Risk management prediction for overcrowding in railway stations Utilising Adaptive Nero Fuzzy Inference System (ANFIS)

In this research, an intelligent system for managing risks is developed with a framework to aid in managing the risks in the railway stations. A method to advance risk management in the railway stations is needed in order to minimize risk through an automated process taking into consideration all the factors in the system and how they work together to provide an acceptable level of safety and security. Thus, the Adaptive Nero Fuzzy Inference System (ANFIS) is proposed to improve risk management as an intelligently selected model which is powerful in dealing with uncertainties in risk variables. The methods of artificial neural network (ANN) and Fuzzy interface system (FIS) have been proven as tools for measuring risks in many fields. In this case study, the railway is selected as a place for managing the risks of overcrowding in the railway stations taking two parameters as input for risk value output using a hybrid model, which has the potency to deal with risk uncertainties and to learn by ANN training processes. The results show that the ANFIS method is more promising in the management of station risks. The framework can be applied for other risks in the station and more for a wide range of other systems. Also, ANFIS has the ability to learn from past risk records for future prediction. Clearly, the risk indexes are essential to reflect the actual condition of the station and they can indicate a high level of risks at the early stage, such as with overcrowding. The dynamic model of risk management can define risk levels and aid the decision makers by convenient and reliable results based on recorded data. Finally, the model can be generalised for other risks.