• 제어로봇시스템학회논문지
• /
• 제17권8호
• /
• pp.731-738
• /
• 2011

In this paper, we introduce an advanced architecture of K-Means clustering-based polynomial Radial Basis Function Neural Networks (p-RBFNNs) designed with the aid of SSOA (Space Search Optimization Algorithm) and develop a comprehensive design methodology supporting their construction. In order to design the optimized p-RBFNNs, a center value of each receptive field is determined by running the K-Means clustering algorithm and then the center value and the width of the corresponding receptive field are optimized through SSOA. The connections (weights) of the proposed p-RBFNNs are of functional character and are realized by considering three types of polynomials. In addition, a WLSE (Weighted Least Square Estimation) is used to estimate the coefficients of polynomials (serving as functional connections of the network) of each node from output node. Therefore, a local learning capability and an interpretability of the proposed model are improved. The proposed model is illustrated with the use of nonlinear function, NOx called Machine Learning dataset. A comparative analysis reveals that the proposed model exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• 전자공학회논문지B
• /
• 제31B권9호
• /
• pp.159-165
• /
• 1994

In this paper, we propose a multi-layer associative neural network structure suitable for hardware implementaion with the function of performance refinement and improved robutst capability. Unlike other methods which reduce network complexity by putting restrictions on synaptic weithts, we are imposing a requirement of hidden layer neurons for the function. The proposed network has synaptic weights obtainted by Hebbian rule between adjacent layer's memory patterns such as Kosko's BAM. This network can be extended to arbitary multi-layer network trainable with Genetic algorithm for getting hidden layer memory patterns starting with initial random binary patterns. Learning is done to minimize newly defined network error. The newly defined error is composed of the errors at input, hidden, and output layers. After learning, we have bidirectional recall process for performance improvement of the network with one-shot recall. Experimental results carried out on pattern recognition problems demonstrate its performace according to the parameter which represets relative significance of the hidden layer error over the sum of input and output layer errors, show that the proposed model has much better performance than that of Kosko's bidirectional associative memory (BAM), and show the performance increment due to the bidirectionality in recall process.

• Journal of Ship and Ocean Technology
• /
• 제12권4호
• /
• pp.1-6
• /
• 2008

Nowadays, the computational capability and graphical power based on PCs increase very rapidly every year. As a result, the complicated engineering or scientific problems that could have only been handled by supercomputers a couple of decades ago can now be routinely run on PCs. Besides, the PCs can be assembled in parallel to increase its computational capability theoretically without limitation. The Web-based interface and communication tools are also being enhanced very rapidly and the real-time distance learning (E-Learning) and project cooperation on web get increasing attention. Using the-state-of-the-art computational method, a number of complicated and computationally intensive problems are being solved by PCs. The results can be well demonstrated on screen by graphics and animation tools. Those examples include the simulations of fully nonlinear waves, their interactions with floating bodies, global-motion analysis of multi-unit floating production system including complicated mooring lines and risers. Several examples will be presented in this regard. Also, Web and java-applet based educational tools have been developed at Texas A&M University for better understanding of waves and wave-body interactions. The background and examples of such Web-based educational tools published in Kim et al. (2003) are briefly introduced here.

• The Journal of Asian Finance, Economics and Business
• /
• 제6권1호
• /
• pp.149-158
• /
• 2019

Due to the rapid development of IT (information technology) and internet, products become smart and able to collect, process and produce information and can think of themselves to provide better service to consumers. However, research on the characteristics of smart product is still sparse. In this paper, we report the systemic development of a scale to measure the perceived product smartness associated with smart product. To develop product smartness scale, this study follows systemic scale development processes of item generation, item reduction, scale validation, reliability and validity test consequently. And, after acquiring a large amount of qualitative interview data asking the definition of smart product, we add a unique process to reduce the initial items using both a text mining method using 'r' s/w and traditional reliability and validity tests including factor analysis. Based on an initial qualitative inquiry and subsequent quantitative survey, an eight-factor scale of product smartness is developed. The eight factors are multi-functionality, human-like touch, ability to cooperate, autonomy, situatedness, network connectivity, integrity, and learning capability consequently. Results from Korean samples support the proposed measures of product smartness in terms of reliability, validity, and dimensionality. Implications and directions for further study are discussed. The developed scale offers important theoretical and pragmatic implications for researchers and practitioners.

• 농촌지도와개발
• /
• 제29권1호
• /
• pp.19-31
• /
• 2022

This study aims to examine the moderating effect of regional agricultural leader's capacity between the sense of community of female farmers and the resident participation. A survey was conducted on 312 female farmers from October 20 to November 19, 2020. The main results of the analysis are as follows. First, it showed that the higher the sense of community, the higher the awareness of resident participation. Second, it was found that the sense of community had a positive effect on resident participation as self-directed learning capability was higher, and that self-directed learning capability had a moderating effect on the relationship between the sense of community and the resident participation. Third, regional agricultural leadership capacity was found to have a moderating effect in the relationship between the sense of community and the resident participation.

• 정보처리학회논문지D
• /
• 제13D권3호
• /
• pp.425-436
• /
• 2006

정형화된 교육 절차에 따라 학습을 수행하고 종료하는 방식의 e-learning으로는 학습자의 수준에 맞는 적절한 교육을 제공하기 어렵다. 이와 같은 문제점을 해결하기 위해 SCORM에서는 학습 결과에 따라 학습 절차를 규정하는 시퀀싱을 활용하여 학습자의 수준에 맞는 적절한 교육을 제공한다. 일반적으로 시퀀싱 설계는 교수자나 학습 저작자가 담당하여 학습 프로그램을 규칙화한다. 그러나 정형화된 시퀀싱은 학습 집단이나 학습자의 특성을 반영하지 못하며, 잘못된 시퀀싱이 설계되었을 경우에 학습자들이 불필요한 재학습을 수행해야 한다. 본 논문에서는 이와 같은 문제점을 해결하기 위해 동적 시퀀싱을 적용한 학습 평가 자동화 시스템을 제안한다. 동적 시퀀싱에서는 학습자들의 평가점수가 시퀀싱에서 활용하는 기준점수에 반영되어 기준점수를 동적으로 변화시킨다. 기준점수를 동적으로 변화시킴으로 시퀀싱은 학습 집단이나 학습자들의 수준에 맞게 동적으로 변화된다. 본 논문에서는 몇 가지 실험을 통하여 제안한 동적 시퀀싱을 적용한 학습 평가 자동화 시스템이 학습 집단이나 학습자의 수준에 적합한 교육 절차를 제공함을 보였다.

• 벤처창업연구
• /
• 제15권1호
• /
• pp.185-195
• /
• 2020

본 연구에서는 중소벤처기업의 기술혁신역량과 신제품개발성과가 상호 인과관계가 있음을 밝히고, 기술혁신역량을 강화하기 위한 수단으로 협업을 도입하면 신제품개발성과가 향상됨을 규명하였다. 연구방법으로는 국내 소재 중소벤처기업 R&D업무에 종사하는 실무담당자들을 대상으로 설문조사를 실시하였다. 연구결과, 중소 벤처기업의 기술혁신역량에 속하는 기술전략, 기술학습, 그리고 개방형 혁신이 신제품개발성과에 영향을 미치는 것으로 나타났다. 즉 신제품개발성과에 미치는 다수의 핵심전략으로서 협업을 선택한 결과, 협업이 신제품개발성과에 영향을 주는 전략임을 규명하였다. 아울러 협업을 도입하면 기술혁신역량이 신제품개발성과를 강화하는데 조절역할을 하는 지도 함께 살펴보았는데, 일반적인 협업은 기술전략 강화에는 직접적인 영향을 미치지 않지만, 협업에 따라서는 기술전략과 개방형 혁신이 강화되어 신제품개발성과의 크기에 긍정적인 영향을 주는 것으로 평가되었다.

• 한국건설관리학회논문집
• /
• 제20권5호
• /
• pp.31-41
• /
• 2019

본 연구의 목적은 건설기술인력의 일터학습 참여 실태와 더불어 일터학습의 하위유형인 형식학습과 무형식학습이 각각 건설기술인력의 인적자원성과에 어떠한 영향을 미치는가를 살펴보는 것이다. 이를 위해 본 연구에서는 2015년 한국직업능력개발원의 6차 인적자본기업패널조사 근로자용 설문자료에서 건설기술인력 306명의 응답치를 선택하여 활용하였다. 연구 결과, 건설기술인력의 일터학습(형식학습, 무형식학습) 참여는 10,069명 전체 근로자에 비해 상대적으로 낮은 수준에 머물러 있으며, 특히 무형식 학습의 참여는 더욱 낮은 수준이었다. 회귀분석 결과를 보면 형식학습의 참여는 직무만족과 직무몰입에만 정(+)의 영향을, 직무능력의 향상에는 영향을 미치지 못하는 것으로 나타났다. 반면에 무형식학습은 직무능력, 직무만족, 조직몰입 모두에 정(+)의 영향을 미치는 것으로 나타났으며 또한 형식학습에 비해 더욱 큰 영향을 미치는 것으로 나타났다.

• 디지털콘텐츠학회 논문지
• /
• 제7권4호
• /
• pp.257-261
• /
• 2006

본 논문에서는 한글의 자음과 모음을 별도로 분류 한 후, 자음과 모음을 실시간으로 조합하여 단어를 만드는 퍼즐게임을 구현하였다. 단어 조합기는 API 에서 지원하는 에디터를 이용하여 구현하였고, 효율적인 조합단어의 검색을 위하여 초기 합성소 자음기반 방식을 이용하였다. 구현된 한글 조합 퍼즐게임은 아동들의 단어 학습 능력의 향상과 한글과 친해질 수 있는 기대 효과를 갖는다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권8호
• /
• pp.495-497
• /
• 2005

Recently Neural Network techniques have widely used in adaptive and learning control schemes for production systems. However, generally it costs a lot of time for learning in the case applied in control system. Furthermore, the physical meaning of neural networks constructed as a result is not obvious. And this method has been used as a learning algorithm to estimate the parameter of a neural network used for identification of the process dynamics of s signal input and signal output system and it was shown that this method offered superior capability over the conventional back propagation algorithm. This controller is designed by using three-layered neural networks. The effectiveness of the proposed Neural Network-based control scheme is investigated through an application for a production control system. This control method can enable a plant to operate smoothy and obviously as the plant condition varies with any unexpected accident. This paper goal estimate input signal about controller using neural networks.