KR20220068731A - A method for learning a model that detects infectious diseases early in real time by recognizing the spread pattern of infectious diseases - Google Patents

A method for learning a model that detects infectious diseases early in real time by recognizing the spread pattern of infectious diseases Download PDF

Info

Publication number
KR20220068731A
KR20220068731A KR1020200155810A KR20200155810A KR20220068731A KR 20220068731 A KR20220068731 A KR 20220068731A KR 1020200155810 A KR1020200155810 A KR 1020200155810A KR 20200155810 A KR20200155810 A KR 20200155810A KR 20220068731 A KR20220068731 A KR 20220068731A
Authority
KR
South Korea
Prior art keywords
infectious disease
infectious diseases
prediction model
data
learning
Prior art date
Application number
KR1020200155810A
Other languages
Korean (ko)
Inventor
김유신
박은주
주연진
민두홍
유우상
김민선
Original Assignee
주식회사 에어딥
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 주식회사 에어딥 filed Critical 주식회사 에어딥
Priority to KR1020200155810A priority Critical patent/KR20220068731A/en
Publication of KR20220068731A publication Critical patent/KR20220068731A/en

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
    • G06N20/00—Machine learning
    • 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
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
    • 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
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Data Mining & Analysis (AREA)
  • Primary Health Care (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The present invention relates to a real-time infectious disease early detection model learning method based on infectious disease spread pattern recognition, which proceeds with clustering of infectious diseases through analysis of the spread pattern of infectious diseases based on the construction of a database server for predicting infectious diseases. In addition, by generating, learning, and utilizing prediction models for each clustered infectious disease, risk signs are captured to promptly recognize the occurrence of infectious diseases, and areas with a high risk of infectious diseases can be identified.

Description

감염병 확산 패턴인식에 기반한 실시간 감염병 조기탐지모델 학습 방법{A METHOD FOR LEARNING A MODEL THAT DETECTS INFECTIOUS DISEASES EARLY IN REAL TIME BY RECOGNIZING THE SPREAD PATTERN OF INFECTIOUS DISEASES}A method for learning a real-time early detection model of an infectious disease based on the recognition of an infectious disease spread pattern

본 발명은 감염병 확산 패턴인식에 기반한 실시간 감염병 조기탐지모델 학습 방법에 관한 것으로서, 보다 구체적으로는, 감염병 예측을 위한 데이터 베이스 서버 구축을 기반으로 감염병의 확산 패턴 분석을 통한 감염병 클러스터링을 진행하고, 또한 군집화된 감염병별로 예측모델을 생성 및 학습하여 활용하여 위험 징후를 포착해 감염병 발생을 신속히 인지하고, 감염병이 발생할 위험도가 높은 지역을 도출할 수 있는 감염병 확산 패턴인식에 기반한 실시간 감염병 조기탐지모델 학습 방법에 관한 것이다.The present invention relates to a method for learning a real-time early detection model of an infectious disease based on the recognition of an infectious disease spread pattern. A method of learning a real-time early detection model of an infectious disease based on the recognition of an infectious disease spread pattern that can generate, learn, and utilize a predictive model for each clustered infectious disease to quickly recognize the occurrence of an infectious disease by capturing risk signs, and derive areas with a high risk of an infectious disease is about

최근, COVID-19와 같은 감염병이 확산되고 있는 가운데, 현 상황에서는 감염증상이 나타난 후 감염의심자가 직접 감염검사를 받지 않는 한 감염유무, 확산 여부 등을 확인하기가 어렵다는 점에서, 위험 징후를 포착하여 감염병 발생을 신속히 인지하고, 감염병 발생 위험도가 높은 지역을 조기 탐지하여 방역 레드존으로 설정할 수 있는 기술이 무엇보다 필요한 실정이다.Recently, as an infectious disease such as COVID-19 is spreading, in the current situation, it is difficult to confirm the presence or absence of infection or the spread of infection unless a person suspected of infection is directly tested for infection after the appearance of an infectious disease, so it is possible to detect signs of danger. Therefore, a technology that can quickly recognize the outbreak of an infectious disease, detect an area with a high risk of an infectious disease at an early stage, and set it as a quarantine red zone is needed above all else.

한국등록특허 제10-1925506호Korean Patent Registration No. 10-1925506

본 발명은 상기의 문제점을 해결하기 위함으로써, 감염병 예측을 위한 데이터 베이스 서버 구축을 기반으로 감염병의 확산 패턴 분석을 통한 감염병 클러스터링을 진행하고, 또한 군집화된 감염병별로 예측모델을 생성 및 학습하여 활용하여 위험 징후를 포착해 감염병 발생을 신속히 인지하고, 감염병이 발생할 위험도가 높은 지역을 도출할 수 있는 감염병 확산 패턴인식에 기반한 실시간 감염병 조기탐지모델 학습 방법을 제공하고자 한다.In order to solve the above problems, the present invention performs clustering of infectious diseases through analysis of the spread pattern of infectious diseases based on the construction of a database server for predicting infectious diseases, and also generates, learns, and utilizes predictive models for each clustered infectious disease. The purpose of this study is to provide a real-time early detection model learning method for infectious diseases based on recognizing the spread of infectious diseases that can detect dangerous signs to quickly recognize the occurrence of infectious diseases and derive areas with a high risk of infectious diseases.

본 발명의 일 실시예에 따른 감염병 확산 패턴인식에 기반한 실시간 감염병 조기탐지모델 학습 방법은 감염병 데이터베이스, 시계열 트렌드 데이터 베이스, 해외이동 데이터베이스 및 방역이력 데이터베이스로부터 데이터를 획득하고, 획득된 상기 데이터들을 토대로 변수 데이터를 정의 및 파생변수 데이터를 생성하는 단계, 상기 변수 데이터 및 상기 파생변수 데이터, 타겟 데이터로 설정된 감염병 별 감염정보 및 타겟 데이터로 설정된 지역별 감염병 확진자 데이터를 포함하는 학습데이터를 생성하고, 머신러닝에 기초하여 감염병 발생 예측모델 및 지역 발생 예측모델을 생성하는 단계 및 상기 감염병 발생 예측모델 및 상기 지역 발생 예측모델에 파생변수를 추가하고, 각 예측모델의 하이퍼파라미터를 반복 수정하여 상기 감염병 발생 예측모델 및 상기 지역 발생 예측모델을 반복 학습하는 단계를 포함하는 것을 특징으로 할 수 있다.According to an embodiment of the present invention, a method for learning a real-time infectious disease early detection model based on infectious disease spread pattern recognition acquires data from an infectious disease database, a time series trend database, an overseas movement database, and a quarantine history database, and a variable based on the acquired data defining data and generating derived variable data; generating learning data including the variable data and the derived variable data, infection information for each infectious disease set as target data, and regional infectious disease confirmed patient data set as target data, machine learning generating an infectious disease outbreak prediction model and a regional occurrence prediction model based on and repeatedly learning the regional occurrence prediction model.

본 발명의 일 측면에 따르면, 감염병의 확산 패턴 분석을 통한 감염병 클러스터링을 진행하고, 또한 군집화된 감염병별로 예측모델을 생성 및 학습하여 활용하여 위험 징후를 포착해 감염병 발생을 신속히 인지하고, 감염병이 발생할 위험도가 높은 지역을 도출할 수 있는 이점을 가진다.According to one aspect of the present invention, infectious disease clustering is carried out through analysis of the spread pattern of infectious diseases, and a predictive model is created and learned for each clustered infectious disease and used to capture risk signs to quickly recognize the occurrence of infectious diseases, and when infectious diseases occur. It has the advantage of deriving high-risk areas.

도 1은 본 발명의 일 실시예에 따른 감염병 확산 패턴인식에 기반한 실시간 감염병 조기탐지모델 학습 방법을 위한 단계를 순서대로 도시한 도면이다.
도 2는 데이터베이스로부터 데이터를 획득, 실시간 감염병 조기탐지모델을 생성 및 이를 토대로 감염병 발생을 조기탐지하는 전 과정을 일련의 순서대로 도시한 도면이다.
도 3은 특정 감염병 국내외 발생 확인 시 감염병 조기탐지 순서를 도시한 도면이다.
도 4는 도 1에서의 감염병 발생 예측모델 및 지역 발생 예측모델을 반복 학습하는 과정을 순서대로 도시한 도면이다.1 is a diagram sequentially illustrating steps for a method for learning a real-time early detection model of an infectious disease based on recognition of an infectious disease spread pattern according to an embodiment of the present invention.
2 is a diagram illustrating the entire process of acquiring data from a database, generating a real-time early detection model of an infectious disease, and early detection of an outbreak of an infectious disease based on the data in a sequential order.
3 is a diagram illustrating the sequence of early detection of an infectious disease when confirming the occurrence of a specific infectious disease at home and abroad.
4 is a diagram sequentially illustrating a process of repeatedly learning the infectious disease occurrence prediction model and the regional outbreak prediction model in FIG. 1 .

이하, 본 발명의 이해를 돕기 위하여 바람직한 실시예를 제시한다. 그러나 하기의 실시예는 본 발명을 보다 쉽게 이해하기 위하여 제공되는 것일 뿐, 실시예에 의해 본 발명의 내용이 한정되는 것은 아니다.Hereinafter, preferred examples are presented to help the understanding of the present invention. However, the following examples are only provided for easier understanding of the present invention, and the content of the present invention is not limited by the examples.

도 1은 본 발명의 일 실시예에 따른 감염병 확산 패턴인식에 기반한 실시간 감염병 조기탐지모델 학습 방법을 위한 단계를 순서대로 도시한 도면이고, 도 2는 데이터베이스로부터 데이터를 획득, 실시간 감염병 조기탐지모델을 생성 및 이를 토대로 감염병 발생을 조기탐지하는 전 과정을 일련의 순서대로 도시한 도면이다.1 is a sequence diagram showing the steps for a method for learning a real-time infectious disease early detection model based on the recognition of an infectious disease spread pattern according to an embodiment of the present invention, and FIG. It is a diagram showing the entire process of generation and early detection of an infectious disease outbreak based on it in a sequential order.

도 1 및 도 2를 살펴보면, 본 발명의 일 실시예에 따른 감염병 확산 패턴인식에 기반한 실시간 감염병 조기탐지모델 학습 방법은 크게 감염병 데이터베이스, 시계열 트렌드 데이터 베이스, 해외이동 데이터베이스 및 방역이력 데이터베이스로부터 데이터를 획득하고, 획득된 상기 데이터들을 토대로 변수 데이터를 정의 및 파생변수 데이터를 생성하는 단계(S101), 상기 변수 데이터 및 상기 파생변수 데이터, 타겟 데이터로 설정된 감염병 별 감염정보 및 타겟 데이터로 설정된 지역별 감염병 확진자 데이터를 포함하는 학습데이터를 생성하고, 머신러닝에 기초하여 감염병 발생 예측모델 및 지역 발생 예측모델을 생성하는 단계(S102) 및 상기 감염병 발생 예측모델 및 상기 지역 발생 예측모델에 파생변수를 추가하고, 각 예측모델의 하이퍼파라미터를 반복 수정하여 상기 감염병 발생 예측모델 및 상기 지역 발생 예측모델을 반복 학습하는 단계(S103)로 진행된다.1 and 2, the method for learning a real-time infectious disease early detection model based on the recognition of an infectious disease spread pattern according to an embodiment of the present invention mainly acquires data from an infectious disease database, a time series trend database, an overseas movement database, and a quarantine history database. and defining variable data and generating derived variable data based on the obtained data (S101); generating training data including data, generating an infectious disease occurrence prediction model and a regional occurrence prediction model based on machine learning (S102), and adding a derived variable to the infectious disease occurrence prediction model and the regional occurrence prediction model; The process proceeds to the step (S103) of iteratively learning the infectious disease occurrence prediction model and the regional occurrence prediction model by repeatedly modifying the hyperparameters of each prediction model.

보다 구체적으로, S101 단계에서는 방역이력 데이터베이스(방역대상 시설 주소, 최근 방역일, 사용 약품 등)와, 해외이동 데이터베이스(입출국 인구 수, 무역 선박 입출항 수, 수출입 금액 등)와, 감염병 정보 데이터베이스(감염병 위험 등급, 주요 증상, 감염원, 주요 매개체 등)와, 소셜 트랜드 데이터베이스(감염병 및 주요 증상 관련 뉴스기사, 키워드 등)로부터 데이터를 획득(취득)하는 과정이다. 이를 통해 획득된 데이터를 통해 변수 데이터가 정의되며 파생변수 데이터가 생성된다.More specifically, in step S101, the quarantine history database (address of the facility subject to quarantine, the latest quarantine date, medications used, etc.), the overseas movement database (the number of inbound and outbound populations, the number of trade vessels entering and leaving ports, the amount of import and export, etc.), and the infectious disease information database (infectious disease) It is the process of acquiring (acquiring) data from risk grade, major symptoms, infectious agents, major vectors, etc.) and social trend databases (news articles related to infectious diseases and major symptoms, keywords, etc.). Through the obtained data, variable data is defined and derived variable data is created.

또한, 이 과정에서, 감염병 정보 데이터베이스 및 소셜 트랜드 데이터베이스로부터 획득된 데이터를 토대로 감염병 및 증상별 시계열 트랜드 분석, 최근 n개월 간 시계열 패턴 및 특징 추출, 군집분석 모델 적용, 군집 결과 라벨링과 같은 감염병 시계열 군집분석이 시행된다.In addition, in this process, based on the data obtained from the infectious disease information database and social trend database, time series trend analysis by infectious disease and symptom, time series pattern and feature extraction for the last n months, cluster analysis model application, clustering result labeling, such as time series clustering of infectious diseases analysis is carried out.

S102 단계에서는 앞서 살펴본 S101 단계를 통해 획득된 변수 데이터, 파생변수 데이터와, 감염병 별 감염정보를 타겟 데이터로 하여 감염병 발생 예측모델을 생성하고, 또한 지역 별 감염병 확진자 데이터를 타겟 데이터로 하여 지역 발생 예측모델을 생성하게 된다.In step S102, an infectious disease outbreak prediction model is created using the variable data, derived variable data, and infection information for each infectious disease obtained in step S101 as the target data. A predictive model is created.

S103 단계에서는 앞서 살펴본 S102 단계를 통해 생성된 감염병 발생 예측모델을 토대로 감염병 별 발생 위험도를 예측 및 감염병 발생을 조기 탐지하고, 지역 발생 예측모델을 토대로 지역 별 감염병 발생 위험도를 예측 및 방역 레드존을 탐지하게 된다.In step S103, based on the infectious disease outbreak prediction model created in step S102, the risk of occurrence of each infectious disease and the occurrence of an infectious disease are detected early, and the risk of occurrence of infectious diseases by region is predicted and quarantine red zone is detected based on the regional outbreak prediction model. will do

도 3은 특정 감염병 국내외 발생 확인 시 감염병 조기탐지 순서를 도시한 도면이다.3 is a diagram illustrating the sequence of early detection of an infectious disease when confirming the occurrence of a specific infectious disease at home and abroad.

도 3을 살펴보면, 특정 감염병 국내발생 및 특정 감염병 해외발생이 확인될 경우, 앞서 도 1을 통해 생성된 감염병 별 예측모델 및 지역 발생 예측모델에 감염병 군집 모형이 적용됨에 따라 군집에 해당하는 예측모형들이 군집의 종류, 수에 따라 하나 이상 생성되며, 앞으로 n일간 특정 감염병발생 위험도가 예측될 수 있고 또한 앞으로 n일간 지역별 감염병발생 위험도가 예측될 수 있다.Referring to FIG. 3, when the domestic occurrence of a specific infectious disease and overseas occurrence of a specific infectious disease are confirmed, the predictive models corresponding to the cluster are applied to the predictive model for each infectious disease and the regional outbreak predictive model generated in FIG. 1 above. One or more clusters are created according to the type and number of clusters, and the risk of occurrence of a specific infectious disease can be predicted for the next n days, and the risk of occurrence of an infectious disease by region can also be predicted for the next n days.

도 4는 도 1에서의 감염병 발생 예측모델 및 지역 발생 예측모델을 반복 학습하는 과정을 순서대로 도시한 도면이다.4 is a diagram sequentially illustrating a process of repeatedly learning the infectious disease occurrence prediction model and the regional outbreak prediction model in FIG. 1 .

도 4를 살펴보면, 실시간 감염병 조기탐지모델의 학습 방법은 주요 피처 선정 및 파생변수를 생성하는 학습용 특징 추출 단계, 예측 타겟 구분에 따른 데이터셋을 구성하는 학습 데이터셋 생성 단계를 거치게 되며, 이를 통해 감염병 발생 예측모델 및 지역 발생 예측모델의 학습 후 모델 검증 및 튜닝이 진행된다. 또한 이러한 과정은 파생변수 추가, 예측모델의 하이퍼파라미터 수정과 같은 과정을 통해 반복되며 성능이 개선될 수 있다.Referring to FIG. 4 , the learning method of the real-time infectious disease early detection model goes through a feature extraction step for learning that selects major features and generates derived variables, and a training dataset creation step that composes a dataset according to classification of prediction targets. After learning the occurrence prediction model and the regional occurrence prediction model, model validation and tuning are carried out. In addition, this process is repeated through processes such as adding derived variables and modifying hyperparameters of the predictive model, and performance can be improved.

상기에서는 본 발명의 바람직한 실시예를 참조하여 설명하였지만, 해당 기술 분야의 숙련된 당업자는 하기의 특허 청구의 범위에 기재된 본 발명의 사상 및 영역으로부터 벗어나지 않는 범위 내에서 본 발명을 다양하게 수정 및 변경시킬 수 있음을 이해할 수 있을 것이다.Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that it can be done.

Claims (1)

감염병 데이터베이스, 시계열 트렌드 데이터 베이스, 해외이동 데이터베이스 및 방역이력 데이터베이스로부터 데이터를 획득하고, 획득된 상기 데이터들을 토대로 변수 데이터를 정의 및 파생변수 데이터를 생성하는 단계;
상기 변수 데이터 및 상기 파생변수 데이터, 타겟 데이터로 설정된 감염병 별 감염정보 및 타겟 데이터로 설정된 지역별 감염병 확진자 데이터를 포함하는 학습데이터를 생성하고, 머신러닝에 기초하여 감염병 발생 예측모델 및 지역 발생 예측모델을 생성하는 단계; 및
상기 감염병 발생 예측모델 및 상기 지역 발생 예측모델에 파생변수를 추가하고, 각 예측모델의 하이퍼파라미터를 반복 수정하여 상기 감염병 발생 예측모델 및 상기 지역 발생 예측모델을 반복 학습하는 단계;를 포함하는 것을 특징으로 하는, 감염병 확산 패턴인식에 기반한 실시간 감염병 조기탐지모델 학습 방법.acquiring data from an infectious disease database, a time series trend database, an overseas movement database, and a quarantine history database, and defining variable data and generating derived variable data based on the acquired data;
The variable data and the derived variable data, the infection information for each infectious disease set as the target data, and the regional infectious disease confirmed case data set as the target data are generated, and based on machine learning, an infectious disease occurrence prediction model and a regional occurrence prediction model are generated. creating a; and
adding a derived variable to the infectious disease occurrence prediction model and the regional occurrence prediction model, and repeatedly modifying hyperparameters of each prediction model to repeatedly learn the infectious disease occurrence prediction model and the regional occurrence prediction model; A method for learning a real-time early detection model for infectious diseases based on the recognition of infectious disease spread patterns.
KR1020200155810A 2020-11-19 2020-11-19 A method for learning a model that detects infectious diseases early in real time by recognizing the spread pattern of infectious diseases KR20220068731A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020200155810A KR20220068731A (en) 2020-11-19 2020-11-19 A method for learning a model that detects infectious diseases early in real time by recognizing the spread pattern of infectious diseases

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020200155810A KR20220068731A (en) 2020-11-19 2020-11-19 A method for learning a model that detects infectious diseases early in real time by recognizing the spread pattern of infectious diseases

Publications (1)

Publication Number Publication Date
KR20220068731A true KR20220068731A (en) 2022-05-26

Family

ID=81808999

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020200155810A KR20220068731A (en) 2020-11-19 2020-11-19 A method for learning a model that detects infectious diseases early in real time by recognizing the spread pattern of infectious diseases

Country Status (1)

Country Link
KR (1) KR20220068731A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116959715A (en) * 2023-09-18 2023-10-27 之江实验室 Disease prognosis prediction system based on time sequence evolution process explanation

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101925506B1 (en) 2017-12-12 2018-12-06 한국과학기술정보연구원 Method and apparatus for predicting the spread of an infectious disease

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101925506B1 (en) 2017-12-12 2018-12-06 한국과학기술정보연구원 Method and apparatus for predicting the spread of an infectious disease

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116959715A (en) * 2023-09-18 2023-10-27 之江实验室 Disease prognosis prediction system based on time sequence evolution process explanation
CN116959715B (en) * 2023-09-18 2024-01-09 之江实验室 Disease prognosis prediction system based on time sequence evolution process explanation

Similar Documents

Publication Publication Date Title
Chen et al. Feature selection to improve generalization of genetic programming for high-dimensional symbolic regression
US11100220B2 (en) Data type recognition, model training and risk recognition methods, apparatuses and devices
Wang et al. Metamorphic object insertion for testing object detection systems
CN104991965B (en) For asking the creation method and apparatus that extension is asked based on standard
US11580560B2 (en) Identity resolution for fraud ring detection
JPWO2018167900A1 (en) Neural network learning apparatus, method, and program
KR20190053616A (en) Data merging device and method for bia datda analysis
Cimen et al. Classification of human motion based on affective state descriptors
CN111143838A (en) Database user abnormal behavior detection method
CN114065199B (en) Cross-platform malicious code detection method and system
KR20220068731A (en) A method for learning a model that detects infectious diseases early in real time by recognizing the spread pattern of infectious diseases
CN110543765A (en) malicious software detection method
Thilina et al. Intruder detection using deep learning and association rule mining
CN113326187A (en) Data-driven intelligent detection method and system for memory leakage
CN110716957B (en) Intelligent mining and analyzing method for class case suspicious objects
Agrawal et al. A survey on video-based fake news detection techniques
Zhu et al. Egoobjects: A large-scale egocentric dataset for fine-grained object understanding
Wang et al. Understanding and facilitating the co-evolution of production and test code
Schneider et al. Concept-based adversarial attacks: Tricking humans and classifiers alike
CN106874762A (en) Android malicious code detecting method based on API dependence graphs
Wurst et al. Novelty detection and analysis of traffic scenario infrastructures in the latent space of a vision transformer-based triplet autoencoder
JP2005128628A (en) Generation of template used for matching in pattern identification, and method, apparatus, and program for pattern identification using the template
CN109542766B (en) Large-scale program similarity rapid detection and evidence generation method based on code mapping and lexical analysis
Sharif et al. Function identification in android binaries with deep learning
Xiong et al. An Anomaly Detection Framework for System Logs Based on Ensemble Learning