Wen Long Yue

A Bayesian Network Approach to Causation Analysis of Road Accidents Using Netica

Based on an overall consideration of factors affecting road safety evaluations, the Bayesian network theory based on probability risk analysis was applied to the causation analysis of road accidents. By taking Adelaide Central Business District (CBD) in South Australia as a case, the Bayesian network structure was established by integrating K2 algorithm with experts’ knowledge, and Expectation-Maximization algorithm that could process missing data was adopted to conduct the parameter learning in Netica, thereby establishing the Bayesian network model for the causation analysis of road accidents. Then Netica was used to carry out posterior probability reasoning, the most probable explanation, and inferential analysis. The results showed that the Bayesian network model could effectively explore the complex logical relation in road accidents and express the uncertain relation among related variables. The model not only can quantitatively predict the probability of an accident in certain road traffic condition but also can find the key reasons and the most unfavorable state combination which leads to the occurrence of an accident. The results of the study can provide theoretical support for urban road management authorities to thoroughly analyse the induction factors of road accidents and then establish basis in improving the safety performance of the urban road traffic system.

A Comparison between Genetic Algorithms and Simulated Annealing for Minimizing Transfer Waiting Time in Transit Systems

—Reducing the waiting time imposed on thepassengerstransferring between transit lines has always been a concern for public transport schedulers, as it is a complicated problem by nature. Typically, network-wide minimization of transfer waiting time is a highly complex optimization problem, particularly in the case of dealing with huge transit networks. This problem is unlikely to be solved by exact optimization techniques. This study aims to investigate the capability of two powerful metaheuristic algorithms, genetic algorithms and simulate annealing, in coping with the transfer optimization problem. Amathematical model is presented in this study for minimizing the total transfer waiting time in transit systems. Based on this model, a genetic algorithm and a simulated annealing algorithm are developed and applied to a transit network comprising numerous transfer points. The comparative analysis of the results revealed the ability of the both algorithms in reducing the transfer waiting time although the genetic algorithm could return better results in relatively shorter computation times.

Application of Simulated Annealing in Transit Schedule Synchronization

transport servicesis of vital importance in transit planning, as it has direct impacts on the waiting time imposed on transferring passengers. This task, which is widely recognized as schedule synchronization, is highly complicated by nature since it typically leads to a complex combinatorial optimization problem. This study aims to investigate the capability of simulated annealing algorithm in coping with this problem. A new mathematical programming model is presented for the purpose of minimizing the total transfer waiting time in transit networks. Then, a simulated annealing algorithm is developed and applied to a small-size transit network in order to test the algorithm applicability. The numerical results showed the capability of the algorithm in tackling the transit schedule synchronization problem.

The Deduction of Coefficient Matrix for Cubic Non-Uniform B-Spline Curves

The cubic B-Spline curves have many engineering applications, such as graphic matching, materials cutting and layout arrangement. The existing mathematical representations, usually defined as polynomial function, its coefficient matrix of non-uniform B-Spline curves are complicated, difficult to understand, and require sophisticated algorithm in programming implementation. This paper aims at presenting a procedure based on the de Boor-Cox recursion formula, the coefficient matrixes of non-uniform B-Spline curves could be deducted. The application of this approach has been successfully used in shoe manufacturing process for material cutting control system.

The Methodology Development of Railway Level Crossing Safety Systems – South Australia Case Study

This paper describes how railway level crossing accident is one of the major contributing factors of railway related fatalities in many countries. Even though railway level crossing accidents can be considered as a rare event, the impact is often severe. In Australia, safety issues at railway level crossing are not very serious relative to those of developing countries. However, railway level crossing accidents have continuously become a concern in railway industries in especially when it involved fatalities. This paper presents a methodological development proposed for railway level crossing safety systems and South Australia’s situation is used as a testing case. Due to the complex nature of railway level crossing safety systems; Petri Nets approach will be applied in assisting the development of a meaningful evaluation model. The components of basic concept of safety engineering; engineering infrastructure, level crossing surrounding environment and human factors will also be considered in the model.