LSTM Recurrent Neural Networks for Influenza Trends Prediction

Influenza-like illness (ILI) is an acute respiratory infection causes substantial mortality and morbidity. Predict Influenza trends and response to a health disease rapidly is crucial to diminish the loss of life. In this paper, we employ the long short term memory (LSTM) recurrent neural networks to forecast the influenza trends. We are the first one to use multiple and novel data sources including virologic surveillance, influenza geographic spread, Google trends, climate and air pollution to predict influenza trends. Moreover, We find there are several environmental and climatic factors have the significant correlation with ILI rate.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[3]  Thomas G. Dietterich.  Machine Learning for Sequential Data: A Review , 2002, SSPR/SPR.

[4]  E. Lofgren,et al.  Influenza Seasonality: Underlying Causes and Modeling Theories , 2006, Journal of Virology.

[5]  A. Dugas,et al.  Google Flu Trends: correlation with emergency department influenza rates and crowding metrics. , 2011, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[6]  Shouling Ji,et al.  Generating Uncertain Networks Based on Historical Network Snapshots , 2013, COCOON.

[7]  Mark Dredze,et al.  Combining Search, Social Media, and Traditional Data Sources to Improve Influenza Surveillance , 2015, PLoS Comput. Biol..

[8]  Yingshu Li,et al.  An exploration of broader influence maximization in timeliness networks with opportunistic selection , 2016, J. Netw. Comput. Appl..

[9]  Angélique Stéphanou,et al.  Towards the Design of a Patient-Specific Virtual Tumour , 2016, Comput. Math. Methods Medicine.

[10]  Yi Pan,et al.  Bayesian Inference for Functional Dynamics Exploring in fMRI Data , 2016, Comput. Math. Methods Medicine.

[11]  Yingshu Li,et al.  The Roles of Social Network Mavens , 2016, 2016 12th International Conference on Mobile Ad-Hoc and Sensor Networks (MSN).

[12]  Guy Pujolle,et al.  NeuTM: A neural network-based framework for traffic matrix prediction in SDN , 2017, NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium.