Institution
Korea University
Education•Seoul, South Korea•
About: Korea University is a education organization based out in Seoul, South Korea. It is known for research contribution in the topics: Population & Thin film. The organization has 39756 authors who have published 82424 publications receiving 1860927 citations. The organization is also known as: Bosung College & Bosung Professional College.
Topics: Population, Thin film, Catalysis, Large Hadron Collider, Cancer
Papers published on a yearly basis
Papers
More filters
•
TL;DR: This paper proposes Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which involve identifying useful connections between unconnected nodes on the original graph, while learning effective node representation on the new graphs in an end-to-end fashion.
Abstract: Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved state-of-the-art performance in tasks such as node classification and link prediction. However, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. In this paper, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which involve identifying useful connections between unconnected nodes on the original graph, while learning effective node representation on the new graphs in an end-to-end fashion. Graph Transformer layer, a core layer of GTNs, learns a soft selection of edge types and composite relations for generating useful multi-hop connections so-called meta-paths. Our experiments show that GTNs learn new graph structures, based on data and tasks without domain knowledge, and yield powerful node representation via convolution on the new graphs. Without domain-specific graph preprocessing, GTNs achieved the best performance in all three benchmark node classification tasks against the state-of-the-art methods that require pre-defined meta-paths from domain knowledge.
255 citations
••
TL;DR: It is shown that trapdoor indistinguishability is a sufficient condition for thwarting keyword-guessing attacks and answers the open problem of how to construct PEKS (dPEKS) schemes that are provably secure against keyword-Guessing attacks.
254 citations
••
TL;DR: There was no significant difference in the efficacy or response rate between haloperidol and risperidone in the treatment of delirium, and no significant differences in mean Memorial Delirium Assessment Scale scores between groups were found.
254 citations
••
TL;DR: The enhancement and deterioration of the C(2)H(5)OH sensing characteristics by the introduction of the Ag decoration layer were strongly governed by the morphological configurations of theAg catalysts on SnO( 2) NWs and their sensitization mechanism.
Abstract: The effect of Ag decoration on the gas sensing characteristics of SnO(2) nanowire (NW) networks was investigated. The Ag layers with thicknesses of 5-50 nm were uniformly coated on the surface of SnO(2) NWs via e-beam evaporation, which were converted into isolated or continuous configurations of Ag islands by heat treatment at 450 °C for 2 h. The SnO(2) NWs decorated by isolated Ag nano-islands displayed a 3.7-fold enhancement in gas response to 100 ppm C(2)H(5)OH at 450 °C compared to pristine SnO(2) NWs. In contrast, as the Ag decoration layers became continuous, the response to C(2)H(5)OH decreased significantly. The enhancement and deterioration of the C(2)H(5)OH sensing characteristics by the introduction of the Ag decoration layer were strongly governed by the morphological configurations of the Ag catalysts on SnO(2) NWs and their sensitization mechanism.
254 citations
••
TL;DR: A direct adaptive state-feedback controller is proposed for highly nonlinear systems and employs a neural network with flexible structure, i.e., an online variation of the number of neurons that approximates and adaptively cancels an unknown plant nonlinearity.
Abstract: A direct adaptive state-feedback controller is proposed for highly nonlinear systems. We consider uncertain or ill-defined nonaffine nonlinear systems and employ a neural network (NN) with flexible structure, i.e., an online variation of the number of neurons. The NN approximates and adaptively cancels an unknown plant nonlinearity. A control law and adaptive laws for the weights in the hidden layer and output layer of the NN are established so that the whole closed-loop system is stable in the sense of Lyapunov. Moreover, the tracking error is guaranteed to be uniformly asymptotically stable (UAS) rather than uniformly ultimately bounded (UUB) with the aid of an additional robustifying control term. The proposed control algorithm is relatively simple and requires no restrictive conditions on the design constants for the stability. The efficiency of the proposed scheme is shown through the simulation of a simple nonaffine nonlinear system.
254 citations
Authors
Showing all 40083 results
Name | H-index | Papers | Citations |
---|---|---|---|
Anil K. Jain | 183 | 1016 | 192151 |
Hyun-Chul Kim | 176 | 4076 | 183227 |
Yongsun Kim | 156 | 2588 | 145619 |
Jongmin Lee | 150 | 2257 | 134772 |
Byung-Sik Hong | 146 | 1557 | 105696 |
Daniel S. Berman | 141 | 1363 | 86136 |
Christof Koch | 141 | 712 | 105221 |
David Y. Graham | 138 | 1047 | 80886 |
Suyong Choi | 135 | 1495 | 97053 |
Rudolph E. Tanzi | 135 | 638 | 85376 |
Sung Keun Park | 133 | 1567 | 96933 |
Tae Jeong Kim | 132 | 1420 | 93959 |
Robert S. Brown | 130 | 1243 | 65822 |
Mohammad Khaja Nazeeruddin | 129 | 646 | 85630 |
Klaus-Robert Müller | 129 | 764 | 79391 |