J
Jun Feng
Researcher at Northwest University (China)
Publications - 108
Citations - 915
Jun Feng is an academic researcher from Northwest University (China). The author has contributed to research in topics: Convolutional neural network & Computer science. The author has an hindex of 11, co-authored 92 publications receiving 420 citations. Previous affiliations of Jun Feng include Northwestern University & Nanjing University of Science and Technology.
Papers
More filters
Journal ArticleDOI
Drug-Drug Interaction Extraction via Recurrent Hybrid Convolutional Neural Networks with an Improved Focal Loss.
TL;DR: A novel recurrent hybrid convolutional neural network (RHCNN) for DDI extraction from biomedical literature and applies an improved focal loss function to mitigate against the defects of the traditional cross-entropy loss function when dealing with class imbalanced data.
Journal ArticleDOI
Breast mass classification via deeply integrating the contextual information from multi-view data
TL;DR: A hybrid deep network framework is presented, aiming to efficiently integrate and exploit information from multi-view data for breast mass classification, and learns the attention-driven features of CNN as well as the semantic label dependency among different views.
Journal ArticleDOI
MOOC Dropout Prediction Using a Hybrid Algorithm Based on Decision Tree and Extreme Learning Machine
TL;DR: DT-ELM, a novel hybrid algorithm combining decision tree and extreme learning machine (ELM), which requires no iterative training is proposed, which is effective on the benchmark KDD 2015 dataset.
Journal ArticleDOI
Mechanical analyses of hooked fiber pullout performance in ultra-high-performance concrete
TL;DR: In this paper, a practical model to simulate the pullout performance of hooked steel fiber in ultra-high-performance concrete is proposed, based on which slip-hardening, matrix spalling and tunnel damage assumptions are made.
Journal ArticleDOI
Analysis of patient dose in full field digital mammography
Baoying Chen,Yingmei Wang,Xin Sun,Wei Guo,Ming Zhao,Guangbin Cui,Lina Hu,Pei Li,Yan Ren,Jun Feng,Jun Yu +10 more
TL;DR: The findings on dose and exposure characteristics of the three AOP modes get useful message of patient dose in the acquisition of FFDM.