Short-Term Prediction of Signal Cycle on an Arterial With Actuated-Uncoordinated Control Using Sparse Time Series Models

Abstract

Traffic signals as part of intelligent transportation systems can play a significant role toward making cities smart. Conventionally, most traffic lights are designed with fixed-time control, which induces a lot of slack time (unused green time). Actuated traffic lights control traffic flow in real time and are more responsive to the variation of traffic demands. For an isolated signal, a family of time series models such as autoregressive integrated moving average (ARIMA) models can be beneficial for predicting the next cycle length. However, when there are multiple signals placed along a corridor with different spacing and configurations, the cycle length variation of such signals is not just related to each signal's values, but it is also affected by the platoon of vehicles coming from neighboring intersections. In this paper, a multivariate time series model is developed to analyze the behavior of signal cycle lengths of multiple intersections placed along a corridor in a fully actuated setup. Five signalized intersections have been modeled along a corridor, with different spacing among them, together with multiple levels of traffic demand. To tackle the high-dimensional nature of the problem, penalized least squares method are utilized in the estimation procedure to output sparse models. Two proposed sparse time series methods captured the signal data reasonably well, and outperformed the conventional vector autoregressive (VAR) model -in some cases up to 17% -as well as being more powerful than univariate models such as ARIMA.

Methodology Designed to Evaluate Accidents at Intersection Crossings with Respect to Forensic Purposes and Transport Sustainability

“…where N is the total number of accidents during the monitored period (it is possible to replace the absolute number of accidents with another parameter, such as the number of fatalities, severe injuries, etc., and, in this way, to define the derived parameters as well); I is the daily average traffic intensity (vehicles/day); L is the length of the section (km); and t is the monitored period (years) [27]. The marker value is most frequently between 0.1 and 0.9; when exceeding the value of 1.6, the respective road section is considered as problematic.…”

“…The marker value is most frequently between 0.1 and 0.9; when exceeding the value of 1.6, the respective road section is considered as problematic. A disadvantage of the mentioned marker is that the calculation does not take into account the accident seriousness [22,27].…”

“…For the evaluation of safety or non-safety, the relative accident rate indicator, R, is used, which indicates the probability of an accident at a certain place with regard to the driving performance [27]. The indicator unit is the number of accidents per one million kilometers traveled by vehicles and it is calculated according to the following relation:…”

“…where N is the total number of accidents during the monitored period (it is possible to replace the absolute number of accidents with another parameter, such as the number of fatalities, severe injuries, etc., and, in this way, to define the derived parameters as well); I is the daily average traffic intensity (vehicles/day); L is the length of the section (km); and t is the monitored period (years) [27]. At a junction, there are areas restricted for non-collision movement, but also areas where there is a chance of collision (the collision area), and traffic screened areas which are non-drivable and are either limited by means of horizontal signs or modified as elevated traffic islands [25].…”

Traffic Status Prediction of Arterial Roads Based on the Deep Recurrent Q-Learning

“…To deal with the abovementioned issues, many methods, such as combined vector machine-based [27] and phase space reconstructionbased [28], have been proposed to achieve better results. However, most of these machine learning-based methods lack robustness to catch the huge data, resulting in the model generally lacking long-term effectiveness and scalability [29][30][31].…”