tetano
Editor, Senior Moderator
BMC Bioinformatics. 2019 Nov 25;20(Suppl 18):575. doi: 10.1186/s12859-019-3131-8. [h=1]Attention-based recurrent neural network for influenza epidemic prediction.[/h]
Zhu X[SUP]1[/SUP], Fu B[SUP]1[/SUP], Yang Y[SUP]1[/SUP], Ma Y[SUP]2[/SUP], Hao J[SUP]3[/SUP], Chen S[SUP]1[/SUP], Liu S[SUP]1[/SUP], Li T[SUP]2[/SUP], Liu S[SUP]4[/SUP], Guo W[SUP]4[/SUP], Liao Z[SUP]5,[/SUP][SUP]6[/SUP].
[h=3]Author information[/h] 1 College of Intelligence and Computing, Tianjin University, Peiyang Park Campus: No.135 Yaguan Road, Haihe Education Park, Tianjin, 300350, China. 2 Guangzhou Center for Disease Control and Prevention, Guangzhou, 510440, China. 3 College of Intelligence and Computing, Tianjin University, Peiyang Park Campus: No.135 Yaguan Road, Haihe Education Park, Tianjin, 300350, China. haojianye@gmail.com. 4 Automotive Data Center, China Automotive Technology & Research, Tianjin, 300300, China. 5 Pony Testing International Group, Tianjin, 300051, China. 6 Tianjin FoodSafety Inspection Technology Institute, Tianjin, 300300, China.
[h=3]Abstract[/h] [h=4]BACKGROUND:[/h] Influenza is an infectious respiratory disease that can cause serious public health hazard. Due to its huge threat to the society, precise real-time forecasting of influenza outbreaks is of great value to our public.
[h=4]RESULTS:[/h] In this paper, we propose a new deep neural network structure that forecasts a real-time influenza-like illness rate (ILI%) in Guangzhou, China. Long short-term memory (LSTM) neural networks is applied to precisely forecast accurateness due to the long-term attribute and diversity of influenza epidemic data. We devise a multi-channel LSTM neural network that can draw multiple information from different types of inputs. We also add attention mechanism to improve forecasting accuracy. By using this structure, we are able to deal with relationships between multiple inputs more appropriately. Our model fully consider the information in the data set, targetedly solving practical problems of the Guangzhou influenza epidemic forecasting.
[h=4]CONCLUSION:[/h] We assess the performance of our model by comparing it with different neural network structures and other state-of-the-art methods. The experimental results indicate that our model has strong competitiveness and can provide effective real-time influenza epidemic forecasting.
[h=4]KEYWORDS:[/h] Attention mechanism; Influenza epidemic prediction; Multi-channel LSTM neural network
PMID: 31760945 DOI: 10.1186/s12859-019-3131-8
Free full text
Zhu X[SUP]1[/SUP], Fu B[SUP]1[/SUP], Yang Y[SUP]1[/SUP], Ma Y[SUP]2[/SUP], Hao J[SUP]3[/SUP], Chen S[SUP]1[/SUP], Liu S[SUP]1[/SUP], Li T[SUP]2[/SUP], Liu S[SUP]4[/SUP], Guo W[SUP]4[/SUP], Liao Z[SUP]5,[/SUP][SUP]6[/SUP].
[h=3]Author information[/h] 1 College of Intelligence and Computing, Tianjin University, Peiyang Park Campus: No.135 Yaguan Road, Haihe Education Park, Tianjin, 300350, China. 2 Guangzhou Center for Disease Control and Prevention, Guangzhou, 510440, China. 3 College of Intelligence and Computing, Tianjin University, Peiyang Park Campus: No.135 Yaguan Road, Haihe Education Park, Tianjin, 300350, China. haojianye@gmail.com. 4 Automotive Data Center, China Automotive Technology & Research, Tianjin, 300300, China. 5 Pony Testing International Group, Tianjin, 300051, China. 6 Tianjin FoodSafety Inspection Technology Institute, Tianjin, 300300, China.
[h=3]Abstract[/h] [h=4]BACKGROUND:[/h] Influenza is an infectious respiratory disease that can cause serious public health hazard. Due to its huge threat to the society, precise real-time forecasting of influenza outbreaks is of great value to our public.
[h=4]RESULTS:[/h] In this paper, we propose a new deep neural network structure that forecasts a real-time influenza-like illness rate (ILI%) in Guangzhou, China. Long short-term memory (LSTM) neural networks is applied to precisely forecast accurateness due to the long-term attribute and diversity of influenza epidemic data. We devise a multi-channel LSTM neural network that can draw multiple information from different types of inputs. We also add attention mechanism to improve forecasting accuracy. By using this structure, we are able to deal with relationships between multiple inputs more appropriately. Our model fully consider the information in the data set, targetedly solving practical problems of the Guangzhou influenza epidemic forecasting.
[h=4]CONCLUSION:[/h] We assess the performance of our model by comparing it with different neural network structures and other state-of-the-art methods. The experimental results indicate that our model has strong competitiveness and can provide effective real-time influenza epidemic forecasting.
[h=4]KEYWORDS:[/h] Attention mechanism; Influenza epidemic prediction; Multi-channel LSTM neural network
PMID: 31760945 DOI: 10.1186/s12859-019-3131-8
Free full text