Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Hyunjoong Cho"'
Publikováno v:
IEEE Access, Vol 10, Pp 39769-39781 (2022)
This study presents a deep neural network (DNN)-based safety monitoring method. Nonstationary objects such as moving workers, heavy equipment, and pallets were detected, and their trajectories were tracked. Time-varying safety zones (SZs) of moving o
Externí odkaz:
https://doaj.org/article/d62bd3eddc33410daa7aa0ed819fc785
Publikováno v:
IEEE Access, Vol 6, Pp 72173-72178 (2018)
How we perceive property of surfaces with distinct geometry and reflectance under various illumination conditions is not fully understood. One widely studied approach to understanding perceptual surface property is to derive statistics from images of
Externí odkaz:
https://doaj.org/article/f420505abe1e458b940853c8ff23ddcf
Publikováno v:
Neural Networks. 134:95-106
In this study, we present a neural network that consists of nodes with heterogeneous sensitivity. Each node in a network is assigned a variable that determines the sensitivity with which it learns to perform a given task. The network is trained via a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d1823a64b64aa0e149735ae2c928e8a8
https://doi.org/10.1016/j.neunet.2020.10.017
https://doi.org/10.1016/j.neunet.2020.10.017
Publikováno v:
Neural networks : the official journal of the International Neural Network Society. 126
In this study, we present deep neural networks with a set of node-wise varying activation functions. The feature-learning abilities of the nodes are affected by the selected activation functions, where the nodes with smaller indices become increasing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::033f522bcea19ba21c82f9d2c50c8e51
https://pubmed.ncbi.nlm.nih.gov/32203875
https://pubmed.ncbi.nlm.nih.gov/32203875
Publikováno v:
IEEE transactions on cybernetics. 49(2)
This paper presents a recurrent learning-based facial attribute recognition method that mimics human observers’ visual fixation. The concentrated views of a human observer while focusing and exploring parts of a facial image over time are generated
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::52aa386737ff242258f31d3e04c3c777
https://pubmed.ncbi.nlm.nih.gov/29993966
https://pubmed.ncbi.nlm.nih.gov/29993966
Autor:
Hyunjoong Cho, Taylan Altan
Publikováno v:
Journal of Materials Processing Technology. 170:64-70
An inverse analysis technique has been introduced to obtain the flow stress of the bulk and sheet materials at elevated temperatures. The inverse problem is defined as the minimization of the differences between the experimental measurements and the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::93c7d3cf811a326237700ca3a46ef2c9
https://doi.org/10.1016/j.jmatprotec.2005.04.091
https://doi.org/10.1016/j.jmatprotec.2005.04.091
Publikováno v:
steel research international. 76:191-198
This paper presents an overview on the application of FE simulation as a virtual manufacturing tool in designing manufacturing processes for precision parts. The processes discussed include forging, sheet metal forming and hydroforming. Determination
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::17cd165bf8ee33ba53ff3452847f02f8
https://doi.org/10.1002/srin.200505995
https://doi.org/10.1002/srin.200505995
Autor:
Gracious Ngaile, Taylan Altan, John Balconi, Hyunjoong Cho, W.J. Worrell, Manas Shirgaokar, Richard Rentfrow, Jang-Horng Yu
Publikováno v:
Journal of Materials Processing Technology. 146:35-43
The crimping process is used often in the assembly of tubular components. In this study, with the aid of the finite-element method (FEM), the mechanical crimping operation was evaluated and optimized for a specific application. The effect of various
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c92e0f8977fbd1f6473e8763ed93a952
https://doi.org/10.1016/s0924-0136(03)00842-2
https://doi.org/10.1016/s0924-0136(03)00842-2
