• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2009년도 추계학술발표대회
• /
• pp.369-370
• /
• 2009

Robot이 음악에 맞춰 어떤 행동을 하기 위해선 먼저 Acoustic을 이해 할 수 있는 인지 능력이 필요하며 인지한 음악적 내용을 Dance Motion에 가깝게 Action을 표현할 수 있어야 한다. 본 논문에서는 신호처리와 기계학습을 사용하여 음악의 Tempo를 Tracking하고 이것을 참고하여 행동 Pattern을 결정하는 Dance Robot System을 소개한다.

• 동의신경정신과학회지
• /
• 제30권1호
• /
• pp.1-11
• /
• 2019

Objectives: Attention-Deficit/Hyperactivity Disorder (ADHD) is characterized by a persistent pattern of inattention and/or hyperactivity impulsivity that interferes with function or development in children. In traditional Korean medicine (TKM) and traditional Chinese medicine (TCM), ADHD is classified by several patterns based on symptoms and signs. However, currently, there is no objective diagnostic tool for ADHD in traditional medicine. The objective of this study was to develop the Pattern Identification Questionnaire for ADHD (parents-survey style) to be used in Korean medicine, through a literature review and consultation with groups of experts. Methods: The types of pattern identifications of ADHD mentioned in 13 pieces of Korean and Chinese literatures and their symptoms and signs were analyzed. The advisory committee (15 Neuropsychiatrist and 11 Pediatrist in Korean Medicine) assessed the appropriateness of the literature selection and the types of pattern identification selection and their symptoms and signs, and weighed the significance of the symptoms and signs. The Pattern Identification Questionnaire for ADHD was developed using the calculated weights by evaluated significance. The translation of symptoms and signs to the Korean language was achieved through consultation with expert translators. Results: 1. Four pattern identification types and their symptoms and signs were selected according to frequency of appearance in the Korean and Chinese literatures, and were reviewed by the advisory committee: Kidney yin deficiency and liver yang ascendant hyperactivity (腎虛肝亢), Dual deficiencies in the heart and spleen (心脾兩虛), Phlegm-fire harassing the heart (痰火擾心), and Spleen weakness and liver energy preponderance (脾虛肝旺). 2. The weights of all the symptoms and signs in the four patterns were calculated using the means and standard deviations of the symptoms and signs' importance that were obtained from specialists' significance weighting. 3. The Pattern Identification Questionnaire for ADHD (parents-survey style) in Korean medicine composed of 38 questions was suggested. Conclusions: Using a review of the literature and expert advice, Pattern Identification Questionnaire for ADHD (parents-survey style) in Korean medicine was developed. Further clinical study is required to develop a final version of the questionnaire through the evaluation of reliability and validity.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 춘계학술대회
• /
• pp.304-309
• /
• 2003

In this study, natural flaws in welding parts are classified using the signal pattern classification method. The storage digital oscilloscope including FFT function and enveloped waveform generator is used and the signal pattern recognition procedure is made up the digital signal processing, feature extraction, feature selection and classifier design. It is composed with and discussed using the distance classifier that is based on euclidean distance the empirical Bayesian classifier. Feature extraction is performed using the class-mean scatter criteria. The signal pattern classification method is applied to the signal pattern recognition of natural flaws.

• 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.

• 한국컴퓨터정보학회논문지
• /
• 제20권11호
• /
• pp.9-16
• /
• 2015

We propose a hybrid pattern recognition method that effectively combines two different features for improving data classification. We first extract the PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis) features, both of which are widely used in pattern recognition, to construct a set of basic features, and then evaluate the separability of each basic feature. According to the results of evaluation, we select only the basic features that contain a large amount of discriminative information for construction of the combined features. The experimental results for the various data sets in the UCI machine learning repository show that using the proposed combined features give better recognition rates than when solely using the PCA or LDA features.

• E2M - 전기 전자와 첨단 소재
• /
• 제11권11호
• /
• pp.1-8
• /
• 1998

This paper presents an arificial neuro-fuzzy technique based prtial discharge (PD) pattern classifier to power system application. This may require a complicated analysis method employ -ing an experts system due to very complex progressing discharge form under exter-nal stress. After referring briefly to the developments of artificical neural network based PD measurements, the paper outlines how the introduction of new emerging technology has resulted in the design of a number of PD diagnostic systems for practical applicaton of residual lifetime prediction. The appropriate PD data base structure and selection of learning data size of PD pattern based on fractal dimentsional and 3-D PD-normalization, extraction of relevant characteristic fea-ture of PD recognition are discussed. Some practical aspects encountered with unknown stress in the neuro-fuzzy techniques based real time PD recognition are also addressed.

• 스마트미디어저널
• /
• 제1권1호
• /
• pp.36-41
• /
• 2012

특징 선택은 패턴 인식의 성능을 향상시키기 위해 부분집합을 구성하는 중요한 문제다. 특징 선택에는 순차 탐색 알고리즘으로부터 확률 기반의 유전 알고리즘까지 다양한 접근 방법이 적용 되었다. 본 연구에서는 특징 선택을 위해 양자 비트, 상태의 중첩 등 양자 컴퓨터 개념을 기반으로 하는 양자 기반 유전 알고리즘(QGA: Quantum-inspired Genetic Algorithm)을 적용하였다. QGA 성능은 전통적인 유전 알고리즘(CGA: Conventional Genetic Algorithm)을 적용한 특징 선택 방법과 분류율 및 평균 특징 개수의 비교를 통해 이루어졌으며, UCI 데이터를 이용한 실험 결과 QGA를 적용한 특징 선택 방법이 CGA를 적용한 경우에 비해 전반적으로 좋은 성능을 보임을 확인 할 수 있었다.

• 대한기계학회논문집
• /
• 제16권4호
• /
• pp.696-706
• /
• 1992

본 연구에서는 공구선정 작업의 자동화를 목표로 하였다.공구선정을 완전 자동으로 행하기 위해 해결해야 할 문제는, 현재 공구대(turret)에 장착되어 있는 공 구중에서 어떤 공구를 얼마칸큼 직선, 회전 이동시키면 판재 경계와 정확하게 일치하 는가 하는 문제와, 복잡한 형상의 펀칭을 위해선 효과적인 공구조합은 어떻게 해야하 나 하는 문제로 귀결되므로 이 두가지 문제의 해결방안을 기술한다.

• 산업경영시스템학회지
• /
• 제35권2호
• /
• pp.163-172
• /
• 2012

In this study, It is assumed that customers are both usage unit of spare parts and stores of displaying and selling the goods that are installation unit of having the spare parts. The demand pattern through the effective order of spare parts and issue list in installation unit is investigated based on the assumption. Current ASL (Authorized Stockage List) selection of the army has been conducted in the way of using the analysis result of real usage experiences on spare parts used during the Korea War. For this study, ASL selection criteria and procedures based on army regulations and field manuals are specified. Since the traditional method does not presents the association analysis on spare parts used for the current equipment operating and does not have the clear criterion and analysis system about the ASL selection, in order to solve these problems, it was carried out that the association rule is employed for analyzing relationship between the effective order and issue list of the spare parts in point of the spare parts between usage unit and occurring month about purchase spare parts based on the star-schema table. Finally the new ASL selection way using the analysis result is proposed.

• 한국공작기계학회논문집
• /
• 제18권1호
• /
• pp.59-67
• /
• 2009

The purpose of this study is to provide a decision support to select an appropriate layered manufacturing(LM) machine that suits the application of a part. Selection factors include concept model, form/fit/functional model, pattern model far molding, material property, build time and part cost that greatly affect the performance of LM machines. However, the selection of a LM is not an easy decision because they are uncertain and vague. For this reason, the aim of this research is to propose hybrid multiple attribute decision making approaches to effectively evaluate LM machines. In addition, because subjective considerations are relevant to selection decision, a fuzzy logic approach is adopted. The proposed selection procedure consists of several steps. First, we identify LM machines that the users consider After constructing the evaluation criteria, we calculate the weights of the criteria by applying the fuzzy Analytic Hierarchy Process(AHP) method. Finally, we construct the fuzzy Technique of Order Preference by Similarity to Ideal Solution(TOPSIS) method to achieve the ranking order of all machines providing the decision information for the selection of LM machines.