5篇
您的检索式：作者名="Jaejun Kim"
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Recurrent massive bleeding due to dissecting intramural hematoma of the esophagus: Treatment with therapeutic angiography显示文摘Spontaneous or traumatic intramural bleeding of the esophagus, which is often associated with overlying mucosal dissection, constitutes a rare spectrum of esophageal injury called dissecting intramural hematoma of the esophagus (DIHE). Chest pain, swallowing diffi culty, and minor hematemesis are common, which resolve spontaneously in most cases. This case report describes a patient with spontaneous DIHE with recurrent massive bleeding which required critical management and highlights a potential role for therapeutic angiography as an alternative to surgery. | Jaejun Shim Jae Young Jang Young Hwangbo Seok Ho Dong Joo Hyeong Oh Hyo Jong Kim Byung-Ho Kim Young Woon Chang Rin Chang | 2009 | World Journal of Gastroenterology2009，15，41： | 8 |
| 2 | Water removal characteristics of proton exchange membrane fuel cells using a dry gas purging method显示文摘 | Sang-Yeop Lee Sang-Uk Kim Hyoung-Juhn Kim Jong Hyun Jang In-Hwan Oh Eun Ae Cho Seong-Ahn Hong Jaejun Ko Tae-Won Lim Kwan-Young Lee Tae-Hoon Lim | 2008 | Journal of Power Sources2008，，2： | 1 |
| 3 | The peroxisome proliferator-activated receptor γ ligands, pioglitazoneand 15-deoxy-Δ12,14-prostaglandin J2, have antineoplastic effects against hepatitisB virus-associated hepatocellular carcinoma cells显示文摘 | Jaejun Shim Byung-Ho Kim Young Kim Kyung Kim Young Hwangbo Jae Jang Seok Dong Hyo Kim Young Chang Rin Chang | 2010 | International Journal of Oncology2010，，1： | 1 |
| 4 | A Core system for design information management using industry foundation classes显示文摘 | Lee Keunhyong Chin Sangyoon Kim Jaejun | 2003 | Computer-aided Civil and Infrastructure Engineering2003，18，4： | 1 |
| 5 | Iterative learning-based many-objective history matching using deep neural network with stacked autoencoder显示文摘This paper presents an innovative data-integration that uses an iterative-learning method,a deep neural network(DNN)coupled with a stacked autoencoder(SAE)to solve issues encountered with many-objective history matching.The proposed method consists of a DNN-based inverse model with SAE-encoded static data and iterative updates of supervised-learning data are based on distance-based clustering schemes.DNN functions as an inverse model and results in encoded flattened data,while SAE,as a pre-trained neural network,successfully reduces dimensionality and reliably reconstructs geomodels.The iterative-learning method can improve the training data for DNN by showing the error reduction achieved with each iteration step.The proposed workflow shows the small mean absolute percentage error below 4%for all objective functions,while a typical multi-objective evolutionary algorithm fails to significantly reduce the initial population uncertainty.Iterative learning-based manyobjective history matching estimates the trends in water cuts that are not reliably included in dynamicdata matching.This confirms the proposed workflow constructs more plausible geo-models.The workflow would be a reliable alternative to overcome the less-convergent Pareto-based multi-objective evolutionary algorithm in the presence of geological uncertainty and varying objective functions. | Jaejun Kim Changhyup Park Seongin Ahn Byeongcheol Kang Hyungsik Jung Ilsik Jang | 2021 | Petroleum Science2021，18，5： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员