• Journal of Korean Home Economics Education Association
• /
• v.8 no.1
• /
• pp.51-57
• /
• 1996

The purpose of this study were to examine the difference of the effect of CAI and students’attitude to Home Economics Class through CAI. 120 girl students of the first year were chosen at B middle school in Daegu. Among them each 30 students were classified into 4 groups； High Intelligence group/Individual learning pattern, High Intelligence group/Small group learning pattern, Low Intelligence group/Individual learning pattern, Low Intelligence group/Small group learning pattern. The task of learning was “management of washing”Unit of the second grade. The data were processed with Cronbach’s ${\alpha}$, t-test, ANOVA by SPSS/PC(sup)+. The research findings are as follows： 1. In the verification of CAI Learning effect according to student group pattern, there is no difference between Individual learning pattern and Small group learning pattern in Achivement and Retention of learning. 2. In the verification of CAI Learning effect according to student intelligence level, there is no difference between High Intelligence group and Low Intelligence group in Achivement and Retention of learning. 3. The result of students’attitude to Home Economics Class verificated is an follows. (1) Individual learning pattern is more attensive than Small group learning pattern, but there is no difference in Intelligence level. (2) Low Intelligence group is more positive than High Intelligence group, and Small group learning pattern is more positive than Individual learning pattern in a view of Home Economics Class after using CAI.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.7
• /
• pp.675-679
• /
• 2001

In this paper, we present a new competitive learning algorithm called Dynamic Competitive Learning (DCL). DCL is a supervised learning method that dynamically generates output neurons and initializes automatically the weight vectors from training patterns. It introduces a new parameter called LOG (Limit of Grade) to decide whether an output neuron is created or not. If the class of at least one among the LOG number of nearest output neurons is the same as the class of the present training pattern, then DCL adjusts the weight vector associated with the output neuron to learn the pattern. If the classes of all the nearest output neurons are different from the class of the training pattern, a new output neuron is created and the given training pattern is used to initialize the weight vector of the created neuron. The proposed method is significantly different from the previous competitive learning algorithms in the point that the selected neuron for learning is not limited only to the winner and the output neurons are dynamically generated during the learning process. In addition, the proposed algorithm has a small number of parameters, which are easy to be determined and applied to real-world problems. Experimental results for pattern recognition of remote sensing data and handwritten numeral data indicate the superiority of DCL in comparison to the conventional competitive learning methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.12
• /
• pp.954-961
• /
• 2013

In this paper, we propose a new learning method using a variable learning to improve pattern recognition in the FCSR(Fast Commit Slow Recode) learning method of the Fuzzy ART. Traditional learning methods have used a fixed learning rate in updating weight vector(representative pattern). In the traditional method, the weight vector will be updated with a fixed learning rate regardless of the degree of similarity of the input pattern and the representative pattern in the category. In this case, the updated weight vector is greatly influenced from the input pattern where it is on the boundary of the category. Thus, in noisy environments, this method has a problem in increasing unnecessary categories and reducing pattern recognition capacity. In the proposed method, the lower similarity between the representative pattern and input pattern is, the lower input pattern contributes for updating weight vector. As a result, this results in suppressing the unnecessary category proliferation and improving pattern recognition capacity of the Fuzzy ART in noisy environments.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.1
• /
• pp.243-251
• /
• 2008

The cyber classes of an e-Learning system have been considered as one of the important form of education. Especially. some of non-major(liberal arts and science) and major subjects are held in cyber classes. However, there is no or little study of effectiveness and function for the students' position. In this study, we analyzed log files in the e-learning system. and classified login and learning hour patterns of students. who were enrolled in the cyber classes. into hourly pattern in a day, daily pattern in a week, and weekly pattern in a semester. We proposed general ideas to improve effectiveness and function of current e-learning. Over 50% of logins were for less than 30 minutes learning and there is wasteful use of e-learning system resources.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.5
• /
• pp.171-177
• /
• 2007

The cyber classes of an e-Learning system have been considered as one of the important form of education. However, there is no or little study of effectiveness and function for the students' position. In this study, I analyzed log files in the e-learning system, and classified login and teaming hour patterns of students, who were enrolled in the undergraduate courses of the university, into hourly pattern in a daily pattern in a week, weekly pattern in a semester. I proposed general ideas to improve effectiveness and function of current e-learning. Over 50% of logins were for less than 30minutes learning and there is wasteful use of e-learning system resources.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.2
• /
• pp.366-373
• /
• 2017

In this paper, we propose a variable weighted average (VWA) learning method in order to improve the performance of the fuzzy ART neural network that has been developed by Grossberg. In a conventional method, the Fast Commit Slow Recode (FCSR), when an input pattern falls in a category, the representative pattern of the category is updated at a fixed learning rate regardless of the degree of similarity of the input pattern. To resolve this issue, a variable learning method proposes reflecting the distance between the input pattern and the representative pattern to reduce the FCSR's category proliferation issue and improve the pattern recognition rate. However, these methods still suffer from the category proliferation issue and limited pattern recognition rate due to inevitable excessive learning created by use of fuzzy AND. The proposed method applies a weighted average learning scheme that reflects the distance between the input pattern and the representative pattern when updating the representative pattern of a category suppressing excessive learning for a representative pattern. Our simulation results show that the newly proposed variable weighted average learning method (VWA) mitigates the category proliferation problem of a fuzzy ART neural network by suppressing excessive learning of a representative pattern in a noisy environment and significantly improves the pattern recognition rates.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.7 no.4
• /
• pp.212-222
• /
• 2014

In the current study, the authors propose a method for extracting license plate regions by means of a neural network trained to output the plate's center of gravity. The method is shown to be effective. Since the learning pattern presentation positions are defined by random numbers, a different pattern is submitted to the neural network for learning each time, which enables it to form a neural network with high universality of coverage. The article discusses issues of the optimal learning surface for a license plate covered by the learning pattern, the effect of suppression learning of the number and pattern enlargement/reduction and of concentration value conversion. Results of evaluation tests based on pictures of 595 vehicles taken at an under-ground parking garage demonstrated detection rates of 98.5%, 98.7%, and 100%, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.77-86
• /
• 2005

In this paper, we designed a learning algorithm of LVQ that extracts classification errors and learns ones and improves classification performance. The proposed LVQ learning algorithm is the learning Networks which is use SOM to learn initial reference vectors and out-star learning algorithm to determine the class of the output neurons of LVQ. To extract pattern vectors which cause classification errors, we proposed the error-cause condition, which uses that condition and constructed the pattern vector space which consists of the input pattern vectors that cause the classification errors and learned these pattern vectors , and improved performance of the pattern classification. To prove the performance of the proposed learning algorithm, the simulation is performed by using training vectors and test vectors that are Fisher' Iris data and EMG data, and classification performance of the proposed learning method is compared with ones of the conventional LVQ, and it was a confirmation that the proposed learning method is more successful classification than the conventional classification.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.11
• /
• pp.1464-1471
• /
• 1999

This paper introduces complex-valued competitive learning neural network for spatio-temporal pattern recognition. There have been quite a few neural networks for spatio-temporal pattern recognition. Among them, recurrent neural network, TDNN, and avalanche model are acknowledged as standard neural network paradigms for spatio-temporal pattern recognition. Recurrent neural network has complicated learning rules and does not guarantee convergence to global minima. TDNN requires too many neurons, and can not be regarded to deal with spatio-temporal pattern basically. Grossberg's avalanche model is not able to distinguish long patterns, and has to be indicated which layer is to be used in learning. In order to remedy drawbacks of the above networks, unsupervised competitive learning using complex umber is proposed. Suggested neural network also features simultaneous recognition, time-shift invariant recognition, stable categorizing, and learning rate modulation. The network is evaluated by computer simulation with randomly generated patterns.

• Journal of Information Technology Applications and Management
• /
• v.15 no.1
• /
• pp.225-242
• /
• 2008

PM (Inconsistency Pattern Modeling) is a hybrid supervised learning technique using the inconsistence pattern of input variables in mining data sets. The IPM tries to improve prediction accuracy by combining more than two different supervised learning methods. The previous related studies have shown that the IPM was superior to the single usage of an existing supervised learning methods such as neural networks, decision tree induction, logistic regression and so on, and it was also superior to the existing combined model methods such as Bagging, Boosting, and Stacking. The objectives of this paper is explore the characteristics of the IPM. To understand characteristics of the IPM, three experiments were performed. In these experiments, there are high performance improvements when the prediction inconsistency ratio between two different supervised learning techniques is high and the distance among supervised learning methods on MDS (Multi-Dimensional Scaling) map is long.