DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Jung, Yousung | - |
dc.contributor.advisor | 정유성 | - |
dc.contributor.author | Kim, Juhwan | - |
dc.date.accessioned | 2021-05-12T19:37:23Z | - |
dc.date.available | 2021-05-12T19:37:23Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=910838&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/284043 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 생명화학공학과, 2020.2,[iii, 26 p. :] | - |
dc.description.abstract | Chemical reaction product prediction is a fundamental exercise for chemists. Various product prediction models have been developed, but because most models are focused on main product prediction, the prediction of toxic byproducts was difficult. Therefore, we developed a binary classification model for toxic byproducts. The model is trained for 17 toxins and in every case, binary classification shows better performance than the previous state-of-art model. Our binary classification model cannot completely replace past models. However, by using both models together, we can predict reaction products more accurately and reliably. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Product Prediction▼aBinary classification▼aToxic byproducts | - |
dc.subject | 반응 생성물 예측▼a이항 분류 모델▼a독성 부산물 | - |
dc.title | Toxin formation predetection using deep neural network | - |
dc.title.alternative | 심층 신경망을 이용한 독성 물질 생성 예측 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :생명화학공학과, | - |
dc.contributor.alternativeauthor | 김주환 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.