• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2000년도 춘계학술대회논문집A
• /
• pp.505-510
• /
• 2000

Vehicle performances such as fuel consumption and catalyst-out emissions are affected by a driving pattern, which is defined as a driving cycle with the grade in this study. We developed an algorithm to recognize a current driving pattern by using a neural network. And this algorithm can be used in adapting the driving control strategy to the recognized driving pattern. First, we classified the general driving patterns into 6 representative driving patterns, which are composed of 3 urban driving patterns, 2 suburban driving patterns and 1 expressway driving pattern. A total of 24 parameters such as average cycle velocity, positive acceleration kinetic energy, relative duration spent at stop, average acceleration and average grade are chosen to characterize the driving patterns. Second, we used a neural network (especially the Hamming network) to decide which representative driving pattern is closest to the current driving pattern by comparing the inner products between them. And before calculating inner product, each element of the current and representative driving patterns is transformed into 1 and -1 array as to 4 levels. In the end, we simulated the driving pattern recognition algorithm in a temporary pattern composed of 6 representative driving patterns and, verified the reliable recognition performance.

• 전자공학회논문지B
• /
• 제30B권6호
• /
• pp.67-75
• /
• 1993

ECG pattern was classified using a back-propagation neural network. An improved feature extractor of ECG is proposed for better classification capability. It is consisted of preprocessing ECG signal by an FIR filter faster than conventional one by a factor of 5. QRS complex recognition by moving-window integration, and peak extraction by quadratic approximation. Since the FIR filter had a periodic frequency spectrum, only one-fifth of usual processing time was required. Also, segmentation of ECG signal followed by quadratic approximation of each segment enabled accurate detection of both P and T waves. When improtant features were extracted and fed into back-propagation neural network for pattern classification, the required number of nodes in hidden and input layers was reduced compared to using raw data as an input, also reducing the necessary time for study. Accurate pattern classification was possible by an appropriate feature selection.

• 한국의류산업학회지
• /
• 제10권6호
• /
• pp.857-863
• /
• 2008

The purpose of this study is to analyze the types of Hibiscus patterns expressed on Aloha shirts. This study analyzed real data collected from man's aloha shirts displayed at the International Market Place in Waikiki of Hawaii during January 21-27, 2007. 35 pieces of Aloha shirts with Hibiscus Patterns were was analyzed. The total of each analysis means all number of patterns sampled or appeared to analyze the types of patterns. The motif of Hibiscus was sampled a total of 42 units for some shirts having several motifs. Its motif was divided into two groups, 20 units(47.62%) of natural type and 22 units(52.38%) of stylized type, according to modeling. Two types were much the same percentage. Hibiscus patterns were classified into three groups, isolated, band and arabesque type, by formation type. The isolated type was appeared most frequently. The layout of Hibiscus pattern was classified into three groups, engineered print, all over print and border print. All over print was appeared most frequently. The data of this study will be provided as a resource to promote using and developing of the pattern of Korean rose of Sharon.

• 한국레이저가공학회지
• /
• 제3권2호
• /
• pp.53-61
• /
• 2000

On the laser weld production line, a slight alteration of the welding condition produces many defects. The defects are monitored in real time, in order to prevent continuous occurrence of defects, reduce the loss of material, and guarantee good quality. The measurement system is produced by using three photo-diodes for detection of the plasma and spatter signal in CO$_2$ laser welding. For high speed CO$_2$ laser welding, laser tailored welded blanks for example, on-line weld quality monitoring system was developed by using fuzzy multi-feature pattern recognition. Weld qualities were classified optimal heat input, a little low heat input, low heat input, and focus misalignment, and final weld quality were classified good and bad.

• 한국멀티미디어학회논문지
• /
• 제18권11호
• /
• pp.1281-1288
• /
• 2015

Nongroup Cellular Automata(CA) having two trees in the state transition diagram of a CA is suitable for pattern classifier which divides pattern set into two classes. Maji et al. [1] classified patterns by using multiple attractor cellular automata as a pattern classifier with dependency vector. In this paper we propose a method of generation of a pattern classifier using feature vector which is the extension of dependency vector. In addition, we propose methods for finding nonreachable states in the 0-tree of the state transition diagram of TPMACA corresponding to the given feature vector for the analysis of the state transition behavior of the generated pattern classifier.

• 한국의상디자인학회지
• /
• 제7권3호
• /
• pp.83-94
• /
• 2005

This paper is to analyze patterns for Indonesian traditional textiles. Ikat is the resist-dyeing process in which designs are reserved in warp or weft yams by tying off small bundles of threads with fiber resists to prevent the penetration of dye. Batik is the technique applying a wax resist before dyeing to form a pattern in negative. Ikat and batik are the most renowned textile arts of Indonesia. Patterns are classified as geometric pattern, plant pattern, animal pattern. Also this paper discusses the origins of ikat and batik. Therefore this Paper proposes the classification and feature extraction of ikat and batik patterns. The results of this study can be effectively applied to develop competitive pattern design for Indonesian textile market.

• Archives of Pharmacal Research
• /
• 제22권4호
• /
• pp.335-339
• /
• 1999

The oxidation-reduction potentials of cosmetic raw materials, showing tyrosinase inhibitory action, and phenolic compounds structurally similar to L-tyrosine were determined by cylcic voltammetry. The voltammograms obtained could be classified ito 4 patterns (patterns 1-4). Patterns 1, characterized by oxidation and reduction peaks as a pair, was observed with catechol, hydroquinone or phenol, and pattern 2 exhibiting another oxidation peak in addition to oxidation and reduction peaks as a pair was found with arbutin, kojic acid, resorcinol, methyl p-hydroxybenzoate and L-tyrosine as the substrate of tyrosinase. Pattern 3 with an independent oxidation peak only was expressed by L-ascorbic acid, and pattern 4 with a reduction peak only at high potentials, by hinokitiol. The tyrosinase inhibitory activity of these compounds was also evaluated using the 50% inhibitory concentration ($IC_{50}$) and the inhibition constant (Ki) as parameters. Hinokitiol, classified as patterns 4, showed the highest inhibitory activity (lowest $IC_{50}$ and Ki). Hydroquinone showing the second highest activity belonged to pattern 1, which also included compounds exhibiting pattern 2 was relatively low with Ki values being in the order of 10-4 M. Although there was no consistent relationship between oxidation-reduction potentials and tyrosinase inhibitory action, the voltammetry data can be used as an additional index to establish the relationship between the structure and the tyrosine inhibitory activity.

• 한국지능시스템학회논문지
• /
• 제13권5호
• /
• pp.530-538
• /
• 2003

최근 마케팅 업계의 동향을 보면 기존 고객 유지에 대한 필요성을 중요시하면서, 타깃 마케팅의 개념에 의한 고객집단의 세분화된 분류와 각각의 세분화된 고객집단에 대한 차별적인 대응이 요구되고 있다. 본 논문에서는 신경망과 연관규칙의 Cumulate 알고리즘을 이용하여 고객집단을 분류하고 고객집단간의 구매패턴을 분류하는 시스템을 구현하였다. 실제 특정 두 집단간의 연관규칙을 조사한 결과 서로 간에 비슷한 연관규칙이 있음을 알 수 있었고, 마케팅 의사결정을 위해 우량／일반 고객집단으로 분류해야 할 필요성이 있음을 밝혔다. 따라서 고객집단의 분류에 있어 예측율의 정확성을 높임으로써 차별적인 마케팅의 효율을 극대화 할 수 있음을 보였다.

• 복식
• /
• 제56권3호
• /
• pp.116-128
• /
• 2006

The purpose of this study is to investigate Seon expressed in the costume of Chinese Song. For the purpose, this researcher classified types of Seon, found in the Chinese costume, in terms of composition method, decorative technique and used materials. In addition, the researcher attempted to analyze formative characteristics of Sean in accordance with the range and post of use, pattern and color combination. Seon expressed in the costume of Chinese Song can be classified into standard, decoration, application and Buseon in type. When the typical distribution of Seon expressed in the costume of Chinese Song, standard type was highest in percentage, especially different color type. Looking at the range of use, Seon was mainly used for outfits, especially Jikcheol(直?) and Hakchangeui for men and Baeja(背子) for women. Looking at the post of use, Seon was mainly used to edges of costume and sometimes also to seams. In regard to materials of Seon, they were selectively used depending on the existence or non-existence, size and brilliance or non-brilliance of pattern employed in the texture of Seon. The most commonly used pattern of Seon was single-type pattern, especially the pattern of plant. Pattern arrangement was most often filling in type. Concerning the color combination of Seon, men's dress most often used black-white combination, followed by different color combination while, women's dress most often employed complementary color combination, followed by different color combination.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1990년도 추계학술대회 논문집 학회본부
• /
• pp.428-431
• /
• 1990

This paper describes a pattern classification algorithm of QRS-complexes using significant point detection for extracting features of signals. Significant point extraction was processed by zero-crossing method, and decision function based on relational spectrum was used for pattern classification of the QRS-complexes. The hierarchical AND/OR graph was obtained by decomposing the signal, and by use of this graph, QRS's patterns were classified. By using the proposed algorithm, the accuracy of pattern classification and the processing speed were improved.