularly when conditions differ from the norm. Machine learning approaches such as artificial neural networks, nonparametric regression and kernel methods (KMs) have often been shown to outperform linear models in the literature. A bottleneck of the latter approach is that the information pertaining to all previous traffic states must be contained within the kernel, but the computational complexity of KMs usually scales cubically with the number of data points in the kernel. In this paper, a novel kernel-based machine learning (ML) algorithm is developed, namely the local online kernel ridge regression (LOKRR) model. Exploiting the observation that traffic data exhibits strong cyclic patterns characterised by rush hour traffic, LOKRR makes use of local kernels with varying parameters that are defined around each time point. This approach has 3 advantages over the standard single kernel approach: (1) It allows parameters to vary by time of day, capturing the time varying distribution of traffic data; (2) It allows smaller kernels to be defined that contain only the relevant traffic patterns, and; (3) It is online, allowing new traffic data to be incorporated as it arrives. The model is applied to the forecasting of travel times on London’s road network, and is found to outperform three benchmark models in forecasting up to 1 h ahead.     

A genetic algorithm-based method for improving quality of travel time prediction intervals

The transportation literature is rich in the application of neural networks for travel time prediction. The uncertainty prevailing in operation of transportation systems, however, highly degrades prediction performance of neural networks. Prediction intervals for neural network outcomes can properly represent the uncertainty associated with the predictions. This paper studies an application of the delta technique for the construction of prediction intervals for bus and freeway travel times. The quality of these intervals strongly depends on the neural network structure and a training hyperparameter. A genetic algorithm–based method is developed that automates the neural network model selection and adjustment of the hyperparameter. Model selection and parameter adjustment is carried out through minimization of a prediction interval-based cost function, which depends on the width and coverage probability of constructed prediction intervals. Experiments conducted using the bus and freeway travel time datasets demonstrate the suitability of the proposed method for improving the quality of constructed prediction intervals in terms of their length and coverage probability.     

时间序列法预测沥青路面损坏状况指数研究

由于沥青路面损坏状况影响因素很多,因此要准确预测路面损坏状况较困难。文章采用时间序列法建立预测模型,结合同三高速公路（上海段）路面损坏状况的实测数据进行预测分析。分析结果表明时间序列法具有较高的预测精度和易修正性。     

Influence of coordinated traffic lights parameters on roadside pollutant concentrations

The paper examines the effects of coordinated traffic lights on CO and C₆H₆ roadside concentrations in an urban area of Palermo in Southern Italy. Traffic loop detectors and one pollution-monitoring are used to collect data for use in DRACULA traffic microsimulator software. CO and C₆H₆ roadside concentrations associated with varying cycle and offset times of the coordinated traffic lights are estimated using a neural network. Two functions were set up describing the relations of pollutant concentrations in term of cycle and offset time.     

CO2 emissions and expansion of railway,road, airline and in-land waterway networks over the 1985–2013 period in China: A time series analysis

China, the world’s largest CO₂ emitter, is continuing its long-term strategy to use transportation investments as a tool for development. With the expectation that transportation will contribute 30–40% of the total CO₂ emissions in China in the near future, there is an imminent need to identify how the development of different transportation modes may have different long-term effects on CO₂ emissions. Using time series data over the period of 1985–2013, this paper applies the combined autoregressive distributed lag (ARDL) and vector error correction model (VECM) approach to identify short- and long-run causal relationships between CO₂ emissions and mode-specific transportation development, including railway, road, airline, and inland waterway. We find that China’s domestic expansions of road, airline, and waterway infrastructure lead to long-run increases in CO₂ emissions. Among them, waterway has the strongest positive impact on CO₂ emissions, followed by road. Despite a short-run, positive impact on CO₂ emissions, railway expansion leads to long-run decreases in CO₂ emissions. The results are especially encouraging for the central government of China given its long-standing and on-going efforts to expand railway infrastructure at the national level. Looking forward, it is recommended that China continues its national investments in railway infrastructure to achieve both environment and economy goals.     

Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks

Short-term passenger flow forecasting is a vital component of transportation systems. The forecasting results can be applied to support transportation system management such as operation planning, and station passenger crowd regulation planning. In this paper, a hybrid EMD-BPN forecasting approach which combines empirical mode decomposition (EMD) and back-propagation neural networks (BPN) is developed to predict the short-term passenger flow in metro systems. There are three stages in the EMD-BPN forecasting approach. The first stage (EMD Stage) decomposes the short-term passenger flow series data into a number of intrinsic mode function (IMF) components. The second stage (Component Identification Stage) identifies the meaningful IMFs as inputs for BPN. The third stage (BPN Stage) applies BPN to perform the passenger flow forecasting. The historical passenger flow data, the extracted EMD components and temporal factors (i.e., the day of the week, the time period of the day, and weekday or weekend) are taken as inputs in the third stage. The experimental results indicate that the proposed hybrid EMD-BPN approach performs well and stably in forecasting the short-term metro passenger flow.     

Real time detection of driver attention: Emerging solutions based on robust iconic classifiers and dictionary of poses

Real time monitoring of driver attention by computer vision techniques is a key issue in the development of advanced driver assistance systems. While past work mostly focused on structured feature-based approaches, characterized by high computational requirements, emerging technologies based on iconic classifiers recently proved to be good candidates for the implementation of accurate and real-time solutions, characterized by simplicity and automatic fast training stages.In this work the combined use of binary classifiers and iconic data reduction, based on Sanger neural networks, is proposed, detailing critical aspects related to the application of this approach to the specific problem of driving assistance. In particular it is investigated the possibility of a simplified learning stage, based on a small dictionary of poses, that makes the system almost independent from the actual user.On-board experiments demonstrate the effectiveness of the approach, even in case of noise and adverse light conditions. Moreover the system proved unexpected robustness to various categories of users, including people with beard and eyeglasses. Temporal integration of classification results, together with a partial distinction among visual distraction and fatigue effects, make the proposed technology an excellent candidate for the exploration of adaptive and user-centered applications in the automotive field.     

Does telecommuting reduce vehicle-miles traveled? An aggregate time series analysis for the U.S.

. This study examines the impact of telecommuting on passenger vehicle-miles traveled (VMT) through a multivariate time series analysis of aggregate nationwide data spanning 1966–1999 for all variables except telecommuting, and 1988–1998 for telecommuting. The analysis was conducted in two stages. In the first stage, VMT (1966–1999) was modeled as a function of conventional variables representing economic activity, transportation price, transportation supply and socio-demographics. In the second stage, the residuals of the first stage (1988–1998) were modeled as a function of the number of telecommuters. We also assessed the change in annual VMT per telecommuter as well as VMT per telecommuting occasion, for 1998. The models suggest that telecommuting reduces VMT, with 94% confidence. Together with independent external evidence, the results suggest a reduction in annual VMT on the order of 0.8% or less. Even with impacts that small, when informally compared to similar reductions in VMT due to public transit ridership, telecommuting appears to be far more cost-effective in terms of public sector expenditures.