APPLYING TIME SERIES MODELS TO PREDICT THE RATE OF INFLUENZA IN SEVERAL NORTHERN VIETNAM PROVINCES

Nguyen Duc Tuan Anh; Nguyen Anh Duc; Pham Thi Anh Huong; Tran Thi Thu Huyen; Nguyen Van Hau

Nguyen Duc Tuan Anh Hung Yen University of Technology and Education
Nguyen Anh Duc Hung Yen University of Technology and Education
Pham Thi Anh Huong Hung Yen University of Technology and Education
Tran Thi Thu Huyen Hung Yen University of Technology and Education
Nguyen Van Hau Hung Yen University of Technology and Education

Keywords: machine learning, influenza, Auto regression, Moving average, Autoregressive Integrated Moving Average

Abstract

Many provinces in the center of the Red River Delta in North Vietnam are heavily affected by infectious diseases. In recent times, many scientists have studied and applied time series models to predict the rate and number of infectious diseases, thus helping healthcare organizations to prevent the spread of deadly outbreaks such as dengue, diarrhea, and influenza. This paper investigates and applies three deep learning models, CNN, RNN, and LSTM, in order to compare with two traditional machine learning models Support Vector Machine (SVM) and Linear Regression (LR). Experimental results open up several interesting research directions.

References

Tổng cục thống kê và tổ chức Unicef Vietnam, 2014, Điều tra đánh giá các mục tiêu trẻ em và phụ nữ 2014.

Viện Vệ sinh dịch tễ Trung ương, 2013, Ảnh hưởng của biến đổi khí hậu với một số bệnh dịch lây truyền qua đường tiêu hóa và đề xuất giải pháp can thiệp.

-3 WHO, 2013, Cholera, WHO, accessed 27 February-2013, from http://www.who.int/topics/cholera/about/en/index.html.

Buckle, G.C., Walker, C.L., and Black, R.E., “Typhoid fever and paratyphoid fever: Systematic review to estimate global morbidity and mortality for 2010”. J Glob Health, 2012, 2(1), p. 10401.

Global Burden of Disease Study 2016 Diarrhoeal Disease Collaborators, “Estimates of the global, regional, and national morbidity, mortality, and aetiologies of diarrhoea in 195 countries: a systematic analysis for the Global Burden of Disease Study 2016”. Lancet Infect Dis, 2018, 18(11), pp. 1211-1228.