• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.209-215
• /
• 2003

A new GA-based methodology using information granules is suggested for the construction of fuzzy classifiers. The proposed scheme consists of three steps: selection of information granules, construction of the associated fuzzy sets, and tuning of the fuzzy rules. First, the genetic algorithm (GA) is applied to the development of the adequate information granules. The fuzzy sets are then constructed from the analysis of the developed information granules. An interpretable fuzzy classifier is designed by using the constructed fuzzy sets. Finally, the GA are utilized for tuning of the fuzzy rules, which can enhance the classification performance on the misclassified data (e.g., data with the strange pattern or on the boundaries of the classes). To show the effectiveness of the proposed method, an example, the classification of the Iris data, is provided.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.1
• /
• pp.6-14
• /
• 2012

All types of part-of-speech (POS) tagging errors have been equally treated by existing taggers. However, the errors are not equally important, since some errors affect the performance of subsequent natural language processing seriously while others do not. This paper aims to minimize these serious errors while retaining the overall performance of POS tagging. Two gradient loss functions are proposed to reflect the different types of errors. They are designed to assign a larger cost for serious errors and a smaller cost for minor errors. Through a series of experiments, it is shown that the classifier trained with the proposed loss functions not only reduces serious errors but also achieves slightly higher accuracy than ordinary classifiers.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.113-120
• /
• 2015

In this paper, we propose a feature extraction method using the stacked autoencoders which consist of restricted Boltzmann machines. The stacked autoencoders is a sort of deep networks. Restricted Boltzmann machines (RBMs) are probabilistic graphical models that can be interpreted as stochastic neural networks. In terms of pattern classification problem, the feature extraction is a key issue. We use the stacked autoencoders networks to extract new features which have a good influence on the improvement of the classification performance. After feature extraction, fuzzy k-nearest neighbors algorithm is used for a classifier which classifies the new extracted data set. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.1
• /
• pp.107-113
• /
• 2003

A new GA-based methodology using information granules is suggested for the construction of fuzzy classifiers. The proposed scheme consists of three steps: selection of information granules, construction of the associated fuzzy sets, and tuning of the fuzzy rules. First, the genetic algorithm (GA) is applied to the development of the adequate information granules. The fuzzy sets are then constructed from the analysis of the developed information granules. An interpretable fuzzy classifier is designed by using the constructed fuzzy sets. Finally, the GA are utilized for tuning of the fuzzy rules, which can enhance the classification performance on the misclassified data (e.g., data with the strange pattern or on the boundaries of the classes). To show the effectiveness of the proposed method, an example, the classification of the Iris data, is provided.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.806-809
• /
• 2002

Real-world objects often have two or more significant attributes. For example, face images have attributes of persons, expressions, and so on. Even if we are interested in only one of those attributes, additional informations on auxiliary attributes can help recognition of the main one. In the present paper, the authors propose a method for pattern recognition with double attributes. A pair of classifiers are combined: each classifier makes a guess of its corresponding attribute, and it tells the guess to the other as a hint. Equilibrium point of this iteration can be calculated directly without iterative procedures.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.9
• /
• pp.68-76
• /
• 1997

This paper presents a system which recognizes dynamic hand gestures for virtual reality(VR). A dynamic hand gesture is a method of communication for a computer and human who uses gestures, especially both hands and fingers. Since the human hands and fingers are not the same in physical dimension, the same form of a gestrue produced by two persons with their hands may not have the same numerical values which are obtained through electronic sensors. In this paper, we apply a fuzzy min-max neural network and feature analysis method using fuzzy logic for on-line pattern recognition.

• ETRI Journal
• /
• v.29 no.4
• /
• pp.507-515
• /
• 2007

Skeleton transform of which the medial axis transform is the most popular has been proposed as a useful shape abstraction tool for the representation and modeling of human posture. This paper explains this proposition with a description of the areas in which skeletons could serve to enable the representation of shapes. We present algorithms for two-dimensional posture modeling using the developed simplified shock graph (SSG). The efficacy of SSG extracted feature vectors as shape descriptors are also evaluated using three different classifiers, namely, decision tree, multilayer perceptron, and support vector machine. The paper concludes with a discussion of the issues involved in using shock graphs to model and classify human postures.

• Spatial Information Research
• /
• v.2 no.2
• /
• pp.175-188
• /
• 1994

A competitive learning network was proposed as unsupervised training method of remote sensing data, Its performance and computational re¬quirements were compared with conventional clustering techniques such as Se¬quential and K - Means. An airborne remote sensing data set was used to study the performance of these classifiers. The proposed algorithm required a little more computational time than the conventional techniques. However, the perform¬ance of competitive learning network algorithm was found to be slightly more than those of Sequential and K - Means clustering techniques.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2004.11a
• /
• pp.101-106
• /
• 2004

Subcellular localization is a key functional char acteristic of proteins. With the number of sequences entering databanks rapidly increasing, the importance of developing a powerful tool to identify protein subcellular location has become self-evident. In this paper, we introduce a novel method for predic ting protein subcellular locations from protein sequences. The main idea was motivated from the observation that amino acid pair composition data is redundant. By classifying from multiple feature subsets and using many kinds of amino acid pair composition s, we forced the classifiers to make uncorrelated errors. Therefore when we combined the predictors using a voting scheme, the prediction accuracy c ould be improved. Experiment was conducted on several data sets and significant improvement has been achieve d in a jackknife test.

• International Journal of Contents
• /
• v.7 no.3
• /
• pp.1-5
• /
• 2011

It has been an interesting challenge to find a good classifier for imbalanced data, since it is pervasive but a difficult problem to solve. However, classifiers developed with the assumption of well-balanced class distributions show poor classification performance for the imbalanced data. Among many approaches to the imbalanced data problems, the algorithmic level approach is attractive because it can be applied to the other approaches such as data level or ensemble approaches. Especially, the error back-propagation algorithm using the target node method, which can change the amount of weight-updating with regards to the target node of each class, attains good performances in the imbalanced data problems. In this paper, we analyze the relationship between two optimal outputs of neural network classifier trained with the target node method. Also, the optimal relationship is compared with those of the other error function methods such as mean-squared error and the n-th order extension of cross-entropy error. The analyses are verified through simulations on a thyroid data set.