• 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.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.85-87
• /
• 2000

In pattern classification, the Bhattacharyya distance has been used as a class separability measure and provides useful information for feature selection and extraction. In this paper, we propose a method to predict the classification error for multimodal data based on the Bhattacharyya distance. In our approach, we first approximate the pdf of multimodal distribution with a Gaussian mixture model and find the bhattacharyya distance and classification error. Exprimental results showed that there is a strong relationship between the Bhattacharyya distance and the classification error for multimodal data.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.2
• /
• pp.269-278
• /
• 2006

This paper presents the new hybrid data mining technique using error pattern, modeling of improving classification accuracy. The proposed method improves classification accuracy by combining two different supervised learning methods. The main algorithm generates error pattern modeling between the two supervised learning methods(ex: Neural Networks, Decision Tree, Logistic Regression and so on.) The Proposed modeling method has been applied to the simulation of 10,000 data sets generated by Normal and exponential random distribution. The simulation results show that the performance of proposed method is superior to the existing methods like Logistic regression and Discriminant analysis.

• Journal of the Korean School Mathematics Society
• /
• v.14 no.3
• /
• pp.277-293
• /
• 2011

The purpose of mathematics education is to develop the ability of transforming various problems in general situations into mathematics problems and then solving the problem mathematically. Various teaching-learning methods for improving the ability of the mathematics problem-solving can be tried. However, it is necessary to choose an appropriate teaching-learning method after figuring out students' level of understanding the mathematics learning or their problem-solving strategies. The error analysis is helpful for mathematics learning by providing teachers more efficient teaching strategies and by letting students know the cause of failure and then find a correct way. The following subjects were set up and analyzed. First, the error classification pattern was set up. Second, the errors in the solving process of the function problems were analyzed according to the error classification pattern. For this study, the survey was conducted to 90 first grade students of ${\bigcirc}{\bigcirc}$high school in Chung-nam. They were asked to solve 8 problems in the function part. The following error classification patterns were set up by referring to the preceding studies about the error and the error patterns shown in the survey. (1)Misused Data, (2)Misinterpreted Language, (3)Logically Invalid Inference, (4)Distorted Theorem or Definition, (5)Unverified Solution, (6)Technical Errors, (7)Discontinuance of solving process The results of the analysis of errors due to the above error classification pattern were given below First, students don't understand the concept of the function completely. Even if they do, they lack in the application ability. Second, students make many mistakes when they interpret the mathematics problem into different types of languages such as equations, signals, graphs, and figures. Third, students misuse or ignore the data given in the problem. Fourth, students often give up or never try the solving process. The research on the error analysis should be done further because it provides the useful information for the teaching-learning process.

• Proceedings of the KIEE Conference
• /
• 2004.05a
• /
• pp.92-94
• /
• 2004

We become an industry information society which is advanced to the altitude with the today. The information to be loading various goods each other together at a circumstance environment is increasing extremely. The restriction recognizes the data of many Quantity and it follows because the human deals the task to classify. The development of a mathematical formulation for solving a problem like this is often very difficult. But Artificial intelligent systems such as neural networks have been successfully applied to solving complex problems in the area of pattern recognition and classification. So, in this paper a neural network approach is used to recognize and classification problem was broken into two steps. The first step consist of using a neural network to recognize the existence of purpose pattern. The second step consist of a neural network to classify the kind of the first step pattern. The neural network leaning algorithm is to use error back-propagation algorithm and to find the weight and the bias of optimum. Finally two step simulation are presented showing the efficacy of using neural networks for purpose recognition and classification.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2001.10a
• /
• pp.59-64
• /
• 2001

The objectives of the thesis are to propose a pattern classification method for remote sensing data using artificial neural network. First, we apply the error back propagation algorithm to classify the remote sensing data. In this case, the classification performance depends on a training data set. Using the training data set and the error back propagation algorithm, a layered neural network is trained such that the training pattern are classified with a specified accuracy. After training the neural network, some pixels are deleted from the original training data set if they are incorrectly classified and a new training data set is built up. Once training is complete, a testing data set is classified by using the trained neural network. The classification results of Landsat TM data show that this approach produces excellent results which are more realistic and noiseless compared with a conventional Bayesian method.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.4
• /
• pp.27-43
• /
• 2005

This paper presents a new hybrid data mining technique using error pattern modeling to improve classification accuracy when the data type of a target variable is binary. The proposed method increases prediction accuracy by combining two different supervised learning methods. That is, the algorithm extracts a subset of training cases that are predicted inconsistently by both methods, and models error patterns from the cases. Based on the error pattern model, the Predictions of two different methods are merged to generate final prediction. The proposed method has been tested using practical 10 data sets. The analysis results show that the performance of proposed method is superior to the existing methods such as artificial neural networks and decision tree induction.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.4
• /
• pp.757-764
• /
• 2009

In discriminant analysis, we consider a special pattern which contains a block of missing observations. We assume that the two populations are equally likely and the costs of misclassification are equal. In this situation, we consider the bootstrap confidence intervals of the error rate in the circular models when the covariance matrices are equal and not equal.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1984.12a
• /
• pp.73-77
• /
• 1984

This paper reports on a Voiced-Unvoiced-Silence Classification of speech for Korean Speech Recognition. In this paper, it is describe a method which uses a Pattern Recognition Technique for classifying a given speech segment into the three classes. Best result is obtained with the combination using ZCR, P1, Ep and classification error rate is less than 1%.

• Journal of Korean Institute of Industrial Engineers
• /
• v.28 no.1
• /
• pp.112-127
• /
• 2002

A useful pattern is a pattern that contributes much to learning. For a classification problem those patterns near the class boundary surfaces carry more information to the classifier. For a regression problem the ones near the estimated surface carry more information. In both cases, the usefulness is defined only for those patterns either without error or with negligible error. Using only the useful patterns gives several benefits. First, computational complexity in memory and time for learning is decreased. Second, overfitting is avoided even when the learner is over-sized. Third, learning results in more stable learners. In this paper, we propose a pattern 'utility index' that measures the utility of an individual pattern. The utility index is based on the bias and variance of a pattern trained by a network ensemble. In classification, the pattern with a low bias and a high variance gets a high score. In regression, on the other hand, the one with a low bias and a low variance gets a high score. Based on the distribution of the utility index, the original training set is divided into a high-score group and a low-score group. Only the high-score group is then used for training. The proposed method is tested on synthetic and real-world benchmark datasets. The proposed approach gives a better or at least similar performance.