• 한국의류학회지
• /
• 제26권1호
• /
• pp.15-26
• /
• 2002

The purpose of this study was to classier the somatotype of late middle-aged women and to analyze the characteristics of each somatotype. The subjects were 337 late middle-aged women and their age range os from 45 to 59 fears old. Data were collected through anthropometry and photometry and analyzed by factor analysis, cluster analysis and discriminant analysis. The results were as follows; 1. The result of factor analysis indicated that 9 factors were extracted through factor analysis and those factors comprised 83.56 percent of total valiance. 2. Using factor scores, cluster analysis was carried out and the subject were classified into 4 cluster. Each cluster was classified as their body front and side view contour. Type 1 is tall, slim, and lower balk is flat on the side. Type 2 is standard and lean-back type on the side. Type 3 is standard height and weight, H type in front, and belly-protruded on the side. Type 4 is short, fat, and the side is hip-protruded. 3. According to the stepwise discriminant analysis, the 9 important items in classifying the somatotype of the late middle-aged women are as follows ; lower back tilt angle, hip depth(back) -back waist depth(back), bust depth(fore) - anterior waist depth(fore), jugular fossa point(fore), upper back tilt angle, burst breadth -waist breadth, right shoulder tilt, height of shoulder - height of anterior waist, abdomen breath. The correct classification rate for these items is as exact as 84.62%.

• 대한치과교정학회지
• /
• 제21권1호
• /
• pp.113-130
• /
• 1991

This study was undertaken to investigate soft tissue profile changes by orthodontic treatment in female patients. Traditional cephalometric appraisal yields data of dubious scientific value, the soft tissue profile forms were evaluated by finite element method. The subject was divided into three groups according to Angle's classification and each group was composed of 25 female patients averaged aged 12-14 years at the start of treatment. The changes in soft tissue form were evaluated by computing the degree of distortion in each triangle after treatment compared with the triangle before treatment. The conclusions were as follows; 1. The soft tissue profile forms were evaluated by finite element method and independent evaluation of each element by local changes was possible. 2. Maximum and minimum principal strains showed marked variability depending on the particular finite element and each group and Class II, III sample was greater than Class I sample. 3. Soft tissue size changes as a result of orthodontic treatment was not related to those of shape. 4. Soft tissue changes by orthodontic treatment were variable in individual patient, and were not related to Angle's classification.

• 한국조경학회지
• /
• 제29권4호
• /
• pp.12-23
• /
• 2001

The research focused on the landscape of mountains and hills drawn in a landscape picture. The purpose of the research is to classify patterns of landscape drawning in landscape pictures and to clarify the characteristics of the pattern by a quantitative index. We selected 21 landscape pictures to understand the Landscape Setting Here(LSH) and Landscape Setting These(LST). We investigated size quantitative indices using 1 landscape picture. The index is a follow: altitude, Visual Distance, Angles, Angle of Appearance Size, Inclination, and Angle of Incidence. The following results were obtained by using this data. 1) It has been understood that we offer an important city view because the LSH of this research can establish understanding of the city structure. 2) We dividing 3 patterns by the LST space drawn in the landscape picture. 3 patterns are Ferry point, Beauty point, an Signal-fire point. 3) We clarified the landscape characteristics of each pattern and the characteristics between patterns by using the index according to this pattern. 4) We understood the problem concerning the Seoul city landscape examining the pattern of this research with the ordinance of Seoul city. It is necessary to standardized a system of pattern classification utilized in landscape pictures to establish a universally interpreted detailed quantitative index, which can be applied to research.

• 한국의류학회지
• /
• 제33권5호
• /
• pp.741-751
• /
• 2009

In order to design and develop the various silhouette of pants pattern for standardized pants patterns, this study is to classify the pants style by the silhouette and to characterize each pants pattern which are classified. Recent 37 ready-made pants patterns of various style were collected in order to analyze their silhouette from April to July 2007. Measurement of each region of the pants pattern were compared and analysed. After analyse the standard deviation, coefficient of variance, minimum, maximum, range about the measurement of each region of the pants pattern, major pattern design factors were extracted. Five major factors are the angle of center front line and center back line, the crotch extension, the position of center back line against center front line, the curvature of center back line, and amount of waist dart. As a result, pants style were grouped as the culottes, formal, basic and tight style after considering the extracted design factors, and analysing correlation, degree of dispersion of the measurement by part. As the silhouette of pants classification from culotte to tight, the fits are closer to the figure, crotch depth increases, crotch extensions are shorter, and angle of the center back increases. The shape of the connected front and back center lines is U-shape for culotte and is closer to V-shape as the silhouette becomes tight.

• 대한의용생체공학회:의공학회지
• /
• 제42권4호
• /
• pp.186-192
• /
• 2021

In this paper, we evaluated prediction accuracy of Euler angle spectrograph classification method using a convolutional neural networks (CNN) for hand gesture recognition in augmented reality (AR) cognitive rehabilitation system based on Leap Motion Controller (LMC). Hand gesture recognition methods using a conventional support vector machine (SVM) show 91.3% accuracy in multiple motions. In this paper, five hand gestures ("Promise", "Bunny", "Close", "Victory", and "Thumb") are selected and measured 100 times for testing the utility of spectral classification techniques. Validation results for the five hand gestures were able to be correctly predicted 100% of the time, indicating superior recognition accuracy than those of conventional SVM methods. The hand motion recognition using CNN meant to be applied more useful to AR cognitive rehabilitation training systems based on LMC than sign language recognition using SVM.

• Journal of Biosystems Engineering
• /
• 제40권4호
• /
• pp.417-427
• /
• 2015

Purpose: This study investigated different band selection methods to classify spectrally similar data - obtained from aerial images of healthy citrus canopies and citrus greening disease (Huanglongbing or HLB) infected canopies - using small differences without unmixing endmember components and therefore without the need for an endmember library. However, large number of hyperspectral bands has high redundancy which had to be reduced through band selection. The objective, therefore, was to first select the best set of bands and then detect citrus Huanglongbing infected canopies using these bands in aerial hyperspectral images. Methods: The forward feature selection algorithm (FFSA) was chosen for band selection. The selected bands were used for identifying HLB infected pixels using various classifiers such as K nearest neighbor (KNN), support vector machine (SVM), naïve Bayesian classifier (NBC), and generalized local discriminant bases (LDB). All bands were also utilized to compare results. Results: It was determined that a few well-chosen bands yielded much better results than when all bands were chosen, and brought the classification results on par with standard hyperspectral classification techniques such as spectral angle mapper (SAM) and mixture tuned matched filtering (MTMF). Median detection accuracies ranged from 66-80%, which showed great potential toward rapid detection of the disease. Conclusions: Among the methods investigated, a support vector machine classifier combined with the forward feature selection algorithm yielded the best results.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.698-701
• /
• 2005

This paper examines that is extracted certain information in forest areas within high resolution imagery based on wavelet transformation. First of all, study areas are selected one more species distributed spots refer to forest type map. Next, study area is cut 256 x 256 pixels size because of image processing problem in large volume data. Prior to wavelet transformation, five texture parameters (contrast, dissimilarity, entropy, homogeneity, Angular Second Moment (ASM≫ calculated by using Gray Level Co-occurrence Matrix (GLCM). Five texture images are set that shifting window size is 3x3, distance .is 1 pixel, and angle is 45 degrees used. Wavelet function is selected Daubechies 4 wavelet basis functions. Result is summarized 3 points; First, Wavelet transformation images derived from contrast, dissimilarity (texture parameters) have on effect on edge elements detection and will have probability used forest road detection. Second, Wavelet fusion images derived from texture parameters and original image can apply to forest area classification because of clustering in Homogeneous forest type structure. Third, for grading evaluation in forest fire damaged area, if data fusion of established classification method, GLCM texture extraction concept and wavelet transformation technique effectively applied forest areas (also other areas), will obtain high accuracy result.

• 한국지리정보학회지
• /
• 제21권3호
• /
• pp.205-213
• /
• 2018

초분광영상(Hyperspectral Image)은 다중분광영상에 비해 각 픽셀이 가지는 정보량이 많아 다양한 토지피복을 분류하는데 있어 가장 적합한 영상으로 평가 받고 있다. 하지만 최근의 초분광영상의 연구는 대분류에 해당하는 연구에 그치고 있다. 이에 본 연구에서는 다양한 토지피복분류에 대한 연구를 수행하기 위해 기존의 분석기법인 ED, SAM, SSS 기법을 토대로 Decision Tree를 구성하는 연구를 수행하였다. 그 결과, 대분류의 전체정확도는 1.68%, 세분류 전체정확도는 5.56%가 향상되는 결과를 얻을 수 있었다.

• 한국의류산업학회지
• /
• 제26권1호
• /
• pp.35-43
• /
• 2024

This study aimed to objectively classify the lateral torso posture types and functions of older women. We used 3D body scan data of 119 women aged 70-85 years from the 6th SizeKorea project. First, we defined three torso axes to represent the lateral torso posture types: posterior waist-back, back-cervical, and whole torso axes. Next, we asked experts to select one of four lateral torso posture types-stooped, straight, leaning back, and swayback postures-by looking at the lateral photographic data of 119 older women. To identify the axis that best represented each lateral torso posture type, a discriminant analysis was conducted using the angle of each of the three torso axes as an independent variable and an expert's visual classification as a dependent variable. Based on the analysis, the whole torso and backcervical axis angles were selected as variables for judging lateral torso posture types. Subsequently, we developed a classification function to determine which of the four lateral torso posture types of a particular participant was applicable for a new individual. The method developed in this study is significant in that it enables the objective classification of the lateral torso postures types of older women.

• 복식
• /
• 제49권
• /
• pp.25-48
• /
• 1999

The purpose of this study is to offer fundamental data for classification of somatotype for boys of elementary school age. The subject were 458 elementary school boys aged from 7 to 12 living in Pusan, Data were collected by 57 anthropometric and 11 photographic measurements and analyzed by factor analysis according to SAS package 1. Through the factor analysis by each period of school ages 6-7 factor were obtained in upper half and they are as followings: 1) Factor 1 is horizontal size of upper half in every period 2) Factor 2 is vertical size of upper half in every period 3) Factor 3 is shoulder shape in the first period and length of upper half in the middle and latter period 4) Facto 4 sis length of upper half in the first period and shoulder shape in the middle and latter period 5) Factor 5 is angle shape of the breast and back in the first period angle shape of the lower breast and back in the middle of period and angle shape of the upper breast and back in the latter of period 6) Factor 6 is angle of shoulder in the first period angle shape of the upper breast and back in the middle of period and angle shape of the lower breast and back in the latter of period 7)Factor 7 is angle of shoulder in the latter of period 2. Through the factor analysis by each period of school ages 5-6 factor were obtained in lower half and they are as followings: 1) factor 1 is horizontal size of upper half in every period 2) Factor 2 is vertical size of upper half in every period 3) Pactor 3 is angle shape of the belly and upper buttock in the first period and length of lower half in the middle and latter period 5) Factor 5 is angle shape of the lower buttock in the first period angle shape of the upper belly and buttock in the middle of period and angle of the side posture in the latter of period 6) Factor 6 is angle shape of the lower buttock in the middle of period and angle shape of the lower belly and buttock