第3期 甘雨，等：新冠肺炎疫情趋势预测模型 ·535· CONTENT/10.1101/2020.01.23.20018549V2 model for COVID-19 real-time forecasting[J].Journal of [3]SHEN Mingwang,PENG Zhihang,XIAO Yanni,et al. University of Electronic Science and Technology of Modeling the epidemic trend of the 2019 novel coronavir- China.2020,49(3):362-368. us outbreak in China[J].The innovation,2020,1(3): [14]GUO Wei,XU Tao,TANG Keming.M-estimator-based 100048. online sequential extreme learning machine for predicting [4]HARKO T.LOBO F S N.MAK M K.Exact analytical chaotic time series with outliers[J].Neural computing and solutions of the Susceptible-Infected-Recovered(SIR)epi- applications,2017,28(12):4093-4110. demic model and of the SIR model with equal death and [15]HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al. birth rates[J].Applied mathematics and computation,2014, Deep residual learning for image recognition[Cl/Proceed- 236:184-194 ings of the IEEE Conference on Computer Vision and [5]KROGER M,SCHLICKEISER R.Analytical solution of Pattern Recognition.Las Vegas,NV,USA:IEEE,2016, the SIR-model for the temporal evolution of epidemics. 770-778 Part A:time-independent reproduction factor[J].Journal of [16]SIMONYAN K,ZISSERMAN A.Very deep convolu- pysics A,2020(50):505601. tional networks for large-scale image recognition[EB/OLl. [6]LI M Y,MULDOWNEY J S.Global stability for the SEIR (2015-04-10)[2020-07-28]http://arxiv.org/abs/1409.1556. model in epidemiology [J].Mathematical biosciences, [17]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Im- 1995,125(2):155-164. ageNet classification with deep convolutional neural net- [7]GODIO A.PACE F,VERGNANO A.SEIR modeling of works[C]//Proceedings of the 25th International Confer- the Italian epidemic of SARS-CoV-2 using computational ence on Neural Information Processing Systems.Red swarm intelligence[J].International journal of environ- Hook,NY,USA:Curran Associates Inc.,2012:1097- mental research and public health,2020,17(10):3535. 1105. [8]WU J T,LEUNG K,LEUNG G M.Nowcasting and fore- [18]COLLOBERT R,WESTON J,BOTTOU L,et al.Natur- casting the potential domestic and international spread of al language processing (almost)from scratch[J].The the 2019-nCoV outbreak originating in Wuhan,China:a journal of machine learning research,2011,12: modelling study[J].The lancet,2020,395(10225): 2493-2537. 689-697. [19]TAY Y,LUU A T,HUI S C.Compare,compress and [9]YANG Zifeng,ZENG Zhiqi,WANG Ke,et al.Modified propagate:enhancing neural architectures with alignment SEIR and Al prediction of the epidemics trend of COVID- factorization for natural language inference[C//Proceed- 19 in China under public health interventions[J].Journal of ings of the 2018 Conference on Empirical Methods in thoracic disease,2020,12(3):165-174. Natural Language Processing.Brussels,Belgium,2018: [10]WALKER P,WHITTAKER C,WATSON O,et al.The 1565-1575. global impact of COVID-19 and strategies for mitigation [20]DEVLIN J,CHANG M W,LEE K,et al.BERT:Pre- and suppression[EB/OL].(2020-03-26)[2020-07-28] training of deep bidirectional transformers for language https://www.imperial.ac.uk/mrc-global-infectious-disease- understanding[EB/OL].(2019-05-24)[2020-07-28] analysis/covid-19/report-12-global-impact-covid-19/. http://arxiv.org/abs/1810.04805. [1I]范如国，王奕博，罗明，等.基于SEIR的新冠肺炎传播 [21]HINTON G,DENG Li,YU Dong,et al.Deep neural net- 模型及拐点预测分析[】.电子科技大学学报，2020， works for acoustic modeling in speech recognition:the 49(3:369-374 shared views of four research groups[J].IEEE signal pro- FAN Ruguo,WANG Yibo,LUO Ming,et al.SEIR-based cessing magazine,2012,29(6):82-97. COVID-19 transmission model and inflection point pre- [22]SAK H.SENIOR A,RAO K,et al.Fast and accurate re- diction analysis[J].Journal of University of Electronic current neural network acoustic models for speech recog- Science and Technology of China,2020,49(3):369-374. nition[EB/OL].(2015-07-24[2020-07-28]htp:/arxiv.. [12]ARMOUR G C.BUFFA E S.A heuristic algorithm and org/abs/1507.06947. simulation approach to relative location of facilities[J]. [23]XIONG W,DROPPO J,HUANG X,et al.Achieving hu- Management science,1963,9(2):294-309. man parity in conversational speech recognition[EB/OL]. [13]梅文娟，刘震，朱静怡，等.新冠肺炎疫情极限R实时 (2015-07-24)[2020-07-28]https:/arxiv.org/abs/1610 预测模型).电子科技大学学报，2020,49(3：362-368. 05256. MEI Wenjuan,LIU Zhen,ZHU Jingyi,et al.Extreme IR [24]LIPTON Z C.A critical review of recurrent neural net-CONTENT/10.1101/2020.01.23.20018549V2. SHEN Mingwang, PENG Zhihang, XIAO Yanni, et al. Modeling the epidemic trend of the 2019 novel coronavir￾us outbreak in China[J]. The innovation, 2020, 1(3): 100048. [3] HARKO T, LOBO F S N, MAK M K. Exact analytical solutions of the Susceptible-Infected-Recovered (SIR) epi￾demic model and of the SIR model with equal death and birth rates[J]. Applied mathematics and computation, 2014, 236: 184–194. [4] KRÖGER M, SCHLICKEISER R. Analytical solution of the SIR-model for the temporal evolution of epidemics. Part A: time-independent reproduction factor[J]. Journal of pysics A, 2020(50): 505601. [5] LI M Y, MULDOWNEY J S. Global stability for the SEIR model in epidemiology[J]. Mathematical biosciences, 1995, 125(2): 155–164. [6] GODIO A, PACE F, VERGNANO A. SEIR modeling of the Italian epidemic of SARS-CoV-2 using computational swarm intelligence[J]. International journal of environ￾mental research and public health, 2020, 17(10): 3535. [7] WU J T, LEUNG K, LEUNG G M. Nowcasting and fore￾casting the potential domestic and international spread of the 2019-nCoV outbreak originating in Wuhan, China: a modelling study[J]. The lancet, 2020, 395(10225): 689–697. [8] YANG Zifeng, ZENG Zhiqi, WANG Ke, et al. Modified SEIR and AI prediction of the epidemics trend of COVID- 19 in China under public health interventions[J]. Journal of thoracic disease, 2020, 12(3): 165–174. [9] WALKER P, WHITTAKER C, WATSON O, et al. The global impact of COVID-19 and strategies for mitigation and suppression[EB/OL]. (2020−03−26)[2020−07−28] https://www.imperial.ac.uk/mrc-global-infectious-disease￾analysis/covid-19/report-12-global-impact-covid-19/. [10] 范如国, 王奕博, 罗明, 等. 基于 SEIR 的新冠肺炎传播 模型及拐点预测分析 [J]. 电子科技大学学报, 2020, 49(3): 369–374. FAN Ruguo, WANG Yibo, LUO Ming, et al. SEIR-based COVID-19 transmission model and inflection point pre￾diction analysis[J]. Journal of University of Electronic Science and Technology of China, 2020, 49(3): 369–374. [11] ARMOUR G C, BUFFA E S. A heuristic algorithm and simulation approach to relative location of facilities[J]. Management science, 1963, 9(2): 294–309. [12] 梅文娟, 刘震, 朱静怡, 等. 新冠肺炎疫情极限 IR 实时 预测模型 [J]. 电子科技大学学报, 2020, 49(3): 362–368. MEI Wenjuan, LIU Zhen, ZHU Jingyi, et al. Extreme IR [13] model for COVID-19 real-time forecasting[J]. Journal of University of Electronic Science and Technology of China, 2020, 49(3): 362–368. GUO Wei, XU Tao, TANG Keming. M-estimator-based online sequential extreme learning machine for predicting chaotic time series with outliers[J]. Neural computing and applications, 2017, 28(12): 4093–4110. [14] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceed￾ings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016, 770−778. [15] SIMONYAN K, ZISSERMAN A. Very deep convolu￾tional networks for large-scale image recognition[EB/OL]. (2015-04-10)[2020-07-28] http://arxiv.org/abs/1409.1556. [16] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Im￾ageNet classification with deep convolutional neural net￾works[C]//Proceedings of the 25th International Confer￾ence on Neural Information Processing Systems. Red Hook, NY, USA: Curran Associates Inc., 2012: 1097− 1105. [17] COLLOBERT R, WESTON J, BOTTOU L, et al. Natur￾al language processing (almost) from scratch[J]. The journal of machine learning research, 2011, 12: 2493–2537. [18] TAY Y, LUU A T, HUI S C. Compare, compress and propagate: enhancing neural architectures with alignment factorization for natural language inference[C]// Proceed￾ings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium, 2018: 1565−1575. [19] DEVLIN J, CHANG M W, LEE K, et al. BERT: Pre￾training of deep bidirectional transformers for language understanding[EB/OL]. (2019−05−24)[2020−07−28] http://arxiv.org/abs/1810.04805. [20] HINTON G, DENG Li, YU Dong, et al. Deep neural net￾works for acoustic modeling in speech recognition: the shared views of four research groups[J]. IEEE signal pro￾cessing magazine, 2012, 29(6): 82–97. [21] SAK H, SENIOR A, RAO K, et al. Fast and accurate re￾current neural network acoustic models for speech recog￾nition[EB/OL]. (2015−07−24)[2020−07−28] http://arxiv. org/abs/1507.06947. [22] XIONG W, DROPPO J, HUANG X, et al. Achieving hu￾man parity in conversational speech recognition[EB/OL]. (2015−07−24)[2020−07−28] https://arxiv.org/abs/1610. 05256. [23] [24] LIPTON Z C. A critical review of recurrent neural net- 第 3 期 甘雨，等：新冠肺炎疫情趋势预测模型 ·535·