1. School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China 2. State and Local Joint Engineering Research Center for Satellite Navigation and Location Service, Guilin University of Electronic Technology, Guilin 541004, China
The existing spread predicting models of infectious diseases have not sufficiently considered the intrinsic correlation of the data. To solve this problem, graph polynomial-vector autoregressive (GP-VAR) model was used to predict the spread of infectious diseases, and a new optimization method for estimating model parameters was proposed. The regions where infectious diseases occur were modeled as nodes on the graph, and edges and weights between nodes were determined by the distance information of the regions and the flow of people, so as to reflect the spatial relevance in the transmission process of infectious diseases. The number of cases at different times was modeled as the time-varying graph signal, the GP-VAR model was used to predict the evolution process of the time-varying graph signal on the graph, and a least squares (LS) optimization method was designed to estimate the parameters of the GP-VAR model. Experimental results show that the proposed method can better consider the correlation of data in spatial dimension and the evolution of data in time dimension, and characterize the transmission characteristics of infectious diseases more accurately, which has universality and better prediction effect compared with the existing prediction methods.
Wen-juan LI,Hong-gao DENG,Mou MA,Jun-zheng JIANG. Prediction method of infectious disease transmission based on graph signal processing. Journal of ZheJiang University (Engineering Science), 2022, 56(5): 1017-1024.
Fig.3Connected graph for 125 major cities in Europe
Fig.4Connected graph for 412 regions in Germany
Fig.5One-step prediction results of proposed method for consecutive 50 days with different types of infectious disease data
Fig.6Comparison of 6-step prediction errors of different methods with SI, SEIRS and COVID-19 data
Fig.7Comparison of 5-step prediction error of proposed method with different parameters
[1]
KHADDAJ S, CHRIEF H. Prevention and control of emerging infectious diseases in human populations [C]// Proceedings of 2020 19th International Symposium on Distributed Computing and Applications for Business Engineering and Science. Xuzhou: [s.n.], 2020: 341-344.
[2]
庞维庆, 何宁, 罗燕华, 等 基于数据融合的ABC-SVM社区疾病预测方法[J]. 浙江大学学报: 工学版, 2021, 55 (7): 1253- 1260+1326 PANG Wei-qing, HE Ning, LUO Yan-hua, et al ABC-SVM disease prediction method based on data fusion in community health care[J]. Journal of Zhejiang University: Engineering Science, 2021, 55 (7): 1253- 1260+1326
[3]
KERMACK W O, MCKENDRICK A G A A Contribution to the mathematical theory of epidemics[J]. Proceedings of the Royal Society A: Mathematical Physical and Engineering Sciences, 1927, 115 (772): 700- 721
[4]
GAO S, CHEN L, NIETO J J, et al Analysis of a delayed epidemic model with pulse vaccination and saturation incidence[J]. Vaccine, 2006, 24 (35/36): 6037- 6045
[5]
GOMEZ S, ARENAS A, BORGE-HOLTHOEFER J, et al Discrete-time Markov chain approach to contact-based disease spreading in complex networks[J]. Europhysics Letters, 2010, 89 (3): 38009
doi: 10.1209/0295-5075/89/38009
[6]
BENVENUTO D, GIOVANETTI M, VASSALLO L, et al Application of the ARIMA model on the COVID-2019 epidemic dataset[J]. Data in Brief, 2020, 29: 105340
doi: 10.1016/j.dib.2020.105340
[7]
余艳妮, 聂绍发, 廖青, 等 传染病预测及模型选择研究进展[J]. 公共卫生与预防医学, 2018, 29 (5): 89- 92 YU Yan-ni, NIE Shao-fa, LIAO Qing, et al Research progress on prediction and model selection of infectious diseases[J]. Journal of Public Health and Preventive Medicine, 2018, 29 (5): 89- 92
[8]
KIESHA P, YANG L, TIMOTHY W R, et al The effect of control strategies to reduce social mixing on outcomes of the COVID-19 epidemic in Wuhan, China: a modelling study[J]. The Lancet Public Health, 2020, 5 (5): 261- 270
doi: 10.1016/S2468-2667(20)30073-6
[9]
SANDRYHAILA A, MOURA J M Discrete signal processing on graphs[J]. IEEE Transactions on Signal Processing, 2013, 61 (7): 1644- 1656
doi: 10.1109/TSP.2013.2238935
[10]
杨杰, 蒋俊正 利用联合图模型的传感器网络数据修复方法[J]. 西安电子科技大学学报, 2020, 47 (1): 44- 51 YANG Jie, JIANG Jun-zheng Method for data recovery in the sensor network based on the joint graph model[J]. Journal of Xidian University, 2020, 47 (1): 44- 51
[11]
XUE X The contact process with semi-infected state on the complete graph[J]. Stochastic Analysis and Applications, 2018, 36 (2): 324- 340
doi: 10.1080/07362994.2017.1399802
ISUFI E, LOUKAS A, PERRAUDIN N, et al Forecasting time series with VARMA recursions on graphs[J]. IEEE Transactions on Signal Processing, 2019, 67 (18): 4870- 4885
doi: 10.1109/TSP.2019.2929930
[14]
MEI J, MOUEA J Signal processing on graphs: causal modeling of unstructured data[J]. IEEE Transactions on Signal Processing, 2017, 65 (8): 2077- 2092
doi: 10.1109/TSP.2016.2634543
[15]
NOWZARI C, PRECIADO V M, PAPPAS G J Analysis and control of epidemics: a survey of spreading processes on complex networks[J]. IEEE Control Systems, 2016, 36 (1): 26- 46
doi: 10.1109/MCS.2015.2495000
[16]
PUSCHEL M, MOURA J Algebraic signal processing theory: foundation and 1-D time[J]. IEEE Transactions on Signal Processing, 2008, 56 (8): 3572- 3585
doi: 10.1109/TSP.2008.925261
[17]
SANDRYHAILA A, MOURA J Discrete signal processing on graphs: frequency analysis[J]. IEEE Transactions on Signal Processing, 2014, 62 (12): 3042- 3054
doi: 10.1109/TSP.2014.2321121
[18]
JIANG J, CHENG C, SUN Q Nonsubsampled graph filter banks: theory and distributed algorithms[J]. IEEE Transactions on Signal Processing, 2019, 67 (15): 3938- 3953
doi: 10.1109/TSP.2019.2922160
[19]
TAY D B, JIANG J Time-varying graph signal denoising via median filters[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2021, 68 (3): 1053- 1057
doi: 10.1109/TCSII.2020.3017800
[20]
JIANG J, FENG H, TAY D B, et al Theory and design of joint time-vertex nonsubsampled filter banks[J]. IEEE Transactions on Signal Processing, 2021, 69: 1968- 1982
doi: 10.1109/TSP.2021.3064984
[21]
GRASSI F, LOUKAS A, PERRAUDIN N, et al A time-vertex signal processing framework: scalable processing and meaningful representations for time-series on graphs[J]. IEEE Transactions on Signal Processing, 2018, 66 (3): 817- 829
doi: 10.1109/TSP.2017.2775589
[22]
JIANG J, TAY D B, SUN Q, et al Recovery of time-varying graph signals via distributed algorithms on regularized problems[J]. IEEE Transactions on Signal and Information Processing over Networks, 2020, 6: 540- 555
doi: 10.1109/TSIPN.2020.3010613
