• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.5
• /
• pp.102-108
• /
• 1996

Adaptive resonance theory (ART2) characterized by its built-in mechanism of handling the stability-plasticity switching and by the adaptive learning without forgetting informations learned in the past, is based on an unsupervised template matching. We propose an improved tow-stage learning algorithm for aRT2: the original unsupervised learning followed by a new supervised learning. Each of the output nodes, after the unsupervised learning, is labeled according to the category informations to reinforce the template pattern associated with the target output node belonging to the same category some dominant classes from exhausting a finite number of template patterns in ART2 inefficiently. Experimental results on a set of 2545 FLIR images show that the ART2 trained by the two-stage learning algorithm yields better accuracy than the original ART2, regardless of th esize of the network and the methods of evaluating the accuracy. This improvement shows the effectiveness of the two-stage learning process.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.4
• /
• pp.569-574
• /
• 2013

With probably too many smart phone applications downloaded, it is sometimes frustrating to find frequently used applications quickly. In this paper, we propose a learning application that learns what applications a user frequently uses and match them with several signals that user designated. This learning applications uses ART2 algorithm that is good for stable real-time learning. By executing this learning application, a user simply chooses an application that is to be quickly searched and then draw a figure that would match the designated application at the upper left corner of our learning application. The proposed learning application transforms the background with 0's and the figure with 1's and normalize them to be used as inputs for ART2 and ART2 does clustering to setup a match table between applications and figures. After learning, a user simply draws a figure to execute one's frequently used application.

• International Journal of Contents
• /
• v.18 no.2
• /
• pp.58-67
• /
• 2022

As the Internet rapidly evolves, online learning has emerged as the third largest scenario in the field of education. Online education, different from the two traditional learning scenarios of the school and society, is characterized with broader learning types and higher freedom. In today's post-pandemic era, art education, which relies on face-to-face teaching, is of particular significance to expand online education methods. Based on the UTAUT model, this paper posits seven hypotheses about the willingness to continue learning in online art education. After collecting valid data through a questionnaire, a detailed empirical analysis was conducted via SPSS and AMOS. The results of empirical analysis show that less than half of the respondents had experienced the online art education, mirroring that this is a market worth developing. Based on the findings, learning habit does not significantly impact art learners' willingness to continue learning online. This result and other verified hypotheses are detailed in the discussion part of this paper. This study proves that UTAUT can better explain user behavior than the traditional information system model prior to the improvement, and also has strong explanatory power in the field of art education. The conclusion also posits some operational suggestions from the perspective of practitioners in this field, thereby providing a theoretical basis for art education practitioners.

• Proceedings of the KAIS Fall Conference
• /
• 2003.11a
• /
• pp.84-87
• /
• 2003

This paper proposes the enhanced REF network, which arbitrates learning rate and momentum dynamically by using the fuzzy system, to arbitrate the connected weight effectively between the middle layer of REF network and the output layer of REF network. ART2 is applied to as the learning structure between the input layer and the middle layer and the proposed auto-turning method of arbitrating the learning rate as the method of arbitrating the connected weight between the middle layer and the output layer. The enhancement of proposed method in terms of learning speed and convergence is verified as a result of comparing it with the conventional delta-bar-delta algorithm and the REF network on the basis of the ART2 to evaluate the efficiency of learning of the proposed method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.2C
• /
• pp.31-40
• /
• 2005

we propose an enhanced self-generation supervised algorithm that by combining an ART algorithm and the delta-bar-delta method. Form the input layer to the hidden layer, ART-1 and ART-2 are used to produce nodes, respectively. A winner-take-all method is adopted to the connection weight adaption so that a stored pattern for some pattern is updated. we test the recognition of student identification, a certificate of residence, and an identifier from container that require nodes of hidden layers in neural network. In simulation results, the proposed self-generation supervised learning algorithm reduces the possibility of local minima and improves learning speed and paralysis than conventional neural networks.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.7
• /
• pp.1380-1386
• /
• 2007

This paper proposed an automatic recognition system of shipping container identifiers using fuzzy-based noise removal method and ART2-based self-organizing supervised learning algorithm. Generally, identifiers of a shipping container have a feature that the color of characters is blacker white. Considering such a feature, in a container image, all areas excepting areas with black or white colors are regarded as noises, and areas of identifiers and noises are discriminated by using a fuzzy-based noise detection method. Areas of identifiers are extracted by applying the edge detection by Sobel masking operation and the vertical and horizontal block extraction in turn to the noise-removed image. Extracted areas are binarized by using the iteration binarization algorithm, and individual identifiers are extracted by applying 8-directional contour tacking method. This paper proposed an ART2-based self-organizing supervised learning algorithm for the identifier recognition, which improves the performance of learning by applying generalized delta learning and Delta-bar-Delta algorithm. Experiments using real images of shipping containers showed that the proposed identifier extraction method and the ART2-based self-organizing supervised learning algorithm are more improved compared with the methods previously proposed.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.04b
• /
• pp.451-456
• /
• 1995

This study investigates the feasibility of the real time detection of tool breadage in face milling operation. The proposed methodology using an ART2 neural network overcomes a cumbersome task in terms of the learning or determining a threshold value. The features taken in the researchare the AR parameters modelled from a RLS, and those are proven to be good features for tool breakage from experiments. From the results of the off line application, we can conclude that an ART2 neural network can be well applied to the clustering of tool states in real time regardless of the unsupervised learning.

• Journal of Korean Clinical Health Science
• /
• v.2 no.4
• /
• pp.231-238
• /
• 2014

Purpose. This study examines the effects of improving students self-esteem and sociability by conducting a Group Art Therapy Program for students with learning disabilities. This study focused on three students with learning disabilities, attending B middle school special education class located in K county. The study was conducted for two hours once a week (Friday) at B middle school during special education class from May 2, 2014 to July 18, 2014. Methods. For the tools of studying, Self-esteem and social strip forms/rubrics were filled, by students', before and after and data processing was inspected, paired t-Test using the SPSS / WIN (Ver.18.0) for quantitative analysis. Also, on the basis of content, analyzed data of the individuals' self-esteem social changes are shown in graph format. In addition, this qualitative study shows before and after of dynamic house, tree, person (K-H, T, P), dynamic family (KFD), dynamic school life of search phase (4-6 sessions) significant improvement of self-esteem and sociability in adolescents' with learning disabilities influenced by conducting a Group Art Therapy Program. Results. The result of this study can be summarized as follows. First, Group Art Therapy Program shows a statistically significant difference (p<.05) showing that self esteem average is 2.04 before Group Art Therapy Intervention but self esteem average is 2.92 after Group Art Therapy Intervention. Second, as a result of social strip pre-post, there wasn't statistically significant difference compared to self esteem pre-post result, although, post examination's average level was enhanced after Group Art Therapy Program in difference examination.(p>.05). Third, as a result of analysis the indicated pre-post change of Students' pre-post dynamic house, tree, person (HTP), dynamic family (KFD), a dynamic school daily life (KSD), students' family and interpersonal relationships, self-concept shows statistical significant changes. Conclusion. As the result of this study, Group Art Therapy Program shows effective improvement in students' self-esteem and social skills learning disabilities. However, a future study on larger and more diverse group of students' with learning disabilities are advised to be conducted in order to better understand the significance of the Group Art Therapy Program.

• Journal of the Korean Society of Food Culture
• /
• v.35 no.2
• /
• pp.173-180
• /
• 2020

This study evaluated methods of improving sustained learning participation by examining the structural relationship of school support consisting of professor support, friend-senior support and educational environment support, career decisionmaking self-efficacy, school satisfaction, and learning persistence depending on the characteristics of college students majoring in culinary art and food service. The study findings were as follows. First, the general characteristics of college students majoring in culinary art and food service were perceived significantly more by female students than by male students. Second, school support directly influenced the career decision-making self-efficacy and school satisfaction, but did not directly influence the learning persistence. Instead, school support influenced school satisfaction and learning persistence indirectly by the medium of career decision-making self-efficacy. Third, career decision-making self-efficacy directly influenced school satisfaction and learning persistence and indirectly influenced learning persistence by the medium of school satisfaction. Lastly, school satisfaction directly influenced the learning persistence, implying that school satisfaction is an important factor for the learning persistence of college students majoring in culinary art and food service. These results show that, because school members and environmental support cannot exclusively make learning persistence, diverse systems and programs must be developed and applied to improve the career decision-making self-efficacy and school satisfaction of college students majoring in culinary art and food service.

• Journal of Korea Multimedia Society
• /
• v.9 no.3
• /
• pp.369-376
• /
• 2006

In this paper, we propose an improved fuzzy RBF network which dynamically adjusts the rate of learning by applying the Delta-bar-Delta algorithm in order to improve the learning performance of fuzzy RBF networks. The proposed learning algorithm, which combines the fuzzy C-Means algorithm with the generalized delta learning method, improves its learning performance by dynamically adjusting the rate of learning. The adjustment of the learning rate is achieved by self-generating middle-layered nodes and by applying the Delta-bar-Delta algorithm to the generalized delta learning method for the learning of middle and output layers. To evaluate the learning performance of the proposed RBF network, we used 40 identifiers extracted from a container image as the training data. Our experimental results show that the proposed method consumes less training time and improves the convergence of teaming, compared to the conventional ART2-based RBF network and fuzzy RBF network.