Stochastic model for the prediction of short time number of fire accident occurrence in Niger State using Viterbi Algorithm

Abstract

In this paper, we look into ways by which fire outbreak (accident) can be suppressed. A stochastic model that predicts the number of fire accident occurrence in Niger State using Viterbi Algorithm is presented. A three-State stochastic model was formulated using the principle of Markov and each state of the model has four possible observations. The parameters of the model were estimated using the fire accident data collected from the archive of Niger State Fire Service, after which the model was trained using Baum-welch Algorithm to attend maximum likelihood. The Validity test for the model recorded 75% accuracy for short time prediction and shows 50% accuracy for long time prediction. This indicates that the model is more reliable and dependable for short time prediction.Information for this study could serve as a guide to the government in policy formulation that might assist in curbing the number of fire accident occurrences in Niger State.