Predictive Reasoning and Machine Learning for the Enhancement of Reliability in Railway Systems

Train Dispatching Management With Data- Driven Approaches: A Comprehensive Review and Appraisal

“…The proposed model on overage can achieve over 80% accuracy in predictions within a 60-min horizon [109]. Of course, the joint method with Bayesian Reasoning and Markov model can be used to predict the delay state in different station [110], [111] c: ML Kecman and Goverde [97] proposed a statistical learning method that combines SM and ML methods. The modeling is divided into three steps, namely, least-trimmed squares robust linear regression, regression trees, and random forests.…”

Mitigating errors of predicted delays of a train at neighbouring stops

“…Thereafter, Formula (10) is formed as a quadratic equation for K, which is rather difficult to solve. However, the quadratic terms of K are able to be cancelled out to simplify the calculation under necessary requirements Formula (10) is reformed to be Formula (11) when the cancelling term K = R −1 B T P is substituted into Formula (10). The quadratic term of K is able to be eliminated, then the determination of K is closely related to P which is a hypothetical matrix.…”

“…Furthermore, Martin designed a prototype rail advisory system that applied a series of predictive reasoning and machine-learning models [10]. Gaurav and Srivastava [11] studied the systemic delay of train arrivals by n-order Markov frameworks and experiments with two regression-based models.…”

Forecasting the estimated time of arrival for a cargo dispatch delivered by a freight train along a railway section

“…Paper [12] addresses the development of methods for forecasting trains traffic in time and space under an on-line operation mode. The constructed methods are proposed for a future consultative system of railroad transport dispatch.…”