Institution
Chonbuk National University
Education•Jeonju, South Korea•
About: Chonbuk National University is a education organization based out in Jeonju, South Korea. It is known for research contribution in the topics: Apoptosis & Nanofiber. The organization has 14820 authors who have published 28884 publications receiving 554131 citations.
Topics: Apoptosis, Nanofiber, Population, Graphene, Electrospinning
Papers published on a yearly basis
Papers
More filters
••
TL;DR: In this paper, a novel strategy for synthesis of highly porous nitrogen-sulfur co-doped graphene nanoribbons (NS-GNRs) with enhanced active sites was developed.
116 citations
••
TL;DR: It was found that darkness, (red 780-622 nm, blue 492-455 nm) and white light influenced pigment and biomass yield and growth of fungi in green and yellow wavelengths resulted in low biomass and pigment yield.
115 citations
••
TL;DR: The results suggest that secretory factors released from stem cells could be an important mediator of stem cell therapy in ischemic tissue diseases.
115 citations
••
TL;DR: In this article, a green and facile one-step hydrothermal process was used to synthesize a composite of metal, metal oxide and graphene oxide (GO) for cyclic use.
115 citations
••
TL;DR: Experimental results show that the models using MBPNN outperform than the basic BPNN and the application of LSA for this system can lead to dramatic dimensionality reduction while achieving good classification results.
Abstract: New text categorization models using back-propagation neural network (BPNN) and modified back-propagation neural network (MBPNN) are proposed. An efficient feature selection method is used to reduce the dimensionality as well as improve the performance. The basic BPNN learning algorithm has the drawback of slow training speed, so we modify the basic BPNN learning algorithm to accelerate the training speed. The categorization accuracy also has been improved consequently. Traditional word-matching based text categorization system uses vector space model (VSM) to represent the document. However, it needs a high dimensional space to represent the document, and does not take into account the semantic relationship between terms, which can also lead to poor classification accuracy. Latent semantic analysis (LSA) can overcome the problems caused by using statistically derived conceptual indices instead of individual words. It constructs a conceptual vector space in which each term or document is represented as a vector in the space. It not only greatly reduces the dimensionality but also discovers the important associative relationship between terms. We test our categorization models on 20-newsgroup data set, experimental results show that the models using MBPNN outperform than the basic BPNN. And the application of LSA for our system can lead to dramatic dimensionality reduction while achieving good classification results.
115 citations
Authors
Showing all 14943 results
Name | H-index | Papers | Citations |
---|---|---|---|
Hyun-Chul Kim | 176 | 4076 | 183227 |
Andrew Ivanov | 142 | 1812 | 97390 |
Dong-Chul Son | 138 | 1370 | 98686 |
C. Haber | 135 | 1507 | 98014 |
Tae Jeong Kim | 132 | 1420 | 93959 |
Alessandro Cerri | 129 | 1244 | 103225 |
Paul M. Vanhoutte | 127 | 868 | 62177 |
Jason Nielsen | 125 | 893 | 72688 |
Chi Lin | 125 | 1313 | 102710 |
Paul Lujan | 123 | 1255 | 76799 |
Young Hee Lee | 122 | 1168 | 61107 |
Min Suk Kim | 119 | 975 | 66214 |
Alexandre Sakharov | 119 | 582 | 56771 |
Yang-Kook Sun | 117 | 781 | 58912 |
Rui L. Reis | 115 | 1608 | 63223 |