News register
Search section
Search area
News Type
News type
Search date
Search word OR
List of related articles
Contents of related articles
No info was found
List of related articles
Contents of related articles
No info was found
View details
Information

03/12/2020 HYU News > Student

Title

Student Kim Ji-hu Distributed the "COVID-19 Dataset"

Predicts patients and fatality rate of COVID-19...exceeded 5000 accumulated downloads

Global News Team

Copy URL / Share SNS

http://www.hanyang.ac.kr/surl/JGoIB

Contents
The "COVID-19 Dataset," created by Kim Ji-hu of Department of Computer Science (Master, Class of '19) is drawing the attention of Kaggle.
 
▲ Screenshot of the Kaggle website

On February 24th, Kim registered his "COVID-19 Dataset" on Kaggle, a machine learning-based prediction model·analysis platform. The dataset exceeded more than 5000 accumulated downloads on March 6th. On the 3rd, it placed 1st in the category of Most Popular Data on the website. There are more than 130,000 users throughout the world on Kaggle.

A dataset is a group of information that is made by collecting, processing, and categorizing scattered information into a form that a computer can understand. This is an essential part of the machine learning process, which teaches Artificial Intelligence. The Coronavirus dataset created by Kim is constructed through a daily report provided on the official website of the Korea Centers for Disease Control & Prevention. Various information related to COVID-19 is organized on the dataset, such as the patients' gender, date of birth, and infection process, including information such as accumulated number of checkups, number of positive patients, and fatality rate. 

Codes using the COVID-19 Dataset are re-shared on Kaggle. When the COVID-19 Dataset is used, it allows for the creation of a model that predicts how many additional patients will occur during a certain period in the future. It is also possible to predict each patient's possibility of recovery or death, depending on one's age, gender, and previous illness. Additionally, it can construct groups by the characteristics of the patients by detecting abnormal data and separate the patients such as by super spreaders of the disease.

Kim mentioned in an interview with Etnews that "it is definitely possible to apply this dataset to other infectious diseases, despite the differences in culture and systems of other countries," and he added that "I hope that Korea will build and model good dataset with the COVID-19 situation and that it is utilized greatly in future emergencies."



Global News Team
Translated by: Lee Won-young
global@hanyang.ac.kr

 
Copy URL / Share SNS

0 Comments