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
이 문서에서는 자기 공명 영상(MRI) 분류를 위한 모멘트 및 엔트로피 보존 기능을 갖춘 수정된 비용 함수를 사용하는 AHNN(Annealed Hopfield Neural Network)이라는 감독되지 않은 병렬 접근 방식의 적용에 대해 설명합니다. AHNN의 신경망 아키텍처는 원래의 2D Hopfield net과 동일합니다. 그리고 수정된 에너지 기능이 평형 상태로 수렴되도록 하기 위해 새로운 냉각 일정이 포함됩니다. 아이디어는 훈련 벡터와 클러스터 중심 벡터 사이의 유클리드 거리를 최소화하여 최적의 분류 기준을 선택하는 클러스터링 문제를 공식화하는 것입니다. 이 기사에서는 원본 이미지의 픽셀 강도, 이웃과 결합된 첫 번째 순간 및 회색 레벨 엔트로피를 사용하여 뉴런을 3차원 어닐링된 홉필드 네트에 매핑하는 XNUMX성분 훈련 벡터를 구성합니다. . 시뮬레이션된 어닐링 방법은 전역 최소값을 산출할 수 있지만 점근적 반복을 사용하면 시간이 많이 걸립니다. 또한, Hopfield나 모의 어닐링 신경망을 이용하여 최적의 문제를 해결하기 위해서는 페널티 항을 결합하는 가중치를 결정해야 한다. 최종 결과의 품질은 이러한 가중치에 매우 민감하며 이에 대한 실현 가능한 값을 찾기가 어렵습니다. 자기공명영상 분류를 위해 AHNN을 사용하면 에너지 함수에서 가중치를 찾을 필요성이 제거될 수 있으며 수렴 속도는 시뮬레이션 어닐링보다 훨씬 빠릅니다. 실험 결과는 컴퓨터 생성 이미지 분류에 있어 이전 접근 방식보다 AHNN을 사용하여 더 좋고 더 유효한 솔루션을 얻을 수 있음을 보여줍니다. 제안된 방법을 사용하여 MRI 분할의 유망한 솔루션을 얻을 수 있습니다. 또한 테스트 팬텀에서 다양한 냉각 일정에 따른 수렴 속도에 대해 설명합니다.
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
Jzau-Sheng LIN, "Annealed Hopfield Neural Network with Moment and Entropy Constraints for Magnetic Resonance Image Classification" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 1, pp. 100-108, January 2000, doi: .
Abstract: This paper describes the application of an unsupervised parallel approach called the Annealed Hopfield Neural Network (AHNN) using a modified cost function with moment and entropy preservation for magnetic resonance image (MRI) classification. In the AHNN, the neural network architecture is same as the original 2-D Hopfield net. And a new cooling schedule is embedded in order to make the modified energy function to converge to an equilibrium state. The idea is to formulate a clustering problem where the criterion for the optimum classification is chosen as the minimization of the Euclidean distance between training vectors and cluster-center vectors. In this article, the intensity of a pixel in an original image, the first moment combined with its neighbors, and their gray-level entropy are used to construct a 3-component training vector to map a neuron into a two-dimensional annealed Hopfield net. Although the simulated annealing method can yield the global minimum, it is very time-consuming with asymptotic iterations. In addition, to resolve the optimal problem using Hopfield or simulated annealing neural networks, the weighting factors to combine the penalty terms must be determined. The quality of final result is very sensitive to these weighting factors, and feasible values for them are difficult to find. Using the AHNN for magnetic resonance image classification, the need of finding weighting factors in the energy function can be eliminated and the rate of convergence is much faster than that of simulated annealing. The experimental results show that better and more valid solutions can be obtained using the AHNN than the previous approach in classification of the computer generated images. Promising solutions of MRI segmentation can be obtained using the proposed method. In addition, the convergence rates with different cooling schedules in the test phantom will be discussed.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_1_100/_p
부
@ARTICLE{e83-d_1_100,
author={Jzau-Sheng LIN, },
journal={IEICE TRANSACTIONS on Information},
title={Annealed Hopfield Neural Network with Moment and Entropy Constraints for Magnetic Resonance Image Classification},
year={2000},
volume={E83-D},
number={1},
pages={100-108},
abstract={This paper describes the application of an unsupervised parallel approach called the Annealed Hopfield Neural Network (AHNN) using a modified cost function with moment and entropy preservation for magnetic resonance image (MRI) classification. In the AHNN, the neural network architecture is same as the original 2-D Hopfield net. And a new cooling schedule is embedded in order to make the modified energy function to converge to an equilibrium state. The idea is to formulate a clustering problem where the criterion for the optimum classification is chosen as the minimization of the Euclidean distance between training vectors and cluster-center vectors. In this article, the intensity of a pixel in an original image, the first moment combined with its neighbors, and their gray-level entropy are used to construct a 3-component training vector to map a neuron into a two-dimensional annealed Hopfield net. Although the simulated annealing method can yield the global minimum, it is very time-consuming with asymptotic iterations. In addition, to resolve the optimal problem using Hopfield or simulated annealing neural networks, the weighting factors to combine the penalty terms must be determined. The quality of final result is very sensitive to these weighting factors, and feasible values for them are difficult to find. Using the AHNN for magnetic resonance image classification, the need of finding weighting factors in the energy function can be eliminated and the rate of convergence is much faster than that of simulated annealing. The experimental results show that better and more valid solutions can be obtained using the AHNN than the previous approach in classification of the computer generated images. Promising solutions of MRI segmentation can be obtained using the proposed method. In addition, the convergence rates with different cooling schedules in the test phantom will be discussed.},
keywords={},
doi={},
ISSN={},
month={January},}
부
TY - JOUR
TI - Annealed Hopfield Neural Network with Moment and Entropy Constraints for Magnetic Resonance Image Classification
T2 - IEICE TRANSACTIONS on Information
SP - 100
EP - 108
AU - Jzau-Sheng LIN
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2000
AB - This paper describes the application of an unsupervised parallel approach called the Annealed Hopfield Neural Network (AHNN) using a modified cost function with moment and entropy preservation for magnetic resonance image (MRI) classification. In the AHNN, the neural network architecture is same as the original 2-D Hopfield net. And a new cooling schedule is embedded in order to make the modified energy function to converge to an equilibrium state. The idea is to formulate a clustering problem where the criterion for the optimum classification is chosen as the minimization of the Euclidean distance between training vectors and cluster-center vectors. In this article, the intensity of a pixel in an original image, the first moment combined with its neighbors, and their gray-level entropy are used to construct a 3-component training vector to map a neuron into a two-dimensional annealed Hopfield net. Although the simulated annealing method can yield the global minimum, it is very time-consuming with asymptotic iterations. In addition, to resolve the optimal problem using Hopfield or simulated annealing neural networks, the weighting factors to combine the penalty terms must be determined. The quality of final result is very sensitive to these weighting factors, and feasible values for them are difficult to find. Using the AHNN for magnetic resonance image classification, the need of finding weighting factors in the energy function can be eliminated and the rate of convergence is much faster than that of simulated annealing. The experimental results show that better and more valid solutions can be obtained using the AHNN than the previous approach in classification of the computer generated images. Promising solutions of MRI segmentation can be obtained using the proposed method. In addition, the convergence rates with different cooling schedules in the test phantom will be discussed.
ER -