Statistical analysis of crowd behaviour in catastrophic situation

Abstract

Machine learning (ML) is one of the emerging domains in classification and prediction. It is important to understand the responses of individuals in crowd during an earthquake emergency for making appropriate earthquake emergency management plan. Our research is focused on predicting the behaviour of individuals in a crowd during Catastrophic Situation. For this purpose, intended and actual behavioural response of crowd is collected by conducting a series of surveys. The attributes that are selected for result prediction are gender, age, affiliation, health status, training level, nearby exit, earthquake intensity, earthquake location, environmental status, and individual’s response. The dataset thus collected is divided into two crowds, Crowd 1 shows the intended behaviour whereas Crowd 2 shows actual. The decision tree, k-nearest neighbour, Naïve Bayes and neural network machine learning algorithms are used for predicting results. The results are analysed by using Rapid Miner as data mining tool. The dataset is split into two partitions. By applying randomization techniques like simple random sampling, shuffle random sampling, etc. we have trained and tested the machine learning algorithms. The results of this research will be a source of help in understanding critical details about crowd behaviour in earthquake emergency.