• 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.

• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.965-978
• /
• 2006

This paper implements an automatic Korean word-spacing system based on word-recognition using morpheme unigrams and the pattern that the categories of those morpheme unigrams share within a candidate word. Although previous work on Korean word-spacing models has produced the advantages of easy construction and time efficiency, there still remain problems, such as data sparseness and critical memory size, which arise from the morpho-typological characteristics of Korean. In order to cope with both problems, our implementation uses the stochastic information of morpheme unigrams, and their category patterns, instead of word unigrams. A word's probability in a sentence is obtained based on morpheme probability and the weight for the morpheme's category within the category pattern of the candidate word. The category weights are trained so as to minimize the error means between the observed probabilities of words and those estimated by words' individual-morphemes' probabilities weighted according to their categories' powers in a given word's category pattern.

• 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.

• Korean Journal of Oriental Medicine
• /
• v.13 no.1 s.19
• /
• pp.85-92
• /
• 2007

To evaluate the suitability and effectiveness of the questionnaire concerning personal properties on 'pattern of speech and activity' according to the Sasang constitution that were used in Iksan Wonkwang Oriental Medicine, we analyzed the data of 1,335 patients obtained through the electronic chart in the aspect of 'relative discrimination ability' to Sasang constitutions and 'response ratio' using statistical Package SPSS. In categories of 'speech pattern', No.2 (speak mildly and softly) was effectively discriminating Soeum type. No.4 (talkative) and No.7 (speak fast) were effective factors for the discrimination of Soyang type, though No.4 (talkative) was needed to be improved in response ratio. The category of 'activity pattern' has shown high response ratio but low discriminating power. However, No.2 (keep staying home but avoid going out) in this category was effectively discriminating Soeum type. The discriminating power of 'pattern of speech and activity' for the age group less than 20 years old was too low, so it is necessary to develop the questionnaire for the elementary to high school students as well as for the preschoolers.

• Fashion & Textile Research Journal
• /
• v.11 no.1
• /
• pp.140-146
• /
• 2009

In this study, the ideal human body of adult woman is to express, and the body dimension of the woman model is produced and compared in doll model with the bodily dimension by presenting the body pattern to produce the dolls with the ideal body proportion visually. For the research process, by collecting, comparing and analyzing the body pattern of the currently used embroidery fashion doll, the pattern of body suit that displays the body of women is designed with the size of model with the height of 168cm. This is scaled for 1/4 of its entirety to make the doll of around 40cm and produced the research doll with two revisions. When compared with the ratio of each part of the body for the height of the produced research doll with the bodily ration of the major ratio of the height of the standard bodily size of Size Korea 2004, the ratio of the category of the height is almost consistent, and the width category is shown approximately 80~85%, waist for 75%, thickness category for approximately 90% as the ideal ratio.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.349-357
• /
• 2007

Named entities (NEs) are important in many Natural Language Processing (NLP) applications, and discovering NE-related relations in texts may be beneficial for these applications. This paper proposes a method to extract the ISA relation between a "named entity" and its category, and an IS-RELATED-TO relation between the category and its related object. Based on the pattern extraction algorithm "Person Category Extraction" (PCE), we extend it for solving our problem. Our experiments on Wall Street Journal (WSJ) corpus show promising results. We also demonstrate a possible application of these relations by utilizing them for semantic search.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.5C
• /
• pp.486-492
• /
• 2003

The vigilance threshold of conventional fuzzy ART algorithm decide whether to permit the mismatch between any input pattern and stored pattern. If the vigilance threshold was large, despite of little difference among input and stored patterns, the input pattern may be classified to new category. On the other hand, if the vigilance threshold was small, the similarity between two patterns may be accepted in spite of lots of difference and the input pattern are classified to category of the stored pattern. Therefore, the vigilance threshold for the image recognition must be experientially set for the good result. Moreover, it may occur in the fuzzy ART algorithm that the information of stored patterns is lost in the weight-adjusting process and the rate of pattern recognition is dropped. In this paper, I proposed the enhanced fuzzy ART algorithm that supports the dynamical setting of the vigilance threshold using the generalized intersection operator of fuzzy logic and the weight value being adaptively set in proportional to the current weight change and the previous weight by reflecting the frequency of the selection of winner node. For the performance evaluation of the proposed method, we applied to the recognition of container identifiers from shipping container images. The experiment showed that the proposed method produced fewer clusters than conventional ART2 and fuzzy ART algorithm. and had tile higher recognition rate.

• Journal of Sasang Constitutional Medicine
• /
• v.22 no.3
• /
• pp.18-28
• /
• 2010

1. Objectives: Purpose of this paper is to study the reinterpretation of Taeyang disease(太陽病) in "Shanghanlun(傷寒論)" based on the pathologic perspective of Sa-sang Constitutional Medicine by comparing factors as pathologic mechanisms, clinical symptoms, and remedies. 2. Methods: The texts referred to pathologic mechanisms, clinical symptoms, and remedies of Taeyang disease(太陽病) described in "Donguisusebowon Gabobon(東醫壽世保元 甲午本)", "Donguisusebowon Sinchookbon(東醫壽世保元 辛丑本)", and Shanghanlun(傷寒論)" in "Donguibogam(東醫寶鑑)" were analysed. 3. Results and Conclusions 1) Early phase of Ulgwang symptomatic pattern(鬱狂證 初證) and of Mangyang symptomatic pattern(亡陽證初證) of Kidney Heat-based Exterior Heat disease(腎受熱表熱病), a category of Soeumin(少陰人) diseases, were described by adopting pathologic models of Taeyang-sangpung symptomatic pattern(太陽傷風證) and Sanghan-hyeol symptomatic pattern(傷寒血證) from "Sanghanlun(傷寒論)". 2) Soyang-sangpung symptomatic pattern(少陽傷風證) of Spleen Cold-based Exterior Cold diseae (脾受寒表寒病) and Hyunggyeok-yeol symptomatic pattern(胸膈熱證) of Stomach Heat-based Interior Heat disease(胃受熱裏熱病), categories of Soyangin(少陽人) diseases, were described by adopting pathologic models of Taeyang-yangsangpunghan symptomatic pattern(太陽兩傷風寒證), Soyang-sangpung symptomatic pattern(少陽傷風證) and Tayangbyong-sahak symptomatic pattern(太陽病似瘧證) from "Sanghanlun(傷寒論)". 3) Baechu-pyo symptomatic pattern(背顀表病輕證) and Hangual symptomatic pattern(寒厥證) of Esophagus Cold-based Exterior Cold disease(胃脘受寒表寒病), a category of Taeeumin(太陰人) diseases, was described by adopting pathologic models of Taeyang-sanghan symptomatic pattern(太陽傷寒證) and Hangual symptomatic pattern(寒厥證) from "Sanghanlun(傷寒論)". 4) Je-Ma Lee reinterpreted various diseases classified as Taeyang disease(太陽病) with the pathologic perspective of Sa-sang Constitutional Medicine. Different from existing medicine, diseases were analysed and treated by the standard, constitution of the patient.

• Phonetics and Speech Sciences
• /
• v.2 no.4
• /
• pp.29-37
• /
• 2010

Previous studies have investigated a between-category relationship of multiple acoustic cues for a laryngeal contrast by examining the distributions of VOT, f0 and H1-H2. The current study examined within-category correlations between cues comprising stops by Korean- and English-speaking adults and children to understand how children master the internal structure of stop phonation types in two languages. Word-initial stops were collected from about 70 children and 15 adults speaking English and Korean, and were analyzed in terms of VOT, f0 and H1-H2 to compute correlation coefficients. Findings in adults' productions included a gender-differentiated cue-correlation pattern associated with H1-H2 in Korean tense stops and a trading relationship between f0 and VOT in Korean lax and aspirated stops and English voiced and voiceless stops. Children did not necessarily have adult-like cue-correlation patterns even in early-acquired categories, suggesting that the mastery of intra-category structure of phonation type might occur later than inter-category structure.

• Journal of the Korean Society of Radiology
• /
• v.11 no.5
• /
• pp.401-406
• /
• 2017

Breast cancer rates are increasing every year, biopsy for diagnosing breast cancer is increasing as well. Biopsy also invasive test, have bad side effects from patients anxiety, infection, bleeding. In this study, Conduct a survey of 69 patients who brest lesion patient, both B-mode ultrasound and elastography exam and B-mode ultrasound was classified according to the BI-RADS category, and the elastography exam was classified according to the Color overlay pattern that the value of the kPa expressed in relation to the propagation velocity of Transverse waves. The optimal cut off value of the highest sensitivity and specificity was 54.70 kPa. In the color overlay pattern, Dark Blue 42 people, Light blue ~ Red 27 people classified results and BI-RADS classification results, benign 40 people and malignant 29 people classified results showed similar results. Therefore, It is judged that the color overlay pattern is positive when classified into Dark Blue, and malignant when classified into Light blue ~ Red. In conclusion, breast elastography is expected to play a innovative role in reducing the number of breast cancer examinations and classify between benign and malignant tumor.