Have a personal or library account? Click to login
Regional distribution of non-human H7N9 avian influenza virus detections in China and construction of a predictive model Cover

Regional distribution of non-human H7N9 avian influenza virus detections in China and construction of a predictive model

By: Zeying Huang,  Haijun Li and  Beixun Huang  
Open Access
|Jul 2021

Figures & Tables

Fig. 1

Hierarchical Structure of WPD
Hierarchical Structure of WPD

Fig. 2

Regional distribution of H7N9 avian influenza virus detections in China
Regional distribution of H7N9 avian influenza virus detections in China

Fig. 3

Regional distribution of H7N9 avian influenza virus in China from 2013 to 2020
Regional distribution of H7N9 avian influenza virus in China from 2013 to 2020

Fig. 4

Regional distribution of cumulative H7N9 avian influenza virus detections in China from January to December between 2013 and 2020
Regional distribution of cumulative H7N9 avian influenza virus detections in China from January to December between 2013 and 2020

Fig. 5

Regional distribution of H7N9 avian influenza virus detections before and after comprehensive H7N9 immunisation of at-risk animals in China
Regional distribution of H7N9 avian influenza virus detections before and after comprehensive H7N9 immunisation of at-risk animals in China

Fig. 6

Temporal distribution of positive rate of animal H7N9 avian influenza virus detections in China from 2013 to 2020
Temporal distribution of positive rate of animal H7N9 avian influenza virus detections in China from 2013 to 2020

Fig. 7

Steps for constructing the LS-SVM-ARIMA combined model based on WPDLS-SVM – least squares support-vector machines; ARIMA – autoregressive integrated moving average
Steps for constructing the LS-SVM-ARIMA combined model based on WPDLS-SVM – least squares support-vector machines; ARIMA – autoregressive integrated moving average

Fig. 8

Low-frequency trend sequence decomposition of positive rates of H7N9 avian influenza virus from April 2013 to April 2019
Low-frequency trend sequence decomposition of positive rates of H7N9 avian influenza virus from April 2013 to April 2019

Fig. 9

High-frequency trend sequence decomposition of positive rates of H7N9 avian influenza virus detections from April 2013 to April 2019
High-frequency trend sequence decomposition of positive rates of H7N9 avian influenza virus detections from April 2013 to April 2019

Fig. 10

Comparisons of predicted values from each model with the true valuesLS-SVM – least square support-vector machines; WPD – wavelet packet decomposition; ARIMA – autoregressive integrated moving average
Comparisons of predicted values from each model with the true valuesLS-SVM – least square support-vector machines; WPD – wavelet packet decomposition; ARIMA – autoregressive integrated moving average

Spatial autocorrelation analysis of H7N9 avian influenza virus detections in China

VariableMoran’s IZ scoreP value
From 2013 to 2020−0.0140.3870.350
In 2013−0.0190.2590.398
In 2014−0.046−0.3620.359
In 20150.0421.7830.037
In 2016−0.064−0.9920.161
In 2017−0.034−0.0750.470
In 2018−0.0070.6070.272
In 2019−0.0210.2390.406
In 2020
In January−0.0080.5070.306
In February−0.0080.5260.299
In March−0.0060.5630.287
In April−0.0040.5860.279
In May−0.040−0.2100.417
In June−0.045−0.3500.363
In July0.0091.1030.135
In August
In September−0.073−0.9960.160
In October−0.036−0.1640.435
In November−0.046−0.3660.357
In December0.0722.3200.010
Before comprehensive animal H7N9 immunisation−0.0200.2550.399
After comprehensive animal H7N9 immunisation−0.0280.0580.477

Optimisation results of low-frequency trend sequence parameters

Decomposition sequenceHyperparameters σNormalisation parameters ɣ
[3,0]95067350.8
[3,1]2514.53946.2
[3,2]9113.69740.8
[3,3]818.7097242.1

ARIMA model parameters

Decomposition sequenceARIMA model parameters
[3,4]ARIMA (1,0,0)*(2,0,0) [12]
[3,5]ARIMA (3,0,0)
[3,6]ARIMA (0,0,0)
[3,7]ARIMA (3,0,0)

Prediction results of the LS-SVM-ARIMA combined model based on WPD

DateReal value[3,0][3,1][3,2][3,3][3,4][3,5][3,6][3,7]Predictive value
05/20190000.001000.001000.002
06/2019000000000.0010.001
07/2019000.0010000000.001
08/201900.001000.0010.0010000.003
09/201900000.00100.001000.002
10/20190.0010.0010.0020.0010.0010.0010.00200.0010.010
11/201900.0010.001000.0010000.003
12/201900.00100.0010.00100.00100.0020.006
01/2020000.00100.0010.0010.001000.004
02/202000.0010000.0020000.003
03/2020000.0010000000.001
04/2020000.001000.0010000.002

Evaluation of the prediction results of the different models

Evaluation indexLS-SVM-ARIMA combined model based on WPDARIMA modelLS-SVM modelLS-SVM-model ARIMA
MAE0.0240.1190.0980.077
RMSE0.0200.0670.0590.041

Situation of H7N9 avian influenza epidemic from April 2013 to April 2020

TimeProvinceNumber of outbreaksPoultryNumber of casesNumber of fatalitiesNumber of animals culled
June 2017Inner Mongolia2Chicken63,40637,582424,197
June 2017Heilongjiang1Chicken20,15019,50016,610
August 2017Anhui1Chicken1,36891074,463
March 2018Shaanxi1Chicken1,0008101,000
April 2018Shanxi1Chicken8126996,374
April 2018Ningxia1Chicken1,20058513,578
May 2018Liaoning1Chicken11,0009,0008,000
May 2018Ningxia1Chicken3,0002,21086,000
March 2019Liaoning1Peacock99191

Prediction results based on the three models: ARIMA, LS-SVM and ARIMA-LS-SVM

DateReal valueARIMA modelLS-SVM modelLS-SVM-ARIMA model
05/201900.0140.0130.009
06/201900.0070.0060.011
07/201900.0040.0050.016
08/201900.0110.0120.012
09/201900.0090.0080.008
10/20190.0080.0140.0130.020
11/201900.0170.0100.008
12/201900.0200.0150.016
01/202000.0050.0060.007
02/202000.0100.0070.003
03/202000.0110.0050.005
04/202000.0180.0120.010
Language: English
Page range: 253 - 264
Submitted on: Jan 4, 2021
Accepted on: Jun 10, 2021
Published on: Jul 5, 2021
Published by: National Veterinary Research Institute in Pulawy
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year

© 2021 Zeying Huang, Haijun Li, Beixun Huang, published by National Veterinary Research Institute in Pulawy
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.