Statistical Models for Predicting Swine F1u Incidences in India

Abstract

Swine flu, a respiratory disease caused by influenza viruses also NIHI virus, infects pig’s respiratory tract which results in a barking cough, decrease in appetite, secretions of nasal and endless behavior. These viruses may mutate so that they are easily transmissible among humans. To deal with these viruses, in this manuscript we have used various time series forecasting models to predict future cases of swine flu in India so that Government could take necessary steps to prevent the spread of this disease. Swine Flu data is collected from integrated diseases surveillance programme, Government of India. The data is of year 2010 to 2017; which provides information on yearly cases of Swine flu in different states of India. The forecasting models applied are Box-Cox transformation, Exponential Smoothing, Seasonal Naive and Neural Network. The result of the applied models are compared on the basis of errors such as Mean Error, Mean Absolute Error, Root Mean Square Error, Mean Absolute Scaled Error and Auto Correlation Function. Analyzing the final result we realized that the Neural Network forecasting model gives the best result among all others with the accuracy of 98.4%.