• 대한한의학회지
• /
• 제41권3호
• /
• pp.1-8
• /
• 2020

Objectives: This paper aims to investigate the Donguibogam-based pattern diagnosis by applying natural language processing and machine learning. Methods: A database has been constructed by gathering symptoms and pattern diagnosis from Donguibogam. The symptom sentences were tokenized with nouns, verbs, and adjectives with natural language processing tool. To apply symptom sentences into machine learning, Word2Vec model has been established for converting words into numeric vectors. Using the pair of symptom's vector and pattern diagnosis, a pattern prediction model has been trained through Logistic Regression. Results: The Word2Vec model's maximum performance was obtained by optimizing Word2Vec's primary parameters -the number of iterations, the vector's dimensions, and window size. The obtained pattern diagnosis regression model showed 75% (chance level 16.7%) accuracy for the prediction of Six-Qi pattern diagnosis. Conclusions: In this study, we developed pattern diagnosis prediction model based on the symptom and pattern diagnosis from Donguibogam. The prediction accuracy could be increased by the collection of data through future expansions of oriental medicine classics.

• Korean Journal of Acupuncture
• /
• 제37권3호
• /
• pp.203-208
• /
• 2020

Objectives : Since there are complex associations between diseases/symptoms and acupoints, one-to-one correspondence may not be the proper approach. Pattern identification has been being used as a clinical framework to make treatment decisions by extracting and synthesizing clinical data including patients' signs and symptoms. In this article, we propose two different models explaining the relationships between diseases and acupoints based on the branch treatment [Zhibiaofa] and the root treatment [Zhibenfa]. Methods : We explained the relationships between diseases/symptoms and acupoints from the example data from our previous study on traditional acupuncture point selection patterns for pain control. Diseases include low back pain, migraine, irritable bowel syndrome, osteoarthritis, ankle sprain, carpal tunnel syndrome, and dysmenorrhea, and acupoints included LI4, BL23, BL25, SP6, BL60, TE5, and CV4. Results : The relationships between diseases/symptoms and acupoints can be explained directly based on the branch treatment, and also can be explained indirectly through pattern identification based on the root treatment. Pattern identifications included both meridian-based pattern identification based on the spatial information of diseases and visceral organ-based pattern identification based on the characteristics of diseases. Conclusions : In the East Asian traditional medicine, Korean medicine doctors choose the most appropriate acupoints based either on the diseases/symptoms (i.e., branch treatment) or on the results of pattern identifications (i.e., root treatment). It is necessary to understand the two different approaches to choose specific acupoints for the targeted diseases.

• 전자공학회논문지B
• /
• 제31B권4호
• /
• pp.1-8
• /
• 1994

In this paper, we propose an efficient two-step pattern matching method which promises shape distortion-tolerant recognition of handwritten of handwritten Hangul syllables. In the first step, nonlinear shape normalization is carried out to compensate for global shape distortions in handwritten characters, then a preliminary classification based on simple pattern matching is performed. In the next step, nonlinear pattern matching which achieves best matching between input and reference pattern is carried out to compensate for local shape distortions, then detailed classification which determines the final result of classification is performed. As the performance of recognition systems based on pattern matching methods is greatly effected by the quality of reference patterns. we construct reference patterns by combining the proposed nonlinear pattern matching method with a well-known averaging techniques. Experimental results reveal that recognition performance is greatly improved by the proposed two-step pattern matching method and the reference pattern construction scheme.

• 전력전자학회논문지
• /
• 제4권6호
• /
• pp.616-623
• /
• 1999

엘리베이터의 속도패턴은 출발시부터 목표 위치 근처에 다다를 때까지의 시간기준 속도패턴과 정밀한 정위치 정지를 위한 거리기준 속도패턴등로 이루어진다. 시간기준 속도패턴에서 거리기준 속도패턴으로 절환시 속도와 가속도의 급격한 변화가 없도록 하여야 패턴 절환시의 충격을 최소화하여 안락한 승차감을 얻을 수 있다. 본 논문에서는 속도패턴 절환 시 항상 속도와 가속도가 연속이 되도록 하고, 또한 목표 위치로의 수렴 속도를 개선한 새로운 엘리베이터 속도패턴 발생 방법을 제시한다.

• 한국의류산업학회지
• /
• 제13권5호
• /
• pp.734-742
• /
• 2011

This study has been undertaken as a basic research for automatic pattern design for baseball uniforms manufactured under custom-MTM system, propose building up of a system whereby various partial patterns are combined under an automatic design system and develop a multi-combination type pattern searching algorithm which allows development of a various designs. As a result of this, type classification based on pattern design elements includes side, open, collar, facing and panel type. Design have been divided into coarse classification ranging from level 1 to 7 according to pattern design elements, based on a design distribution chart. Out of 7 such levels, 3 major types determining design which are, more specifically, level 1 sleeve type, level 2 open type and level 3 collar type, have been taken and combined to determine a total of 12 types to be used for design classification codes. Respective name of style and patterns have been coded using alphabet and numerals. Totally, pattern searching algorithm of multi-combination type has been developed whereby combination of patterns belonging to a specific style can be retrieved automatically once that style name is designated on the automatic pattern design system.

• 한국언어정보학회지:언어와정보
• /
• 제14권2호
• /
• pp.159-181
• /
• 2010

This paper presents a hybrid approach to the sentiment analysis of online texts. The sentiment of a text refers to the feelings that the author of a text has towards a certain topic. Many existing approaches employ either a pattern-based approach or a machine learning based approach. The former shows relatively high precision in classifying the sentiments, but suffers from the data sparseness problem, i.e. the lack of patterns. The latter approach shows relatively lower precision, but 100% recall. The approach presented in the current work adopts the merits of both approaches. It combines the pattern-based approach with the machine learning based approach, so that the relatively high precision and high recall can be maintained. Our experiment shows that the hybrid approach improves the F-measure score for more than 50% in comparison with the pattern-based approach and for around 1% comparing with the machine learning based approach. The numerical improvement from the machine learning based approach might not seem to be quite encouraging, but the fact that in the current approach not only the sentiment or the polarity information of sentences but also the additional information such as target of sentiments can be classified makes the current approach promising.

• 복식
• /
• 제60권1호
• /
• pp.101-116
• /
• 2010

In this study, the subjects are the expression methods and compositions of peony patterns in Chinese textiles. This study represents the peony patterns which are from Tang Dynasty to the Qing Dynasty, the research subjects are the peony patterns in fabric, except the peony patterns which are expressed by gold foil, embroidery and kesi. The objects of this study are 72 pieces of peony patterns. We sketched the configuration details of peony patterns through the Illustrator program. Analyze and classify the configuration accurately. Based on the 72 pieces of peony patterns, expression methods and compositions of the peony pattern are as following, firstly, we classified peony patterns into three categories, based on expression methods, as realistic shape, pattern shape and shape. Among these 72 fabric relics, there most of realistic shape 42 pieces(58.3%), pattern shape 25 pieces(34.7%), and shape 5 pieces(7.0%). Secondly, in the realistic shape peony, the most of pattern has petal accumulate as grape- shaped. This type is found in almost every Dynasty and was used regularly in the eras of Song and Ming Dynasty. In the era of Ming Dynasty, by using petals like the curly mushroom, Yeongji(靈芝), the pattern of symbolizing longevity was habitually used. The U-shaped flower pattern (type E) and the pattern of emphasizing the veins of petals are found only in the remains of the era of Qing Dynasty. Thirdly, in the pattern shaped peony, the most of pattern has some petals which are separated(type C). Fourthly, we classified peony patterns into four categories, based on compositions, as individual branch form, floral branch form, cluster branch form and floral nest form. Among these 72 fabric relics, there most of individual branch form 33 pieces(45.8%), floral branch form 18 pieces(25.0%), cluster branch form 13 pieces(18.1%), floral nest form 8 pieces(11.1%).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권4호
• /
• pp.711-725
• /
• 2013

A heuristic with multi-byte suffix matching plays an important role in real pattern matching algorithms. By skipping many characters at a time in the process of comparing a given pattern with the text, the pattern matching algorithm based on a heuristic with multi-byte suffix matching shows a faster average search time than algorithms based on deterministic finite automata. Based on various experimental results and simulations, the previous works show that the pattern matching algorithms with multi-byte suffix matching performs well. However, there have been limited studies on the mathematical model for analyzing the performance in a standard manner. In this paper, we propose a new probabilistic model, which evaluates the performance of a heuristic with multi-byte suffix matching in an average-case search. When the theoretical analysis results and experimental results were compared, the proposed probabilistic model was found to be sufficient for evaluating the performance of a heuristic with suffix matching in the real pattern matching algorithms.

• 정보처리학회논문지D
• /
• 제13D권7호
• /
• pp.947-958
• /
• 2006

컴포넌트 확장성 및 재사용성을 향상시키기 위해서는 분석단계에서부터 가변적인 것들을 규칙기반으로 분석해서 컴포넌트로 식별할 필요가 있다. 본 논문에서는 시스템 외부 이벤트에 대해 트랜잭션 처리를 규칙기반으로 처리해야 하는 도메인 상에서 객체 기반의 중요 개념을 규칙기반으로 효과적으로 추출해 UML Components 개발 프로세스 상에서 가변적인 컴포넌트를 개발할 수 있는 규칙 기반 분석 패턴을 제시한다. 업무 지식이나 경험이 다른 많은 분석가들이 서브 시스템 많은 규칙 기반의 가변적인 복잡한 비즈니스 업무 분석 시 제안한 분석 패턴을 사용할 경우 분석 산출물의 일관성이나 가독성을 좋게 하며 또한 UML Components 방법론상에서 효과적으로 가변적인 비즈니스 컴포넌트들을 식별할 수 있다. 이러한 분석 패턴의 타당성을 증명하기 위해 본 논문에서는 가변적인 규칙기반으로 업무를 처리하는 은행 수신과 수출입 업무 도메인에 적용한 결과 패턴에서 제시한 중요 개념을 기반으로 거의 유사한 비즈니스 개념 모델을 도출할 수 있었으며 또한 이들 중요 개념을 기반으로 UML Components 개발 프로세스 상에서 가변적인 비즈니스 컴포넌트를 효과적으로 식별할 수 있었다.

• Journal of Acupuncture Research
• /
• 제26권3호
• /
• pp.115-131
• /
• 2009

Objectives: This survey was done in order to find out how Korean medical doctors derive pattern identification for acupuncture prescriptions in treating low back pain in real clinical practice. Methods : The survey questionnaire was developed by the committee of experts who major in acupuncture & moxibustion or statistics for acupuncture clinical trial protocol development. The questionnaires were distributed via e-mail to 75 members of Korean Acupuncture & moxibustion society from March 26th to April 14th in 2009. 57 members completed answers, and the computerized data were analyzed by SPSS 17.0 statistical program. Results : 1.57 Korean medical doctors selected meridian pattern identification based on the course of the meridians(44.6%), visceral pattern identification(32.1%), pattern identification based on cause of disease(14.3%) as the most commonly used pattern identification methods for acupuncture prescription when treating low back pain patients in real clinical practice. 2. In meridian pattern identification based on the course of the meridians, gallbladder meridian of hypochondriac region(13.0%), bladder meridian of lateral low back region(11.2%), governer vessel of central low back region(11.7%) were selected 3. In visceral pattern identification, yang deficiency of kidney(20.2%), deficiency of kidney(19.3%), liver(16.7%), yin deficiency of kidney(14.0%), violence qi of kidney(8.8%), small intestine(7.9%) were selected. Conclusions : In our e-mail survey, Korean medical doctors answered that Meridian Pattern Identification based on the course of the meridians is the most often used diagnosis method. Visceral pattern identification, pattern identification based on cause of disease, meridian pattern identification based on symptom and pattern identification based on qi-blood-yin-yang theory in order of frequency used, were selected for low back pain diagnosis in real clinical practice.