• 한국지능시스템학회논문지
• /
• 제11권7호
• /
• pp.675-679
• /
• 2001

In this paper, we present a new competitive learning algorithm called Dynamic Competitive Learning (DCL). DCL is a supervised learning method that dynamically generates output neurons and initializes automatically the weight vectors from training patterns. It introduces a new parameter called LOG (Limit of Grade) to decide whether an output neuron is created or not. If the class of at least one among the LOG number of nearest output neurons is the same as the class of the present training pattern, then DCL adjusts the weight vector associated with the output neuron to learn the pattern. If the classes of all the nearest output neurons are different from the class of the training pattern, a new output neuron is created and the given training pattern is used to initialize the weight vector of the created neuron. The proposed method is significantly different from the previous competitive learning algorithms in the point that the selected neuron for learning is not limited only to the winner and the output neurons are dynamically generated during the learning process. In addition, the proposed algorithm has a small number of parameters, which are easy to be determined and applied to real-world problems. Experimental results for pattern recognition of remote sensing data and handwritten numeral data indicate the superiority of DCL in comparison to the conventional competitive learning methods.

• 한국레이저가공학회지
• /
• 제13권2호
• /
• pp.1-5
• /
• 2010

A high speed laser texturing method that relies on laser scanner conditions, to form pattern shapes with micro-narrow surface detail such as dotted line features is demonstrated and analyzed. For example, this method may be used to piston ring and gear part for automotive. Data on friction characteristics of two laser patterns employed for STD61 steel will be shown. Comparison of pattern depths obtained by repetition overlapping process with laser scanner to the results on friction coefficient will be provide. It will be shown that friction characteristic in dotted line patterns can significantly depend upon interaction with the lubrication and laser pattern conditions. Laser pattern processing into a shallow depth provides only slight improvement in friction, while work into a deep shape indicates a significant improvement.

• 제어로봇시스템학회논문지
• /
• 제12권9호
• /
• pp.935-944
• /
• 2006

EMG pattern recognition is essential for the control of a multifunction myoelectric hand. The main goal of this study is to develop an efficient feature projection method for EMC pattern recognition. To this end, we propose a linear supervised feature projection that utilizes linear discriminant analysis (LDA). We first perform wavelet packet transform (WPT) to extract the feature vector from four channel EMC signals. For dimensionality reduction and clustering of the WPT features, the LDA incorporates class information into the learning procedure, and finds a linear matrix to maximize the class separability for the projected features. Finally, the multilayer perceptron classifies the LDA-reduced features into nine hand motions. To evaluate the performance of LDA for the WPT features, we compare LDA with three other feature projection methods. From a visualization and quantitative comparison, we show that LDA has better performance for the class separability, and the LDA-projected features improve the classification accuracy with a short processing time. We implemented a real-time pattern recognition system for a multifunction myoelectric hand. In experiment, we show that the proposed method achieves 97.2% recognition accuracy, and that all processes, including the generation of control commands for myoelectric hand, are completed within 97 msec. These results confirm that our method is applicable to real-time EMG pattern recognition far myoelectric hand control.

• 한국의류학회지
• /
• 제6권2호
• /
• pp.57-67
• /
• 1982

The purpose of this study was to improve the clothing life of the children between the nine to twelve by making a scientific and rational basic bodice pattern. The comparison of the eight pattern drafting currently used in Korea was referred in order to make new basic pattern. Three hundred fifty-two subjects from 9 to 12 years old in Seoul area were measured on 19 items. The measurements (24 items including 19 measured items and 5 drafted items that were difficult to measure) were analyzed by mean values and correlation coefficients between each item. This new pattern attempted to set the ease for clothing from experiments of the changes of body surface in motion. On the basis of the above results, a new bodice basic pattern was developed and tested with wearing three times. Through the experiments in measuring the changes of the body surface in motion, it was concluded that it desirable to set a standard of 12cm clothing ease on the bust circumference and 4cm on the waist circumference. The correlation coefficient of the tack width to across back was relatively high (r= .677), therefore, the latter measuring items were eliminated. A grading method was adopted to determine the width and depth of neckline and shoulder slope.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.403-413
• /
• 2022

Classification and analysis are improved factors for the realtime automation system. In the field of agriculture, the cultivation of different paddy crop depends on the atmosphere and the soil nature. We need to analyze the moisture level in the area to predict the type of paddy that can be cultivated. For this process, Ensemble Modulation Pattern system and Block Probability Neural Network based classification models are used to analyze the moisture and temperature of land area. The dataset consists of the collections of moisture and temperature at various data samples for a land. The Ensemble Modulation Pattern based feature analysis method, the extract of the moisture and temperature in various day patterns are analyzed and framed as the pattern for given dataset. Then from that, an improved neural network architecture based on the block probability analysis are used to classify the data pattern to predict the class of paddy crop according to the features of dataset. From that classification result, the measurement of data represents the type of paddy according to the weather condition and other features. This type of classification model assists where to plant the crop and also prevents the damage to crop due to the excess of water or excess of temperature. The result analysis presents the comparison result of proposed work with the other state-of-art methods of data classification.

• 한국의류산업학회지
• /
• 제15권6호
• /
• pp.950-962
• /
• 2013

The purpose of this study was to develop the slim-fit dress shirt pattern. Among the published educational patterns, there were four patterns based on similar design and silhouette with slim-fit dress shirts. Then, the drafting method of those patternsBB were compared and analyzed. The subjects for wearing evaluation were three 20 to 39 aged average-sized men. After the wearing evaluation(5 Likert point scale), N pattern had been chosen as the final comparison pattern because it received the highest points. The slim-fit shirt pattern was developed based on the result of wearing evaluation. The foundation design were as following: shirt length (Stature/2-12), back length (Stature/4), armhole depth (Chest/4+1), width (Chest/4+3), Interscye; Back (Chest/6+5), Interscye; Front (Chest/6+4), width of the nape of neck (Neck/6+1=◎), height of the nape of neck (◎/3), of the front neck (◎-0.5), depth of the front neck(◎+1.5). After the wearing evaluation about researched pattern and N pattern, researched patternsBB scale points were bigger than N pattern and there were slight differences. The scale points for N patternsBB movement evaluation showed highest points on all contents. Therefore, the researched pattern is suitable for the original form of slim-fit dress shirt. The new dress shirt pattern reflected the slim-fit trend in the research expected to help educational environment and industrial site.

• 한국의류산업학회지
• /
• 제23권5호
• /
• pp.634-644
• /
• 2021

This study aims to propose various ways to utilize CLO, which focuses mainly on the production of 3D virtual samples, by comparing it with the pattern drafting functions of Four apparel CAD experts, who have teaching experience in YUKA and CLO, participated in a focus group interview, and a basic bodice prototype drafting was carried out by each participant to evaluate the pattern drafting functions of YUKA and CLO. The result of this study showed that the pattern drafting tools of YUKA are subdivided since YUKA is a CAD tool inherently specialized in pattern making. Though CLO provided a relatively limited pattern drafting menu compared to YUKA, it was found that pattern drafting could be accomplished with the help of supplementary tools and functions. This finding suggests that each CAD offers the corresponding tools for the same use of menus or functions in the prototype drafting process. The major difference between YUKA and CLO is that YUKA defines the pattern area by a set of line segments, whereas CLO utilizes an outline composed of closed curves. YUKA provides various specific tools according to the options such as angles, straight lines, and curves, while CLO produces the same results using combinations of a limited number of tools. Compared with YUKA, the advantage of CLO is its user-friendly task environment such as the Windows-based user interface, from the usability perspective. This study concludes that pattern drafting education using CLO would help not only industrial 3D design practitioners but also pattern education in academia

• 동력기계공학회지
• /
• 제20권4호
• /
• pp.75-82
• /
• 2016

In this paper, we developed a 3D printing system using a photo-curing resin in order to reduce the surface roughness of a sculpture produced with the 3D printer. Using the pattern of the resulting variable thickness, that gave rise to a stepped shape, and the area error of the photo-curable sculpture, a study was carried out for the process to reduce the surface roughness. At a given value of stage velocity (40~70 mm/s) and output air pneumatic pressure (20~60 kPa), the minimum pattern thickness of the pattern was achieved $65{\mu}m$ and the maximum pattern thickness of up to $175{\mu}m$. To increases the pattern resolution to about $40{\mu}m$, the process conditions should be optimized. 3D surface Nano profiler was used to find the surface roughness of the sculpture that was measured to be minimum $4.7{\mu}m$ and maximum $8.7{\mu}m$. The maximum surface roughness was reduced about $1.2{\mu}m$ for the maximum thickness of the pattern. In addition, a FDM was used to fabricate the same sculpture and its surface roughness measurements were also taken for comparison with the one fabricated using photo-curing. Same process conditions were used for both fabrication setups in order to perform the comparison efficiently. The surface roughness of the photo-curable sculpture is $5.5{\mu}m$ lower than the sculpture fabricated using FDM. A certain circuit patterns was formed on the laminated surface of the photo-curable sculpture while there was no stable pattern on the laminated surface of the FDM based sculpture the other hand.

• 한국컴퓨터정보학회논문지
• /
• 제25권6호
• /
• pp.183-191
• /
• 2020

본 연구에서는 커스터마이징 시스템 개발을 위한 신한복 치마 패턴 개발의 기초자료를 얻기 위해 신한복 브랜드의 치마 패턴을 비교 분석하고자 하였다. 신한복 6개 브랜드의 패턴을 분석하여 가상착의를 시킨 후 외관평가와 의복압 및 공극량을 평가하였다. 시판 신한복 브랜드 A, B, C, D, E, F의 허리치마 패턴을 분석한 결과, 같은 디자인의 free 사이즈 치마임에도 불구하고 각기 다른 치수로 제작되는 것으로 나타났다. 허리치마의 패턴은 기존의 한복과 같이 평면적인 패턴으로 구성되었다. 외관평가 결과 앞면, 옆면, 뒷면 모든 평가항목에서 6개 브랜드의 패턴 간에 유의미한 차이가 있는 것으로 평가되었다. 외관평가 모든 항목에서 B 브랜드의 허리치마가 우수한 것으로 평가되었다. 의복압을 알아보기 위해 색분포도와 공극량을 살펴본 결과, 허리에 둘러서 착용하는 허리치마의 특성상 대부분의 부위에서 공극량이 큰 것으로 나타나 의복압이 낮은 것으로 평가되었다. 본 연구에서는 신한복 활성화에 따른 치수 및 패턴 규격화를 위한 기초자료를 제안하며, B브랜드 패턴을 기본으로 한 통일된 패턴개발이 이루어져야 할 것으로 생각된다.

• 대한소아치과학회지
• /
• 제5권1호
• /
• pp.12-18
• /
• 1978

The author has observed the ectopic eruption pattern on oblique cephalogram of 195 children. (5years: 78, 6 years: 58, 7 years: 59). The results were as follows; 1) Making a comparison between hold type and jump type of ectopic eruption, there are 4 cases in Hold type, 5 cases in jump type. 2) Making a comparison of ectopic eruptin between male and female, there are 7 cases in male, 2 cases in female. 3) Making a comparison of ectopic eruption between right side and left side, there are 5 cases at right side, 4 cases at left side. 4) Making a comparison of ectopic eruption among 5 years to 7 years, there are 4 cases in 5 years, 3 cases in 6 years, 2 cases in 7 years. 5) The prevalence of ectopic eruption of the maxillary first molar was 4.61%. 6) Normal eruption angle of the maxillary first molar is prevailing in $80^{\circ}{\sim}85^{\circ}$.