• 대한치과교정학회지
• /
• 제21권1호
• /
• pp.171-183
• /
• 1991

This investigation was designed to categorize Angle's class II malocclusion groups through analyzing horizontal and vertical components of craniofacial skeleton in Angle's class II malocclusion. The material selected for this study consisted in standard lateral cephalogram of two hundred and twenteen children, eighty eight boys and one hundred twenty four girls, aged 6 through 18 years, having Angle's class II malocclusion. On the basis of findings of this study, the following results were obtained. 1. In horizontal skeletal classifications, 16 groups were classified according to FMN-A-B, SE-FMN-A, Ba-SE-Me, Ba-Se/Ra P. The sequences that have relatively high frequency are as follows: a) Horizontal Group 16 b) Horizontal Group 12 c) Horizontal Group 13 d) Horizontal Group 9 & 15 2. In vertical skeletal classification, 8 groups were classified according to the PMV/PP, PMV/Occ. P. PMV/Mn. P. The sequences that relatively high frequency are as follows; a) Vertical Group A b) Vertical Group D c) Vertical Group C d) Vertical Group H 3. In vertical and horizontal skeletal classifications, the sequence that relatively high frequency are as follows; a) Group13-A b) Group16-A & 9-A c) Group12-A & 15-A d) Group16-C

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권11호
• /
• pp.4502-4518
• /
• 2015

Fisher linear discriminant analysis (LDA) is one of the most popular projection techniques for feature extraction and has been widely applied in face recognition. However, it cannot be used when encountering the single sample per person problem (SSPP) because the intra-class variations cannot be evaluated. In this paper, we propose a novel method called local similarity based linear discriminant analysis (LS_LDA) to solve this problem. Motivated by the "divide-conquer" strategy, we first divide the face into local blocks, and classify each local block, and then integrate all the classification results to make final decision. To make LDA feasible for SSPP problem, we further divide each block into overlapped patches and assume that these patches are from the same class. To improve the robustness of LS_LDA to outliers, we further propose local similarity based median discriminant analysis (LS_MDA), which uses class median vector to estimate the class population mean in LDA modeling. Experimental results on three popular databases show that our methods not only generalize well SSPP problem but also have strong robustness to expression, illumination, occlusion and time variation.

• 응용통계연구
• /
• 제32권3호
• /
• pp.349-374
• /
• 2019

이분형 자료의 분류에서 자료의 불균형 정도가 심한 경우 분류 결과가 좋지 않을 수 있다. 이런 문제 해결을 위해 학습 자료를 변형시키는 등의 연구가 활발히 진행되고 있다. 본 연구에서는 이러한 이분형 자료의 분류문제에서 불균형을 다루기 위한 방법들 중 표본재추출 방법들을 비교하였다. 이를 통해 자료에서 희소계급의 탐지를 보다 효과적으로 하는 방법을 찾고자 하였다. 모의실험을 통하여 여러 오버샘플링, 언더샘플링, 오버샘플링과 언더샘플링 혼합방법의 총 20가지를 비교하였다. 분류문제에서 대표적으로 쓰이는 로지스틱 회귀분석, support vector machine, 랜덤포레스트 모형을 분류기로 사용하였다. 모의실험 결과, 정확도가 0.5 이상이면서 민감도가 높았던 표본재추출 방법은 random under sampling (RUS)였다. 그 다음으로 민감도가 높았던 방법은 오버샘플링 ADASYN (adaptive synthetic sampling approach)이었다. 이를 통해 RUS 방법이 희소계급값을 찾기 위한 방안으로는 적합했다는 것을 알 수 있었다. 몇 가지 실제 자료에 적용한 결과도 모의실험의 결과와 비슷한 양상을 보였다.

• Communications for Statistical Applications and Methods
• /
• 제16권6호
• /
• pp.1005-1012
• /
• 2009

The area under the curve(AUC) is commonly used as a measure of the receiver operating characteristic(ROC) curve which displays the performance of a set of binary classifiers for all feasible ratios of the costs associated with true positive rate(TPR) and false positive rate(FPR). In the bipartite ranking problem where one has to compare two different observations and decide which one is "better", the AUC measures the quantity that ranking score of a randomly chosen sample in one class is larger than that of a randomly chosen sample in the other class and hence, the function which maximizes an AUC of bipartite ranking problem is different to the function which maximizes (minimizes) accuracy (misclassification error rate) of binary classification problem. In this paper, we develop a way to construct the unified framework for AUC maximizer including support vector machines based on maximizing large margin and logistic regression based on estimating posterior probability. Moreover, we develop an efficient algorithm for the proposed unified framework. Numerical results show that the propose unified framework can treat various methodologies successfully.

• 한국문헌정보학회지
• /
• 제26권
• /
• pp.75-112
• /
• 1994

The purpose of this study is to investigate the problems concerning 780 music division of DDC. The object is especially arrangement of 780 music in the 20th edition of DDC which is the complete revision. The result is summarized as follows : 1. Although music is an important subject in humanities, especially in arts, it was classified as one division (780) not class. 2. The arrangement of 780 music is severely west-oriented music theory, vocal music and instrumental music. 3. Classification number of 780 music becomes longer because of the limitation of decimal notation. 4. 780 music division of DDC neglects music theory and emphasizes music practicing, especially performance. 5. The assignment of classification number is unbalanced, especially between theory and practice, composition and performance, and among sub-sections of vocal and instrumental music. 6. Many important subject are omitted in DDC music schedule, for example, musicology and branches of musicology, composition and traditional instruments of many countries. 7. Employment of terminology is often improper and inconsistant.

• International journal of advanced smart convergence
• /
• 제9권1호
• /
• pp.193-201
• /
• 2020

The main objective of this study is to investigate the impact of additional modalities on the performance of emotion recognition using speech, facial expression and physiological measurements. In order to compare different approaches, we designed a feature-based recognition system as a benchmark which carries out linear supervised classification followed by the leave-one-out cross-validation. For the classification of four emotions, it turned out that bimodal fusion in our experiment improves recognition accuracy of unimodal approach, while the performance of trimodal fusion varies strongly depending on the individual. Furthermore, we experienced extremely high disparity between single class recognition rates, while we could not observe a best performing single modality in our experiment. Based on these observations, we developed a novel fusion method, called parametric decision fusion (PDF), which lies in building emotion-specific classifiers and exploits advantage of a parametrized decision process. By using the PDF scheme we achieved 16% improvement in accuracy of subject-dependent recognition and 10% for subject-independent recognition compared to the best unimodal results.

• 대한치과교정학회지
• /
• 제10권1호
• /
• pp.55-64
• /
• 1980

The purpose of this study was to investigate the interrelationship of the experimental group and control group by analyzing case histories, intraoral radiographs, orthopantomographs, intraoral slide films and dental casts. The data for this study were complied from 654 outpatients of the Department of Orthodontics, Seoul National University Hospital. The following conclusions were obtained. 1. When one or more thins molar teeth were congenitally missing, the incidence of the other congenitally missing teeth was high. 2. The frequency of congenitally missing teeth was comparatively higher in male, maxilla, class II and class III. 3. The congenitally missing srea of the third molar by Angle's classification was not significant. 4. The order of frequency of congenitally missing teeth was the third molar, the second premolar, the lateral incisor, the first premolar, the central incisor, the canine, the first molar, the second molar.

• Journal of Mechanical Science and Technology
• /
• 제19권3호
• /
• pp.846-859
• /
• 2005

Support vector machines (SVMs) have become one of the most popular approaches to learning from examples and have many potential applications in science and engineering. However, their applications in fault diagnosis of rotating machinery are rather limited. Most of the published papers focus on some special fault diagnoses. This study covers the overall diagnosis procedures on most of the faults experienced in rotating machinery and examines the performance of different SVMs strategies. The excellent characteristics of SVMs are demonstrated by comparing the results obtained by artificial neural networks (ANNs) using vibration signals of a fault simulator.

• Journal of Korean Neurosurgical Society
• /
• 제39권2호
• /
• pp.114-119
• /
• 2006

Objective : The authors investigate appropriate evaluation and surgical methods in treatment of the cerebral paragonimiasis accompanying epilepsy. Methods : Thirteen patients with the cerebral paragonimiasis accompanying epilepsy were included for this study. Preoperative evaluation methods included history taking, skin and serologic tests for Paragonimus westermani, neurologic examinations, computerized tomography, magnetic resonance imaging, amytal test, PET or SPECT, and video-EEG monitoring with depth and subdural grid electrodes. Seizure outcome was evaluated according to Engel's classification. Results : Surgical methods were temporal lobectomy including lesions in six, lesionectomy in five, and temporal lobectomy plus lesionectomy in two. Postoperative neurological complications were not noticed, and seizure outcomes were class I in 12 patients [92%], class II in one [8%]. Conclusion : In patients with a cerebral paragonimiasis accompanying epilepsy, further evaluation methods must be done to define the epileptogenic zone, and complete resection of the epileptogenic zone with different surgical methods should be performed for seizure control.

• Journal of Chest Surgery
• /
• 제15권4호
• /
• pp.387-393
• /
• 1982

A total of 18 open mitral commissurotomy were performed at Seoul National University Hospital between January 1975 and August 19. Thirteen patients had open mitral commissurotomy alone and five had additional cardiac procedure. Six patients were men and twelve were women. The mean age was 33 years. According to the NYHA classification, the distribution of patients preoperatively was as follows; Glass II, 2 patients; class III, 14 patients; class IV, 2 patients. Three patients had emboli preoperatively, all of whom were in atrlal fibrillation. There was no operative death. The patients were followed from 2 to 86 months [mean 26 months]. There was no late death and no embolic episode. Mitral valve replacement was required in one patient due to mitral restenosis after 4 years.