http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
The Design of Genetically Optimized Multi-layer Fuzzy Neural Networks
Park, Byoung-Jun,Park, Keon-Jun,Lee, Dong-Yoon,Oh, Sung-Kwun Korean Institute of Intelligent Systems 2004 한국지능시스템학회논문지 Vol.14 No.5
In this study, a new architecture and comprehensive design methodology of genetically optimized Multi-layer Fuzzy Neural Networks (gMFNN) are introduced and a series of numeric experiments are carried out. The gMFNN architecture results from a synergistic usage of the hybrid system generated by combining Fuzzy Neural Networks (FNN) with Polynomial Neural Networks (PNN). FNN contributes to the formation of the premise part of the overall network structure of the gMFNN. The consequence part of the gMFNN is designed using PNN. The optimization of the FNN is realized with the aid of a standard back-propagation learning algorithm and genetic optimization. The development of the PNN dwells on the extended Group Method of Data Handling (GMDH) method and Genetic Algorithms (GAs). To evaluate the performance of the gMFNN, the models are experimented with the use of a numerical example.
Polymorphisms of Mitochondrial DNA Sequences in Somatic Cell Nuclear Transfer Calves
Byoung-Chul Yang,Seongsoo Hwang,Keon-Bong Oh,Chi-Hun Park,Eung-Woo Park,Soo-Bong Park,Dong-Hoon Kim,Tae-Uk Kwak,Sung-Soo Lee,Moon-Suck Ko,Sang-Hyun Han 한국동물번식학회 2009 Reproductive & Developmental Biology(Supplement) Vol.33 No.2s
The Design of Genetically Optimized Multi-layer Fuzzy Neural Networks
Byoung-Jun Park,Keon-Jun Park,Dong-Yoon Lee,Sung-Kwun Oh 한국지능시스템학회 2004 한국지능시스템학회논문지 Vol.14 No.5
In this study, a new architecture and comprehensive design methodology of genetically optimized Multi-layer Fuzzy Neural Networks (gMFNN) are introduced and a series of numeric experiments are carried out. The gMFNN architecture results from a synergistic usage of the hybrid system generated by combining Fuzzy Neural Networks (FNN) with Polynomial Neural Networks (PNN). FNN contributes to the formation of the premise part of the overall network structure of the gMFNN. The consequence part of the gMFNN is designed using PNN. The optimization of the FNN is realized with the aid of a standard back-propagation learning algorithm and genetic optimization. The development of the PNN dwells on the extended Group Method of Data Handling (GMDH) method and Genetic Algorithms (GAs). To evaluate the performance of the gMFNN, the models are experimented with the use of a numerical example.
Automated system for evaluating consistency between CAD model and 3D scan of vehicle seat
Byoung-Keon D. Park,박장운,Byung Cheol Lee,이백희 대한기계학회 2022 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.36 No.2
Reducing the number of design changes in vehicle seat development is critical for minimizing both production cost and product lead time. Generally, discrepancies in measured dimensional specifications of vehicle-seat prototypes and computer-aided design (CAD) models cause significant quality control issues of the finished products. Although threedimensional (3D) scanning technology enables the efficient evaluations and inspection processes of vehicle-seat prototypes, many evaluation processes require time-consuming tasks. This paper proposes an automated system for evaluating a geometrical consistency between a 3D scan of a prototype and the original CAD model. In the current study, the existing evaluation processes conducted by seat engineers were examined by survey questionnaires. The survey responses were analyzed to define a standardized evaluation process for the automated system. Various computational algorithms, including a function-based scan-to-CAD registration, standard seat dimension estimation, and template-based reporting algorithms, were developed to evaluate the scan and CAD consistency automatically. The developed system not only reduced over 99 % of the evaluation time (on average, existing method: > 2 hrs per seat and system method: < 5 min per seat) but also increased the repeatability of evaluations. Furthermore, the system can collect dimensions of diverse seat designs, prototypes, and products to construct a database of seat dimensions for benchmarking and design improvement.
내측개방형 근위경골절골술의 경골절단면 및 경골개방축의 설정에 따른 영향
박병건(Byoung-Keon Park),이호상(Ho-sang Lee),김재정(Jay-Jung Kim),김철웅(Cheol-Woong Kim) 대한기계학회 2011 大韓機械學會論文集A Vol.35 No.8
최근 보편화 되고 있는 내측개방형절골술 시에 의도하지 않은 경골후방경사각의 변화로 인한 문제점들이 보고되었다. 이를 해결하기 위해 많은 연구들이 진행되어 왔지만 환자의 다양한 경골의 형상 및 절단면의 기울기에 적용될 수 있는 일반적 해석 모델은 아직 제안되지 못하고 있다. 따라서 본 논문에서는 일반적인 케이스에 적용할 수 있는 근위경골절골술의 해석 모델을 제안한다. 이를 위해 내반교정각만을 조정할 수 있는 가상경골축을 정의하고, 이를 통해 절단면과 경골개방축이 내반교정각에 주는 영향을 나타내는 수학적 모델을 제안하고, 기존의 수술적인 변수들간의 상관관계를 명확히 나타내었다. 또한 내반교정각과 경골후방경사각에 추가로, 새로운 각도인 경골뒤틀림각의 존재를 도입함으로써 수술 시 발생하는 모든 기하학적 변수들간의 관계를 완성된 형태로 표현하였다. In medial opening wedge high tibial osteotomy (OWHTO), researchers have reported critical problems caused by unexpected changes in the tibial posterior-slope angle. This unexpected change can be analyzed, but there is no general solution for cases with an oblique hinge axis and cut plane. We propose a general analysis model for OWHTO. We first evaluate the effects according to variation in the hinge axis and tibial cut plane and then define an ideal correction axis. This ideal axis, called the virtual tibial correction axis, is not on the tibial cut plane in general. In this paper, we also present an evaluation of feasibility of the proposed analysis model.