CN113113155A - Infectious disease trend prediction method based on neural network and SEIR model - Google Patents

Infectious disease trend prediction method based on neural network and SEIR model Download PDF

Info

Publication number
CN113113155A
CN113113155A CN202110658591.1A CN202110658591A CN113113155A CN 113113155 A CN113113155 A CN 113113155A CN 202110658591 A CN202110658591 A CN 202110658591A CN 113113155 A CN113113155 A CN 113113155A
Authority
CN
China
Prior art keywords
patients
trend prediction
infection rate
epidemic situation
seir
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110658591.1A
Other languages
Chinese (zh)
Inventor
王建勇
章毅
甘雨
吴雨
庞博
吴宇杭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sichuan University
Original Assignee
Sichuan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sichuan University filed Critical Sichuan University
Priority to CN202110658591.1A priority Critical patent/CN113113155A/en
Publication of CN113113155A publication Critical patent/CN113113155A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明涉及人工智能预测领域，具体是一种基于神经网络与SEIR模型的传染病趋势预测方法，包括如下步骤：步骤1、获取数据集；步骤2、数据预处理；步骤3、构建由病毒传染率预测模块和疫情趋势预测模块构成的疫情趋势预测模型；步骤4、使用步骤2预处理的数据对疫情趋势预测模型进行训练，同时设置疫情趋势预测模型的损失函数和模型参数更新方式；步骤5、利用步骤1～步骤4训练好的疫情趋势预测模型对疫情趋势进行预测；该方法可使用较少的训练数据，对传染病疫情趋势进行有效的自动动态实时预测，且预测过程无需人为干预。

Figure 202110658591

The invention relates to the field of artificial intelligence prediction, in particular to a method for predicting an infectious disease trend based on a neural network and an SEIR model, comprising the following steps: step 1, acquiring a data set; step 2, data preprocessing; step 3, constructing a virus-infected disease The epidemic trend prediction model composed of the rate prediction module and the epidemic trend prediction module; Step 4, use the data preprocessed in Step 2 to train the epidemic trend prediction model, and set the loss function and model parameter update method of the epidemic trend prediction model at the same time; Step 5 . Use the epidemic trend prediction model trained in steps 1 to 4 to predict the epidemic trend; this method can use less training data to effectively predict the epidemic trend of infectious diseases automatically and dynamically in real time, and the prediction process does not require human intervention.

Figure 202110658591

Description

一种基于神经网络与SEIR模型的传染病趋势预测方法An Infectious Disease Trend Prediction Method Based on Neural Network and SEIR Model

技术领域technical field

本发明涉及人工智能预测领域，具体是指一种基于神经网络与SEIR模型的传染病趋势预测方法。The invention relates to the field of artificial intelligence prediction, in particular to an infectious disease trend prediction method based on a neural network and an SEIR model.

背景技术Background technique

对传染病疫情的预测，近年来随着机器学习的发展，预测方法可分为未使用机器学习方法的传统方法和使用了机器学习的方法，传统方法使用传统的静态传染病数学模型（如：SIR模型、SEIR模型等）对疫情传播情况进行建模和预测。With the development of machine learning in recent years, prediction methods for infectious disease outbreaks can be divided into traditional methods without machine learning methods and methods using machine learning. Traditional methods use traditional static infectious disease mathematical models (such as: SIR model, SEIR model, etc.) to model and predict the spread of the epidemic.

在传统的传染病疫情趋势预测方法中，预测模型中的参数无法自适应，从而无法实现动态预测，且模型参数凭借经验设置，人工干预的影响较大；在使用了机器学习的方法中，或是没有考虑到数据中的时序信息，或是没有对疫情中的各类人群进行总体把握，难以对疫情趋势情况进行全面预测。In the traditional epidemic trend prediction method of infectious diseases, the parameters in the prediction model cannot be adapted to achieve dynamic prediction, and the model parameters are set by experience, and the impact of manual intervention is greater; in the method using machine learning, or It is difficult to comprehensively predict the trend of the epidemic because the time series information in the data is not considered, or there is no overall grasp of the various groups of people in the epidemic.

发明内容SUMMARY OF THE INVENTION

基于以上问题，本发明提供了一种基于神经网络与SEIR模型的传染病趋势预测方法，该方法可使用较少的训练数据，对传染病疫情趋势进行有效的自动动态实时预测，且预测过程无需人为干预。Based on the above problems, the present invention provides a method for predicting the trend of infectious diseases based on neural network and SEIR model. The method can use less training data to perform effective automatic dynamic real-time prediction of the trend of infectious diseases, and the prediction process does not require Human intervention.

为解决以上技术问题，本发明采用的技术方案如下：For solving the above technical problems, the technical scheme adopted in the present invention is as follows:

一种基于神经网络与SEIR模型的传染病趋势预测方法，包括如下步骤：An infectious disease trend prediction method based on neural network and SEIR model, comprising the following steps:

步骤1、获取数据集；Step 1. Obtain the dataset;

步骤2、数据预处理；Step 2, data preprocessing;

步骤3、构建由病毒传染率预测模块和疫情趋势预测模块构成的疫情趋势预测模型；Step 3. Construct an epidemic trend prediction model composed of a virus infection rate prediction module and an epidemic trend prediction module;

步骤4、使用步骤2预处理的数据对疫情趋势预测模型进行训练，同时设置疫情趋势预测模型的损失函数和模型参数更新方式；Step 4. Use the data preprocessed in Step 2 to train the epidemic trend prediction model, and set the loss function and model parameter update method of the epidemic trend prediction model at the same time;

步骤5、利用步骤1～步骤4训练好的疫情趋势预测模型对疫情趋势进行预测。Step 5. Use the epidemic trend prediction model trained in steps 1 to 4 to predict the epidemic trend.

进一步，所述步骤3中，预处理后的数据输入病毒传染率预测模块，并先后经过一个LSTM层、一个全连接层和一个非线性变换层，LSTM层将含有时序信息的特征输出，随后全连接层对特征进行整合，使用SoftPlus作为激活函数，最后输出预测某时刻确诊患者和潜伏期患者的病毒传染率。Further, in the step 3, the preprocessed data is input into the virus infection rate prediction module, and successively passes through an LSTM layer, a fully connected layer and a nonlinear transformation layer. The LSTM layer outputs the features containing time series information, and then the full The connection layer integrates the features, uses SoftPlus as the activation function, and finally outputs the predicted virus infection rate of confirmed patients and incubation period patients at a certain time.

进一步，所述使用SoftPlus作为激活函数的公式为：

Figure 982173DEST_PATH_IMAGE001
，其中exp为非线性函数。Further, the formula for using SoftPlus as the activation function is:
Figure 982173DEST_PATH_IMAGE001
, where exp is a nonlinear function.

进一步，所述步骤3中，预测某时刻确诊患者和潜伏期患者的病毒传染率的公式为：Further, in the step 3, the formula for predicting the virus infection rate of a confirmed patient and an incubation period patient at a certain moment is:

Figure 768732DEST_PATH_IMAGE002
，
Figure 768732DEST_PATH_IMAGE002
,

其中，

Figure 828961DEST_PATH_IMAGE003
表示确诊患者的病毒传染率，
Figure 943548DEST_PATH_IMAGE004
表示潜伏期患者的病毒传染率，
Figure 724422DEST_PATH_IMAGE005
表示
Figure 176874DEST_PATH_IMAGE006
时刻确诊患者的病毒传染率，
Figure 893157DEST_PATH_IMAGE007
表示
Figure 495040DEST_PATH_IMAGE006
时刻潜伏期患者的病毒传染率，
Figure 204239DEST_PATH_IMAGE008
表示
Figure 575177DEST_PATH_IMAGE006
时刻病毒传染率的缩放比例，
Figure 462362DEST_PATH_IMAGE009
表示
Figure 285961DEST_PATH_IMAGE006
时刻疫情防控措施的强度，
Figure 533272DEST_PATH_IMAGE010
表示
Figure 758717DEST_PATH_IMAGE006
时刻潜伏期患者的病毒传染率相较于确诊患者的病毒传染率的倍数。in,
Figure 828961DEST_PATH_IMAGE003
represents the infection rate of the virus among confirmed patients,
Figure 943548DEST_PATH_IMAGE004
Indicates the virus infection rate of patients in the incubation period,
Figure 724422DEST_PATH_IMAGE005
express
Figure 176874DEST_PATH_IMAGE006
The virus infection rate of patients diagnosed at any time,
Figure 893157DEST_PATH_IMAGE007
express
Figure 495040DEST_PATH_IMAGE006
The virus infection rate of patients during the incubation period at any time,
Figure 204239DEST_PATH_IMAGE008
express
Figure 575177DEST_PATH_IMAGE006
The scaling ratio of the virus infection rate at the moment,
Figure 462362DEST_PATH_IMAGE009
express
Figure 285961DEST_PATH_IMAGE006
The intensity of epidemic prevention and control measures at any time,
Figure 533272DEST_PATH_IMAGE010
express
Figure 758717DEST_PATH_IMAGE006
The virus infection rate of patients in the incubation period at any time is the multiple of the virus infection rate of confirmed patients.

进一步，所述步骤3中，将病毒传染率预测模块的输出结果输入疫情趋势预测模块，并经过一个SEIR模型层，输出对疫情趋势的预测。Further, in the step 3, the output result of the virus infection rate prediction module is input into the epidemic trend prediction module, and a SEIR model layer is passed to output the prediction of the epidemic trend.

进一步，所述步骤3中，疫情趋势的预测公式如下：Further, in the step 3, the prediction formula of the epidemic trend is as follows:

Figure 521530DEST_PATH_IMAGE011
，
Figure 521530DEST_PATH_IMAGE011
,

其中，

Figure 98005DEST_PATH_IMAGE012
表示未被感染的人数，
Figure 634159DEST_PATH_IMAGE013
表示潜伏期患者人数，
Figure 714111DEST_PATH_IMAGE014
表示确诊患者人数，
Figure 457945DEST_PATH_IMAGE015
表示病毒移除者人数，
Figure 256136DEST_PATH_IMAGE016
表示在
Figure 595982DEST_PATH_IMAGE006
时刻时未被感染的人数，
Figure 717391DEST_PATH_IMAGE017
表示在
Figure 507492DEST_PATH_IMAGE006
时刻时潜伏期患者人数，
Figure 402767DEST_PATH_IMAGE018
表示在
Figure 936517DEST_PATH_IMAGE006
时刻时确诊患者人数，
Figure 853044DEST_PATH_IMAGE019
表示在
Figure 876364DEST_PATH_IMAGE006
时刻时病毒移除者人数，
Figure 773782DEST_PATH_IMAGE020
表示确诊患者的病毒传染率，
Figure 845643DEST_PATH_IMAGE021
表示潜伏期患者的病毒传染率，
Figure 630059DEST_PATH_IMAGE022
表示潜伏期患者转化为确诊患者的概率，
Figure 496384DEST_PATH_IMAGE023
表示确诊患者转化为病毒移除者的概率，
Figure 615519DEST_PATH_IMAGE024
、
Figure 491071DEST_PATH_IMAGE025
、
Figure 395573DEST_PATH_IMAGE026
、
Figure 432799DEST_PATH_IMAGE027
分别表示
Figure 307739DEST_PATH_IMAGE028
时刻
Figure 721403DEST_PATH_IMAGE012
、
Figure 480411DEST_PATH_IMAGE013
、
Figure 609910DEST_PATH_IMAGE014
、
Figure 579003DEST_PATH_IMAGE015
的预测值，
Figure 671724DEST_PATH_IMAGE029
，表示人口总数。in,
Figure 98005DEST_PATH_IMAGE012
represents the number of uninfected persons,
Figure 634159DEST_PATH_IMAGE013
represents the number of patients in the incubation period,
Figure 714111DEST_PATH_IMAGE014
represents the number of confirmed patients,
Figure 457945DEST_PATH_IMAGE015
represents the number of virus removers,
Figure 256136DEST_PATH_IMAGE016
expressed in
Figure 595982DEST_PATH_IMAGE006
the number of people who are not infected at any time,
Figure 717391DEST_PATH_IMAGE017
expressed in
Figure 507492DEST_PATH_IMAGE006
The number of patients in the incubation period at any time,
Figure 402767DEST_PATH_IMAGE018
expressed in
Figure 936517DEST_PATH_IMAGE006
The number of confirmed patients at any time,
Figure 853044DEST_PATH_IMAGE019
expressed in
Figure 876364DEST_PATH_IMAGE006
the number of virus removers at any time,
Figure 773782DEST_PATH_IMAGE020
represents the infection rate of the virus among confirmed patients,
Figure 845643DEST_PATH_IMAGE021
Indicates the virus infection rate of patients in the incubation period,
Figure 630059DEST_PATH_IMAGE022
represents the probability that a patient in the incubation period will be converted into a confirmed patient,
Figure 496384DEST_PATH_IMAGE023
represents the probability of converting a confirmed patient into a virus remover,
Figure 615519DEST_PATH_IMAGE024
,
Figure 491071DEST_PATH_IMAGE025
,
Figure 395573DEST_PATH_IMAGE026
,
Figure 432799DEST_PATH_IMAGE027
Respectively
Figure 307739DEST_PATH_IMAGE028
time
Figure 721403DEST_PATH_IMAGE012
,
Figure 480411DEST_PATH_IMAGE013
,
Figure 609910DEST_PATH_IMAGE014
,
Figure 579003DEST_PATH_IMAGE015
the predicted value,
Figure 671724DEST_PATH_IMAGE029
, representing the total population.

进一步，所述步骤4中，选择平均平方误差作为训练时的损失函数。Further, in the step 4, the average squared error is selected as the loss function during training.

进一步，所述步骤4中，模型参数更新方式设置为学习率为0.005，一个完整的训练集为一个学习批次，学习迭代总次数为5000，网络训练过程针对每一个学习批次进行一次参数更新，根据疫情趋势预测模块输出与真实标签计算学习误差，并采用BP算法利用误差对网络参数进行更新，每一次迭代学习完成后，疫情趋势预测模型都会计算当前的预测误差并与历史最小误差作比较，若当前预测误差小于历史最小误差，则保存当前疫情趋势预测模型，并将历史最小误差更新为当前误差，之后继续训练，直到达到学习迭代总次数。Further, in the step 4, the model parameter update method is set to a learning rate of 0.005, a complete training set is a learning batch, the total number of learning iterations is 5000, and the network training process performs a parameter update for each learning batch. , calculate the learning error according to the output of the epidemic trend prediction module and the real label, and use the BP algorithm to use the error to update the network parameters. After each iteration learning is completed, the epidemic trend prediction model will calculate the current prediction error and compare it with the historical minimum error , if the current prediction error is less than the historical minimum error, save the current epidemic trend prediction model, update the historical minimum error to the current error, and continue training until the total number of learning iterations is reached.

与现有技术相比，本发明的有益效果是：Compared with the prior art, the beneficial effects of the present invention are:

1.本发明对传染病病毒的传染率及疫情的趋势发展可实现自动动态预测，减少了人为操作，降低人工干预带来的影响；1. The present invention can realize automatic dynamic prediction to the infectious rate of infectious disease virus and the trend development of epidemic situation, reduce manual operation, and reduce the impact of manual intervention;

2.本发明使用了疫情数据中的时序信息，结合历史信息与当前信息综合预测；2. The present invention uses the time series information in the epidemic data, combined with historical information and current information for comprehensive prediction;

3.对疫情中的各类人群进行预测，把握疫情总体发展趋势。3. Predict various groups of people in the epidemic situation and grasp the overall development trend of the epidemic situation.

附图说明Description of drawings

图1为本实施例的流程图；Fig. 1 is the flow chart of this embodiment;

图2为本实施例中疫情趋势预测模型的框架图。FIG. 2 is a frame diagram of the epidemic trend prediction model in this embodiment.

具体实施方式Detailed ways

下面结合附图对本发明作进一步的说明。本发明的实施方式包括但不限于下列实施例。The present invention will be further described below in conjunction with the accompanying drawings. Embodiments of the present invention include, but are not limited to, the following examples.

如图1所示的一种基于神经网络与SEIR模型的传染病趋势预测方法，包括如下步骤：As shown in Figure 1, an infectious disease trend prediction method based on neural network and SEIR model includes the following steps:

步骤1、获取数据集；Step 1. Obtain the dataset;

步骤2、数据预处理；Step 2, data preprocessing;

步骤3、如图2所示，构建由病毒传染率预测模块和疫情趋势预测模块构成的疫情趋势预测模型；Step 3. As shown in Figure 2, construct an epidemic trend prediction model consisting of a virus infection rate prediction module and an epidemic trend prediction module;

步骤4、使用步骤2预处理的数据对疫情趋势预测模型进行训练，同时设置疫情趋势预测模型的损失函数和模型参数更新方式；Step 4. Use the data preprocessed in Step 2 to train the epidemic trend prediction model, and set the loss function and model parameter update method of the epidemic trend prediction model at the same time;

步骤5、利用步骤1～步骤4训练好的疫情趋势预测模型对疫情趋势进行预测。Step 5. Use the epidemic trend prediction model trained in steps 1 to 4 to predict the epidemic trend.

进一步的是，步骤1中，数据集包括疑似病例数据、确诊病例数据和移除病例数据。Further, in step 1, the data set includes data of suspected cases, data of confirmed cases and data of removed cases.

进一步的是，步骤2中，将第

Figure 409873DEST_PATH_IMAGE030
至
Figure 179115DEST_PATH_IMAGE030
+2天的疑似病例数据、现存确诊病例数据、移除病例数据作为输入，第
Figure 635504DEST_PATH_IMAGE031
天的疑似病例数据、现存确诊病例数据、移除病例数据作为对应标签来进行数据整理，共得到62份数据，然后将这62份数据按训练集规模进一步整理出4个数据集：Data_10、Data_20、Data_30、Data_40；其中Data_10划分规则为: 前10份数据为训练集，第11份输入数据为测试集的初始输入数据，后52份数据的标签为测试集的标签；Data_20、Data_30、Data_40划分规则同理。Further, in step 2, the
Figure 409873DEST_PATH_IMAGE030
to
Figure 179115DEST_PATH_IMAGE030
+2 days of suspected case data, existing confirmed case data, removed case data as input, the first
Figure 635504DEST_PATH_IMAGE031
Data of suspected cases, existing confirmed case data, and removed case data are used as corresponding labels for data sorting, and a total of 62 pieces of data are obtained, and then these 62 pieces of data are further sorted into 4 data sets according to the size of the training set: Data_10, Data_20 , Data_30, Data_40; where the Data_10 division rule is: the first 10 pieces of data are the training set, the 11th input data is the initial input data of the test set, and the labels of the last 52 pieces of data are the labels of the test set; Data_20, Data_30, Data_40 are divided The rules are the same.

进一步的是，病毒传染率预测模块构建原理如下：Further, the construction principle of the virus infection rate prediction module is as follows:

本实施例中，对确诊患者和潜伏期患者各创建了病毒传染率

Figure 266336DEST_PATH_IMAGE032
和
Figure 858992DEST_PATH_IMAGE033
，同时，病毒传染率后期的变化情况与疫情前期的防控措施和诊治手段息息相关，预测病毒传染率需要根据历史信息与当前信息共同分析，因此病毒传染率的预测是一类时序预测问题，深度循环神经网络中的LSTM具有优秀的时序学习能力，能存储过往数据中的信息并将其与当前数据中的信息结合，因此基于LSTM与
Figure 799135DEST_PATH_IMAGE032
和
Figure 477241DEST_PATH_IMAGE033
的数学模型设计了病毒传染率预测模块；In this example, the virus infection rates were created for confirmed patients and incubation period patients respectively.
Figure 266336DEST_PATH_IMAGE032
and
Figure 858992DEST_PATH_IMAGE033
At the same time, the change of the virus infection rate in the later stage is closely related to the prevention and control measures and diagnosis and treatment methods in the early stage of the epidemic. Predicting the virus infection rate needs to be analyzed based on historical information and current information. Therefore, the prediction of the virus infection rate is a kind of time series prediction problem. The LSTM in the recurrent neural network has excellent time-series learning ability, can store the information in the past data and combine it with the information in the current data, so based on LSTM and
Figure 799135DEST_PATH_IMAGE032
and
Figure 477241DEST_PATH_IMAGE033
The mathematical model of the virus infection rate prediction module was designed;

本实施例中，病毒传染率预测模块包括一个LSTM层、一个全连接层和一个非线性变换层，预处理后的数据输入病毒传染率预测模块后，LSTM层将含有时序信息的特征输出，随后全连接层对特征进行整合，使用SoftPlus作为激活函数，公式为

Figure 911764DEST_PATH_IMAGE034
，其中exp为非线性函数。以此增强网络的非线性表达能力，最后输出预测某时刻确诊患者和潜伏期患者的病毒传染率；In this embodiment, the virus infection rate prediction module includes an LSTM layer, a fully connected layer, and a nonlinear transformation layer. After the preprocessed data is input into the virus infection rate prediction module, the LSTM layer will output features containing time series information, and then The fully connected layer integrates the features and uses SoftPlus as the activation function, the formula is
Figure 911764DEST_PATH_IMAGE034
, where exp is a nonlinear function. In this way, the nonlinear expression ability of the network is enhanced, and the final output predicts the virus infection rate of diagnosed patients and incubation period patients at a certain time;

本实施例中，预测某时刻确诊患者和潜伏期患者的病毒传染率的公式为：In this embodiment, the formula for predicting the virus infection rate of a confirmed patient and an incubation period patient at a certain time is:

Figure 624505DEST_PATH_IMAGE035
，
Figure 624505DEST_PATH_IMAGE035
,

其中，

Figure 726761DEST_PATH_IMAGE003
表示确诊患者的病毒传染率，
Figure 157742DEST_PATH_IMAGE004
表示潜伏期患者的病毒传染率，
Figure 130377DEST_PATH_IMAGE005
表示
Figure 697625DEST_PATH_IMAGE006
时刻确诊患者的病毒传染率，
Figure 979571DEST_PATH_IMAGE007
表示
Figure 304373DEST_PATH_IMAGE006
时刻潜伏期患者的病毒传染率，
Figure 205333DEST_PATH_IMAGE008
表示
Figure 17300DEST_PATH_IMAGE006
时刻病毒传染率的缩放比例，
Figure 345513DEST_PATH_IMAGE009
表示
Figure 360873DEST_PATH_IMAGE006
时刻疫情防控措施的强度，
Figure 799945DEST_PATH_IMAGE010
表示
Figure 466418DEST_PATH_IMAGE006
时刻潜伏期患者的病毒传染率相较于确诊患者的病毒传染率的倍数。in,
Figure 726761DEST_PATH_IMAGE003
represents the infection rate of the virus among confirmed patients,
Figure 157742DEST_PATH_IMAGE004
Indicates the virus infection rate of patients in the incubation period,
Figure 130377DEST_PATH_IMAGE005
express
Figure 697625DEST_PATH_IMAGE006
The virus infection rate of patients diagnosed at any time,
Figure 979571DEST_PATH_IMAGE007
express
Figure 304373DEST_PATH_IMAGE006
The virus infection rate of patients during the incubation period at any time,
Figure 205333DEST_PATH_IMAGE008
express
Figure 17300DEST_PATH_IMAGE006
The scaling ratio of the virus infection rate at the moment,
Figure 345513DEST_PATH_IMAGE009
express
Figure 360873DEST_PATH_IMAGE006
The intensity of epidemic prevention and control measures at any time,
Figure 799945DEST_PATH_IMAGE010
express
Figure 466418DEST_PATH_IMAGE006
The virus infection rate of patients in the incubation period at any time is the multiple of the virus infection rate of confirmed patients.

进一步的是，疫情趋势预测模块构建原理如下:Further, the construction principle of the epidemic trend prediction module is as follows:

将病毒传染率预测模块的输出结果

Figure 965533DEST_PATH_IMAGE032
和
Figure 468190DEST_PATH_IMAGE033
输入疫情趋势预测模块，并经过一个SEIR模型层，输出对疫情趋势的预测。The output of the virus infection rate prediction module
Figure 965533DEST_PATH_IMAGE032
and
Figure 468190DEST_PATH_IMAGE033
Input the epidemic trend prediction module, and go through a SEIR model layer to output the prediction of the epidemic trend.

本实施例中，疫情趋势的预测公式如下：In this embodiment, the prediction formula of the epidemic trend is as follows:

Figure 710952DEST_PATH_IMAGE011
，
Figure 710952DEST_PATH_IMAGE011
,

其中，

Figure 234862DEST_PATH_IMAGE012
表示未被感染的人数，
Figure 904878DEST_PATH_IMAGE013
表示潜伏期患者人数，
Figure 629251DEST_PATH_IMAGE014
表示确诊患者人数，
Figure 675704DEST_PATH_IMAGE015
表示病毒移除者人数，
Figure 316770DEST_PATH_IMAGE036
表示在
Figure 157687DEST_PATH_IMAGE006
时刻时未被感染的人数，
Figure 369357DEST_PATH_IMAGE017
表示在
Figure 953922DEST_PATH_IMAGE006
时刻时潜伏期患者人数，
Figure 246232DEST_PATH_IMAGE037
表示在
Figure 133417DEST_PATH_IMAGE006
时刻时确诊患者人数，
Figure 222595DEST_PATH_IMAGE019
表示在
Figure 469906DEST_PATH_IMAGE006
时刻时病毒移除者人数，
Figure 960930DEST_PATH_IMAGE020
表示确诊患者的病毒传染率，
Figure 19016DEST_PATH_IMAGE021
表示潜伏期患者的病毒传染率，
Figure 329912DEST_PATH_IMAGE022
表示潜伏期患者转化为确诊患者的概率，
Figure 118263DEST_PATH_IMAGE023
表示确诊患者转化为病毒移除者的概率，
Figure 463794DEST_PATH_IMAGE038
、
Figure 692781DEST_PATH_IMAGE025
、
Figure 490973DEST_PATH_IMAGE026
、
Figure 345665DEST_PATH_IMAGE027
分别表示
Figure 545703DEST_PATH_IMAGE028
时刻
Figure 945591DEST_PATH_IMAGE012
、
Figure 231079DEST_PATH_IMAGE013
、
Figure 686200DEST_PATH_IMAGE014
、
Figure 616110DEST_PATH_IMAGE015
的预测值，
Figure 311533DEST_PATH_IMAGE029
，表示人口总数。in,
Figure 234862DEST_PATH_IMAGE012
represents the number of uninfected persons,
Figure 904878DEST_PATH_IMAGE013
represents the number of patients in the incubation period,
Figure 629251DEST_PATH_IMAGE014
represents the number of confirmed patients,
Figure 675704DEST_PATH_IMAGE015
represents the number of virus removers,
Figure 316770DEST_PATH_IMAGE036
expressed in
Figure 157687DEST_PATH_IMAGE006
the number of people who are not infected at any time,
Figure 369357DEST_PATH_IMAGE017
expressed in
Figure 953922DEST_PATH_IMAGE006
The number of patients in the incubation period at any time,
Figure 246232DEST_PATH_IMAGE037
expressed in
Figure 133417DEST_PATH_IMAGE006
The number of confirmed patients at any time,
Figure 222595DEST_PATH_IMAGE019
expressed in
Figure 469906DEST_PATH_IMAGE006
the number of virus removers at any time,
Figure 960930DEST_PATH_IMAGE020
represents the infection rate of the virus among confirmed patients,
Figure 19016DEST_PATH_IMAGE021
Indicates the virus infection rate of patients in the incubation period,
Figure 329912DEST_PATH_IMAGE022
represents the probability that a patient in the incubation period will be converted into a confirmed patient,
Figure 118263DEST_PATH_IMAGE023
represents the probability of converting a confirmed patient into a virus remover,
Figure 463794DEST_PATH_IMAGE038
,
Figure 692781DEST_PATH_IMAGE025
,
Figure 490973DEST_PATH_IMAGE026
,
Figure 345665DEST_PATH_IMAGE027
Respectively
Figure 545703DEST_PATH_IMAGE028
time
Figure 945591DEST_PATH_IMAGE012
,
Figure 231079DEST_PATH_IMAGE013
,
Figure 686200DEST_PATH_IMAGE014
,
Figure 616110DEST_PATH_IMAGE015
the predicted value,
Figure 311533DEST_PATH_IMAGE029
, representing the total population.

进一步的是，所述步骤4中，损失函数用于衡量预测结果与真实情况的差异水平，因此，选择结果直接对模型训练的效果产生影响，本实施例中，选择平均平方误差作为训练时的损失函数，同时考虑到现实中各类数据收集的难易性、准确性以及重要性，对

Figure 208951DEST_PATH_IMAGE013
、
Figure 280812DEST_PATH_IMAGE014
、
Figure 65229DEST_PATH_IMAGE015
数据分别计算MSE，并将这三类MSE进行加权和作为网络的整体学习误差，网络的整体学习误差如下：Further, in the step 4, the loss function is used to measure the difference between the predicted result and the real situation. Therefore, the selection result directly affects the effect of model training. In this embodiment, the average squared error is selected as the training value. Loss function, taking into account the difficulty, accuracy and importance of various data collection in reality,
Figure 208951DEST_PATH_IMAGE013
,
Figure 280812DEST_PATH_IMAGE014
,
Figure 65229DEST_PATH_IMAGE015
The MSE is calculated separately for the data, and the weighted sum of these three types of MSE is used as the overall learning error of the network. The overall learning error of the network is as follows:

Figure 197133DEST_PATH_IMAGE039
，
Figure 197133DEST_PATH_IMAGE039
,

其中，

Figure 53618DEST_PATH_IMAGE040
、
Figure 929170DEST_PATH_IMAGE041
、
Figure 568093DEST_PATH_IMAGE042
分别由
Figure 870898DEST_PATH_IMAGE013
、
Figure 680591DEST_PATH_IMAGE014
、
Figure 94255DEST_PATH_IMAGE015
数据计算出的MSE，MSE的计算方法如下：in,
Figure 53618DEST_PATH_IMAGE040
,
Figure 929170DEST_PATH_IMAGE041
,
Figure 568093DEST_PATH_IMAGE042
respectively by
Figure 870898DEST_PATH_IMAGE013
,
Figure 680591DEST_PATH_IMAGE014
,
Figure 94255DEST_PATH_IMAGE015
The MSE calculated from the data, the calculation method of MSE is as follows:

Figure 102531DEST_PATH_IMAGE043
，
Figure 102531DEST_PATH_IMAGE043
,

其中，

Figure 576238DEST_PATH_IMAGE044
为
Figure 420697DEST_PATH_IMAGE006
时刻的真实值，
Figure 372473DEST_PATH_IMAGE045
为
Figure 235255DEST_PATH_IMAGE006
时刻的预测值，
Figure 879863DEST_PATH_IMAGE046
为总时长。in,
Figure 576238DEST_PATH_IMAGE044
for
Figure 420697DEST_PATH_IMAGE006
the true value of the moment,
Figure 372473DEST_PATH_IMAGE045
for
Figure 235255DEST_PATH_IMAGE006
the predicted value at the moment,
Figure 879863DEST_PATH_IMAGE046
for the total duration.

进一步的是，步骤4中，网络设置

Figure 211618DEST_PATH_IMAGE047
，
Figure 967085DEST_PATH_IMAGE048
，模型参数更新方式设置为学习率为0.005，一个完整的训练集为一个学习批次，学习迭代总次数为5000，网络训练过程针对每一个学习批次进行一次参数更新，根据疫情趋势预测模块输出与真实标签计算学习误差，并采用BP算法利用误差对网络参数进行更新，每一次迭代学习完成后，疫情趋势预测模型都会计算当前的预测误差并与历史最小误差作比较，若当前预测误差小于历史最小误差，则保存当前疫情趋势预测模型，并将历史最小误差更新为当前误差，之后继续训练，直到达到学习迭代总次数。Further, in step 4, network settings
Figure 211618DEST_PATH_IMAGE047
,
Figure 967085DEST_PATH_IMAGE048
, the model parameter update method is set to the learning rate of 0.005, a complete training set is a learning batch, and the total number of learning iterations is 5000. The network training process performs a parameter update for each learning batch, and predicts the module output according to the epidemic trend. Calculate the learning error with the real label, and use the BP algorithm to use the error to update the network parameters. After each iteration learning is completed, the epidemic trend prediction model will calculate the current prediction error and compare it with the historical minimum error. If the current prediction error is smaller than the historical If the minimum error is reached, the current epidemic trend prediction model is saved, and the historical minimum error is updated to the current error, and then the training continues until the total number of learning iterations is reached.

进一步的是，步骤5中，由于预测是对未来一段时间内的疫情趋势进行预测，所以当前没有任何未来的疫情数据，因而预测时输入疫情趋势预测模型的只有一组初始数据，其包含了连续三天的

Figure 761339DEST_PATH_IMAGE013
、
Figure 186636DEST_PATH_IMAGE014
、
Figure 130321DEST_PATH_IMAGE015
数据，一天为一个预测周期，疫情趋势预测模型对每一组输入预测出下一天的
Figure 814112DEST_PATH_IMAGE013
、
Figure 526853DEST_PATH_IMAGE014
、
Figure 388630DEST_PATH_IMAGE015
数据，并将预测结果与输入数据中的后两天数据结合，组成新的输入数据，以此继续预测后一天的疫情情况，直至达到预测的总周期。Further, in step 5, since the prediction is to predict the epidemic trend in the future, there is currently no future epidemic data, so only a set of initial data is input into the epidemic trend prediction model during prediction, which includes continuous data. three days
Figure 761339DEST_PATH_IMAGE013
,
Figure 186636DEST_PATH_IMAGE014
,
Figure 130321DEST_PATH_IMAGE015
Data, one day is a prediction cycle, and the epidemic trend prediction model predicts the next day's
Figure 814112DEST_PATH_IMAGE013
,
Figure 526853DEST_PATH_IMAGE014
,
Figure 388630DEST_PATH_IMAGE015
data, and combine the prediction results with the data of the next two days in the input data to form new input data, so as to continue to predict the epidemic situation of the next day until the total period of prediction is reached.

如上即为本发明的实施例。上述实施例以及实施例中的具体参数仅是为了清楚表述发明人的发明验证过程，并非用以限制本发明的专利保护范围，本发明的专利保护范围仍然以其权利要求书为准，凡是运用本发明的说明书及附图内容所作的等同结构变化，同理均应包含在本发明的保护范围内。The above is an embodiment of the present invention. The above examples and the specific parameters in the examples are only to clearly describe the inventor's invention verification process, not to limit the scope of the patent protection of the present invention. The scope of the patent protection of the present invention is still based on the claims. Equivalent structural changes made in the contents of the description and drawings of the present invention shall be included within the protection scope of the present invention.

Claims (8)

1. An infectious disease trend prediction method based on a neural network and an SEIR model is characterized by comprising the following steps:
step 1, acquiring a data set;
step 2, preprocessing data;
step 3, constructing an epidemic situation trend prediction model consisting of a virus infection rate prediction module and an epidemic situation trend prediction module;
step 4, training the epidemic situation trend prediction model by using the data preprocessed in the step 2, and setting a loss function and a model parameter updating mode of the epidemic situation trend prediction model;
and 5, predicting the epidemic situation trend by using the epidemic situation trend prediction model trained in the steps 1 to 4.
2. An infectious disease trend prediction method based on neural networks and SEIR models as claimed in claim 1, wherein: in the step 3, the preprocessed data is input into a virus infection rate prediction module and sequentially passes through an LSTM layer, a full connection layer and a nonlinear transformation layer, the LSTM layer outputs the characteristics containing the time sequence information, then the full connection layer integrates the characteristics, and finally the virus infection rates of the confirmed patients and the latent patients at a certain moment are output and predicted by using SoftPlus as an activation function.
3. An infectious disease trend prediction method based on neural networks and SEIR models as claimed in claim 2, wherein: the formula using SoftPlus as the activation function is:
Figure 480728DEST_PATH_IMAGE001
where exp is a non-linear function.
4. An infectious disease trend prediction method based on neural networks and SEIR models as claimed in claim 3, wherein: in step 3, the formula for predicting the virus infection rates of the confirmed patients and the latent patients at a certain time is as follows:
Figure 457912DEST_PATH_IMAGE002
，
wherein,
Figure 119837DEST_PATH_IMAGE003
indicating the viral infection rate of the diagnosed patient,
Figure 789853DEST_PATH_IMAGE004
indicating the viral infection rate of the patients in the latent stage,
Figure 655172DEST_PATH_IMAGE005
to represent
Figure 436046DEST_PATH_IMAGE006
The virus infection rate of the patient is diagnosed at any moment,
Figure 952478DEST_PATH_IMAGE007
to represent
Figure 793395DEST_PATH_IMAGE006
The viral infection rate of patients in the time incubation period,
Figure 146010DEST_PATH_IMAGE008
to represent
Figure 464996DEST_PATH_IMAGE006
The scaling of the infection rate of the virus at the moment,
Figure 835935DEST_PATH_IMAGE009
to represent
Figure 847753DEST_PATH_IMAGE006
The intensity of the epidemic situation prevention and control measures,
Figure 419155DEST_PATH_IMAGE011
to represent
Figure 807411DEST_PATH_IMAGE006
The viral infection rate of patients with time-latent phase is a multiple compared to the viral infection rate of patients with confirmed diagnosis.
5. An infectious disease trend prediction method based on neural networks and SEIR models as claimed in claim 2, wherein: and in the step 3, the output result of the virus infection rate prediction module is input into an epidemic situation trend prediction module and is output for predicting the epidemic situation trend through an SEIR model layer.
6. An infectious disease trend prediction method based on neural networks and SEIR models as claimed in claim 5, wherein: in the step 3, the prediction formula of the epidemic situation trend is as follows:
Figure 32856DEST_PATH_IMAGE012
，
wherein,
Figure 215576DEST_PATH_IMAGE014
indicates the number of people who are not infected,
Figure 542783DEST_PATH_IMAGE015
the number of patients in the latent period is shown,
Figure 469151DEST_PATH_IMAGE016
the number of patients who have been diagnosed is indicated,
Figure 549102DEST_PATH_IMAGE017
indicating the number of virus removers,
Figure 168302DEST_PATH_IMAGE019
is shown in
Figure 717227DEST_PATH_IMAGE006
The number of people not infected at that moment,
Figure 916127DEST_PATH_IMAGE020
is shown in
Figure 116164DEST_PATH_IMAGE006
The number of patients in the latent period at the moment,
Figure 906265DEST_PATH_IMAGE022
is shown in
Figure 926174DEST_PATH_IMAGE006
The number of patients can be diagnosed at any time,
Figure 210656DEST_PATH_IMAGE023
is shown in
Figure 265200DEST_PATH_IMAGE006
The number of virus removers at any time,
Figure 960623DEST_PATH_IMAGE024
indicating the viral infection rate of the diagnosed patient,
Figure 733407DEST_PATH_IMAGE025
indicating the viral infection rate of the patients in the latent stage,
Figure 553071DEST_PATH_IMAGE026
indicating the probability of a latent patient transforming into a diagnosed patient,
Figure 462121DEST_PATH_IMAGE027
representing the probability of a diagnosed patient transforming into a virus remover,
Figure 594025DEST_PATH_IMAGE029
、
Figure 322947DEST_PATH_IMAGE030
、
Figure 214811DEST_PATH_IMAGE031
、
Figure 243946DEST_PATH_IMAGE032
respectively represent
Figure 281173DEST_PATH_IMAGE033
Time of day
Figure 28549DEST_PATH_IMAGE014
、
Figure 927366DEST_PATH_IMAGE015
、
Figure 811008DEST_PATH_IMAGE016
、
Figure 19136DEST_PATH_IMAGE017
The predicted value of (a) is determined,
Figure 988229DEST_PATH_IMAGE034
and indicates the total population.
7. An infectious disease trend prediction method based on neural networks and SEIR models as claimed in claim 1, wherein: in step 4, the average square error is selected as a loss function during training.
8. An infectious disease trend prediction method based on neural networks and SEIR models as claimed in claim 1, wherein: in the step 4, the model parameter updating mode is set to be that the learning rate is 0.005, a complete training set is a learning batch, the total learning iteration frequency is 5000, the network training process updates parameters once for each learning batch, learning errors are calculated according to the output of the epidemic situation trend prediction module and the real label, the network parameters are updated by using BP algorithm with errors, after each iteration learning is completed, the epidemic situation trend prediction module calculates the current prediction errors and compares the current prediction errors with the historical minimum errors, if the current prediction errors are smaller than the historical minimum errors, the current epidemic situation trend prediction module is stored, the historical minimum errors are updated to be the current errors, and then the training is continued until the total learning iteration frequency is reached.
CN202110658591.1A 2021-06-15 2021-06-15 Infectious disease trend prediction method based on neural network and SEIR model Pending CN113113155A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110658591.1A CN113113155A (en) 2021-06-15 2021-06-15 Infectious disease trend prediction method based on neural network and SEIR model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110658591.1A CN113113155A (en) 2021-06-15 2021-06-15 Infectious disease trend prediction method based on neural network and SEIR model

Publications (1)

Publication Number Publication Date
CN113113155A true CN113113155A (en) 2021-07-13

Family

ID=76723702

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110658591.1A Pending CN113113155A (en) 2021-06-15 2021-06-15 Infectious disease trend prediction method based on neural network and SEIR model

Country Status (1)

Country Link
CN (1) CN113113155A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112529329A (en) * 2020-12-21 2021-03-19 广东珠江智联信息科技股份有限公司 Infectious disease prediction method based on BP algorithm and SEIR model
CN113345599A (en) * 2021-08-04 2021-09-03 医渡云（北京）技术有限公司 Epidemic situation prediction method, epidemic situation prediction device, storage medium and electronic equipment
CN113539517A (en) * 2021-08-05 2021-10-22 浙江大学 Prediction method of time sequence intervention effect
CN113593716A (en) * 2021-07-30 2021-11-02 延安大学 Infectious disease trend prediction method and device
CN113744888A (en) * 2021-09-02 2021-12-03 深圳万海思数字医疗有限公司 Regional epidemic trend prediction early warning method and system
CN114496296A (en) * 2022-02-07 2022-05-13 华北理工大学 SEIARN Propagation Prediction System Based on LSTM Trajectory Intersection
CN117672544A (en) * 2023-12-14 2024-03-08 广东省疾病预防控制中心 Infectious disease transmission prediction method and system based on SEIR model
CN117690601A (en) * 2024-02-02 2024-03-12 江西省胸科医院(江西省第三人民医院) Tuberculosis epidemic trend prediction system based on big data analysis

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170316324A1 (en) * 2016-04-27 2017-11-02 Virginia Polytechnic Institute And State University Computerized Event-Forecasting System and User Interface
CN111524611A (en) * 2020-04-24 2020-08-11 腾讯科技（深圳）有限公司 Method, device and equipment for constructing infectious disease trend prediction model
CN111739658A (en) * 2020-07-20 2020-10-02 医渡云（北京）技术有限公司 Method and device for predicting infectious disease trend based on input case
CN112163705A (en) * 2020-09-29 2021-01-01 重庆邮电大学 Epidemic prediction and early warning method based on CNN+SEIR and LSTM
CN112529329A (en) * 2020-12-21 2021-03-19 广东珠江智联信息科技股份有限公司 Infectious disease prediction method based on BP algorithm and SEIR model
CN112712903A (en) * 2021-01-15 2021-04-27 杭州中科先进技术研究院有限公司 Infectious disease monitoring method based on human-computer three-dimensional cooperative sensing

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170316324A1 (en) * 2016-04-27 2017-11-02 Virginia Polytechnic Institute And State University Computerized Event-Forecasting System and User Interface
CN111524611A (en) * 2020-04-24 2020-08-11 腾讯科技（深圳）有限公司 Method, device and equipment for constructing infectious disease trend prediction model
CN111739658A (en) * 2020-07-20 2020-10-02 医渡云（北京）技术有限公司 Method and device for predicting infectious disease trend based on input case
CN112163705A (en) * 2020-09-29 2021-01-01 重庆邮电大学 Epidemic prediction and early warning method based on CNN+SEIR and LSTM
CN112529329A (en) * 2020-12-21 2021-03-19 广东珠江智联信息科技股份有限公司 Infectious disease prediction method based on BP algorithm and SEIR model
CN112712903A (en) * 2021-01-15 2021-04-27 杭州中科先进技术研究院有限公司 Infectious disease monitoring method based on human-computer three-dimensional cooperative sensing

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
甘雨 等: "新冠肺炎疫情趋势预测模型", 《智能系统学报》 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112529329A (en) * 2020-12-21 2021-03-19 广东珠江智联信息科技股份有限公司 Infectious disease prediction method based on BP algorithm and SEIR model
CN113593716A (en) * 2021-07-30 2021-11-02 延安大学 Infectious disease trend prediction method and device
CN113593716B (en) * 2021-07-30 2024-02-09 延安大学 Infectious disease trend prediction method and device
CN113345599A (en) * 2021-08-04 2021-09-03 医渡云（北京）技术有限公司 Epidemic situation prediction method, epidemic situation prediction device, storage medium and electronic equipment
CN113539517A (en) * 2021-08-05 2021-10-22 浙江大学 Prediction method of time sequence intervention effect
CN113539517B (en) * 2021-08-05 2024-04-16 浙江大学 Prediction Methods of Time-Sequence Intervention Effects
CN113744888A (en) * 2021-09-02 2021-12-03 深圳万海思数字医疗有限公司 Regional epidemic trend prediction early warning method and system
CN113744888B (en) * 2021-09-02 2023-09-22 深圳万海思数字医疗有限公司 Regional epidemic trend prediction and early warning method and system
CN114496296A (en) * 2022-02-07 2022-05-13 华北理工大学 SEIARN Propagation Prediction System Based on LSTM Trajectory Intersection
CN117672544A (en) * 2023-12-14 2024-03-08 广东省疾病预防控制中心 Infectious disease transmission prediction method and system based on SEIR model
CN117690601A (en) * 2024-02-02 2024-03-12 江西省胸科医院(江西省第三人民医院) Tuberculosis epidemic trend prediction system based on big data analysis
CN117690601B (en) * 2024-02-02 2024-05-24 江西省胸科医院(江西省第三人民医院) Tuberculosis epidemic trend prediction system based on big data analysis

Similar Documents

Publication Publication Date Title
CN113113155A (en) Infectious disease trend prediction method based on neural network and SEIR model
Zheng et al. Predicting COVID-19 in China using hybrid AI model
CN110970099B (en) A Drug Molecule Generation Method Based on Regularized Variational Autoencoder
CN111524611A (en) Method, device and equipment for constructing infectious disease trend prediction model
CN111445997A (en) Infectious disease dynamics model based on machine learning algorithm and analysis method
CN113593716B (en) Infectious disease trend prediction method and device
CN115644823B (en) Dynamic prediction of rehabilitation effect and individualized intervention system
CN110223785A (en) A kind of infectious disease transmission network reconstruction method based on deep learning
CN114821204B (en) Meta-learning-based embedded semi-supervised learning image classification method and system
CN113488165B (en) Text matching method, device, equipment and storage medium based on knowledge graph
CN113241188A (en) Cross-region transmission prediction method for new infectious disease under open system
CN107579816B (en) Method for generating password dictionary based on recurrent neural network
CN106126607A (en) A kind of customer relationship towards social networks analyzes method
CN117272040A (en) A small-sample time series forecasting method based on meta-learning framework
CN110310199A (en) Borrow or lend money construction method, system and the debt-credit Risk Forecast Method of risk forecast model
CN113192627A (en) Patient and disease bipartite graph-based readmission prediction method and system
CN117809811A (en) Artificial intelligence-based weight-reduction operation postoperative management method and system
CN114121212B (en) Traditional Chinese medicine prescription generation method based on knowledge graph and group representation learning
CN117457230A (en) A method for short-term rapid forecasting of infectious disease development trends
CN114496296B (en) SEIARN propagation prediction system based on LSTM trajectory intersection
CN113450924B (en) Novel coronavirus propagation model establishing method and system
CN114883001A (en) Disease prediction system based on heterogeneous information network
CN117198555B (en) Disease transmission prediction method based on viral load and neural network
Singh et al. Machine learning approach for data analysis and predicting coronavirus using COVID-19 India dataset
You et al. An improved method for pneumonia image classification based on coatnet

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20210713

RJ01 Rejection of invention patent application after publication