[Abdul/허성구 통합,J.Water.Proc.Eng/JCR10%] 수질 TN/TP AI 소프트센서-XAI | ||
---|---|---|
|
||
Hi EMSEL, I am pleased to inform you that EMSEL Ph.D students, Abdulrahman H. Ba-Alawi, SungKu Heo and Roberto Chang, TaeYong Woo, MinHan Kim's paper has been published in the Journal of Water Process Engineering (ISSN: 2214-7144, IF=7.34, JCR TOP10% journal). Please give your big hands to Abdulrahman H. Ba-Alawi. Congratulations for the paper acceptance indeed. Topic: AI-softsensor, total nitrogen and total phosphorus, Missing data, convolutional auto-encoder , XAI(Explainable AI)
연구실 논문 소식입니다. EMSEL 연구실 Abdul박사과정과 허성구/우태용 통합 과정, 김민한 박사과정 논문이 Journal of Water Process Engineering (IF=7.34, JCR TOP 10%: Water Resources)저널에 게재 l되었습니다. (주) 에이치코비와 공동과제 수행 중인 AI-softsensor 수질 TN/TP 소프트센서 개발로 2022년 실시간 데이타 안양천 총질소/총인 실시간 소프트센서에 관한 내용으로 최신 연구 결과입니다. - Abdulrahman H. Ba-Alawi, SungKu Heo, Hanaa Aamer, Roberto Chang, TaeYong Woo, MinHan Kim, ChangKyoo Yoo*, Development of transparent high-frequency soft sensor of total nitrogen and total phosphorus concentrations in rivers using stacked convolutional auto-encoder and explainable AI, Journal of Water Process Engineering (ISSN: 2214-7144, SCIE, JCR TOP 10%: Water Resources), Elsevier, 53(7), pp.103661 (2023.7) (Ack (4개): BK21, NRF 2021R1A2C2007838, a Graduate School specialized in Climate Change, 중기청-코비) Highlights An explainable DL model was used for first time for water nutrients monitoring. Boruta algorithm identified the most influencing water quality features on TN and TP. The CAE-DFC showed a superior prediction for TN and TP (R 2= 0.9607 and 0.9137). Explainable CAE-DFC based soft sensor outperformed SVR, DNN, RF, and XGBoost models. XAI-based Kernel SHAP provided a clear interpretation of the CAE-DFC model outcome. <o:p></o:p>
|