Traffic congestion is a complex, vexing, and growing issue day by day in most urban areas worldwide. The integration of the newly emerging deep learning approach and the traditional reinforcement learning approach has created an advanced approach called deep reinforcement learning (DRL) that has shown promising results in solving high-dimensional and complex problems, including traffic congestion. This article presents a review of the attributes of traffic signal control (TSC), as well as DRL architectures and methods applied to TSC, which helps to understand how DRL has been applied to address traffic congestion and achieve performance enhancement. The review also covers simulation platforms, a complexity analysis, as well as guidelines and design considerations for the application of DRL to TSC. Finally, this article presents open issues and new research areas with the objective to spark new interest in this research field. To the best of our knowledge, this is the first review article that focuses on the application of DRL to TSC.

Previous studies in computer science education show that game playing is negatively correlated with success in introductory programming classes in (Wilson, Shrock ACM SIGCSE Bulletin, vol 33, pp 184–188, 2001). However, informally, we observed that students who have previous gaming experience take to programming tasks easier than those without gaming experience. There have also been recent studies that show that playing strategic video games can improve problem-solving skills which is an essential skill in program design. This chapter presents the findings of our study to identify if a correlation between previous gaming experience (game playing) and individual computational thinking (CT) skills exists. To achieve this, a survey was administered on undergraduate students undertaking an introductory computing course to collect data on their gaming history and an individual assignment on Scratch. Each project was subsequently analysed to determine the level of mastery of core CT skills. Cochran–Armitage test of trend was then executed on each CT skill category with respect to the coded gaming experience. The results obtained during our analysis shows a correlation between gaming experience and specific categories of the CT skills domain particularly in the area of abstraction and problem-solving and user interactivity. The outcome of our study should be beneficial as ways to leverage on students’ gaming experience in the classroom will also be discussed. Keywords Computational thinking Game-based learning Games and learning Scratch assignment Introductory programming

An extension of the Poisson distribution is derived by considering a stochastic point process where the duration has a generalized Weibull distribution. This distribution is able to represent under, equi and over dispersion, a useful feature in data analysis. The computation of the probabilities and renewal function (expected number of renewals) are examined. Parameter estimation by the method of maximum likelihood is considered with applications of the count distribution to real frequency count data exhibiting under and over dispersion. It is shown that the generalized Weibull count distribution fits much better than the Weibull and gamma duration models.

In this paper, we propose a generalized form of Sichel distribution which is obtained by mixing the Poisson distribution with the extended generalized inverse Gaussian distribution. This distribution models over dispersed, zero-inflated and heavy-tailed count data sets. These characteristics are examined with respect to the dispersion, zero-inflation and the third central moment inflation indices. Examples are provided to compare the extension with several other existing models including the Poisson-inverse Gaussian and the Sichel distributions.

A count distribution is presented by considering a renewal process where the distribution of the duration is a finite mixture of exponential distributions. This distribution is able to model over dispersion, a feature often found in observed count data. The computation of the probabilities and renewal function (expected number of renewals) are examined. Parameter estimation by the method of maximum likelihood is considered with applications of the count distribution to real frequency count data exhibiting over dispersion. It is shown that the mixture of exponentials count distribution fits over dispersed data better than the Poisson process and serves as an alternative to the gamma count distribution.