2020년 컴퓨터종합학술대회
Current Result Document :
| 한글제목(Korean Title) |
Evolvable Symptom-Disease Investigator for Smart Healthcare Decision Support System |
| 영문제목(English Title) |
Evolvable Symptom-Disease Investigator for Smart Healthcare Decision Support System |
| 저자(Author) |
Kyi Thar
Ki Tae Kim
Ye Lin Tun
Chu Myaet Thwal
Choong Seon Hong
|
| 원문수록처(Citation) |
VOL 47 NO. 01 PP. 0578 ~ 0580 (2020. 07) |
한글내용
(Korean Abstract) |
Based on the lessons learned from the COVIC pandemic, the world needs a better and smarter healthcare infrastructure to be able to deliver better healthcare services to society. To develop a better healthcare infrastructure, one of the key components is the Smart Healthcare Decision Support System capable of delivering accurate information to healthcare professionals. Various types of supervised machine learning models can provide accurate information but those models need to retrain if we want to expand both the input features and the target labels. Therefore, in this paper, we proposed a deep learning-based evolvable symptoms-disease investigator where our goal is to provide the system where the models do not need to train from zero levels again when the new input features and target labels are introduced. We implemented the proposed scheme by utilizing Sequence to Sequence Attention Neural Network architecture with TensorFlow. |
영문내용
(English Abstract) |
|
| 키워드(Keyword) |
|
| 파일첨부 |
PDF 다운로드
|
