Search

Your search keyword '"Hyeon-min Shim"' showing total 2 results
Start Over Author "Hyeon-min Shim" Journal symmetry
2 results on '"Hyeon-min Shim"'

1. EMG Pattern Classification by Split and Merge Deep Belief Network

Author

Hyeon-min Shim, Hongsub An, Sanghyuk Lee, Eung Hyuk Lee, Hong-ki Min, and Sangmin Lee

Subjects
EMG pattern recognition, deep learning, deep belief network, split and merge deep belief network, SM-DBN, Mathematics, QA1-939
Abstract

In this paper; we introduce an enhanced electromyography (EMG) pattern recognition algorithm based on a split-and-merge deep belief network (SM-DBN). Generally, it is difficult to classify the EMG features because the EMG signal has nonlinear and time-varying characteristics. Therefore, various machine-learning methods have been applied in several previously published studies. A DBN is a fast greedy learning algorithm that can identify a fairly good set of weights rapidly—even in deep networks with a large number of parameters and many hidden layers. To reduce overfitting and to enhance performance, the adopted optimization method was based on genetic algorithms (GA). As a result, the performance of the SM-DBN was 12.06% higher than conventional DBN. Additionally, SM-DBN results in a short convergence time, thereby reducing the training epoch. It is thus efficient in reducing the risk of overfitting. It is verified that the optimization was improved using GA.

Published
2016
Full Text
View/download PDF

2. EMG Pattern Classification by Split and Merge Deep Belief Network

Author

Hong-Ki Min, Hyeon Min Shim, Sanghyuk Lee, Hongsub An, Eung Hyuk Lee, and Sang Min Lee

Subjects
EMG pattern recognition, deep learning, deep belief network, split and merge deep belief network, SM-DBN, Physics and Astronomy (miscellaneous), Computer science, General Mathematics, 0206 medical engineering, 02 engineering and technology, Overfitting, Machine learning, computer.software_genre, Deep belief network, 0202 electrical engineering, electronic engineering, information engineering, Computer Science (miscellaneous), business.industry, lcsh:Mathematics, Deep learning, lcsh:QA1-939, 020601 biomedical engineering, Nonlinear system, Chemistry (miscellaneous), 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, Merge (linguistics)
Abstract

In this paper; we introduce an enhanced electromyography (EMG) pattern recognition algorithm based on a split-and-merge deep belief network (SM-DBN). Generally, it is difficult to classify the EMG features because the EMG signal has nonlinear and time-varying characteristics. Therefore, various machine-learning methods have been applied in several previously published studies. A DBN is a fast greedy learning algorithm that can identify a fairly good set of weights rapidly—even in deep networks with a large number of parameters and many hidden layers. To reduce overfitting and to enhance performance, the adopted optimization method was based on genetic algorithms (GA). As a result, the performance of the SM-DBN was 12.06% higher than conventional DBN. Additionally, SM-DBN results in a short convergence time, thereby reducing the training epoch. It is thus efficient in reducing the risk of overfitting. It is verified that the optimization was improved using GA.

Published
2016

Catalog

Books, media, physical & digital resources
See catalog results