The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
본 논문에서는 시계열 분석 및 분류에 전념하는 Temporal-CombNET(T-CombNET)이라는 새로운 신경망 구조를 제시합니다. 일본어 문자 인식과 같은 매우 큰 어휘를 처리하도록 설계된 대규모 신경망 구조인 CombNET-II에서 개발되었습니다. 원래 CombNET-II 모델의 특정 수정을 통해 시간 분석을 수행하고 대규모 인간 움직임 인식 시스템에 사용할 수 있습니다. T-CombNET 구조에서 설정해야 할 가장 중요한 매개변수 중 하나는 공간 분할 기준입니다. 본 논문에서는 몇 가지 실용적인 접근법을 분석하고 클래스 간 거리 측정 기반 기준을 제시합니다. T-CombNET 성능을 실제 문제에 일본어 가나 손가락 맞춤법 인식에 적용하여 분석하였다. 얻은 결과는 다층 퍼셉트론, 학습 벡터 양자화, Elman 및 Jordan 부분 순환 신경망, CombNET-II, k-NN 및 제안된 T-CombNET 구조와 같은 다른 신경망 구조와 비교할 때 우수한 인식률을 보여줍니다. .
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Marcus Vinicius LAMAR, Md. Shoaib BHUIYAN, Akira IWATA, "Hand Gesture Recognition Using T-CombNET: A New Neural Network Model" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 11, pp. 1986-1995, November 2000, doi: .
Abstract: This paper presents a new neural network structure, called Temporal-CombNET (T-CombNET), dedicated to the time series analysis and classification. It has been developed from a large scale Neural Network structure, CombNET-II, which is designed to deal with a very large vocabulary, such as Japanese character recognition. Our specific modifications of the original CombNET-II model allow it to do temporal analysis, and to be used in large set of human movements recognition system. In T-CombNET structure one of most important parameter to be set is the space division criterion. In this paper we analyze some practical approaches and present an Interclass Distance Measurement based criterion. The T-CombNET performance is analyzed applying to in a practical problem, Japanese Kana finger spelling recognition. The obtained results show a superior recognition rate when compared to different neural network structures, such as Multi-Layer Perceptron, Learning Vector Quantization, Elman and Jordan Partially Recurrent Neural Networks, CombNET-II, k-NN, and the proposed T-CombNET structure.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_11_1986/_p
부
@ARTICLE{e83-d_11_1986,
author={Marcus Vinicius LAMAR, Md. Shoaib BHUIYAN, Akira IWATA, },
journal={IEICE TRANSACTIONS on Information},
title={Hand Gesture Recognition Using T-CombNET: A New Neural Network Model},
year={2000},
volume={E83-D},
number={11},
pages={1986-1995},
abstract={This paper presents a new neural network structure, called Temporal-CombNET (T-CombNET), dedicated to the time series analysis and classification. It has been developed from a large scale Neural Network structure, CombNET-II, which is designed to deal with a very large vocabulary, such as Japanese character recognition. Our specific modifications of the original CombNET-II model allow it to do temporal analysis, and to be used in large set of human movements recognition system. In T-CombNET structure one of most important parameter to be set is the space division criterion. In this paper we analyze some practical approaches and present an Interclass Distance Measurement based criterion. The T-CombNET performance is analyzed applying to in a practical problem, Japanese Kana finger spelling recognition. The obtained results show a superior recognition rate when compared to different neural network structures, such as Multi-Layer Perceptron, Learning Vector Quantization, Elman and Jordan Partially Recurrent Neural Networks, CombNET-II, k-NN, and the proposed T-CombNET structure.},
keywords={},
doi={},
ISSN={},
month={November},}
부
TY - JOUR
TI - Hand Gesture Recognition Using T-CombNET: A New Neural Network Model
T2 - IEICE TRANSACTIONS on Information
SP - 1986
EP - 1995
AU - Marcus Vinicius LAMAR
AU - Md. Shoaib BHUIYAN
AU - Akira IWATA
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2000
AB - This paper presents a new neural network structure, called Temporal-CombNET (T-CombNET), dedicated to the time series analysis and classification. It has been developed from a large scale Neural Network structure, CombNET-II, which is designed to deal with a very large vocabulary, such as Japanese character recognition. Our specific modifications of the original CombNET-II model allow it to do temporal analysis, and to be used in large set of human movements recognition system. In T-CombNET structure one of most important parameter to be set is the space division criterion. In this paper we analyze some practical approaches and present an Interclass Distance Measurement based criterion. The T-CombNET performance is analyzed applying to in a practical problem, Japanese Kana finger spelling recognition. The obtained results show a superior recognition rate when compared to different neural network structures, such as Multi-Layer Perceptron, Learning Vector Quantization, Elman and Jordan Partially Recurrent Neural Networks, CombNET-II, k-NN, and the proposed T-CombNET structure.
ER -