• 대한안전경영과학회지
• /
• 제10권4호
• /
• pp.127-134
• /
• 2008

The objective of this study is to evaluate the mechanical behaviors and structural integrity of the weldment of high strength steel by using an acoustic emission (AE) techniques. Monotonic simple tension and AE tests were conducted against the 3 kinds of welded specimen. In order to analysis the effectiveness of weldability, joinability and structural integrity, we used K-means clustering method as a unsupervised learning pattern recognition algorithm for obtained multi-variate AE main data sets, such as AE counts, energy, amplitude, hits, risetime, duration, counts to peak and rms signals. Through the experimental results, the effectiveness of the proposed method is discussed.

• 한국컴퓨터정보학회논문지
• /
• 제22권5호
• /
• pp.65-72
• /
• 2017

Premature Ventricular Contraction(PVC) arrhythmia is most common abnormal-heart rhythm that may increase mortal risk of a cardiac patient. Thus, it is very important issue to identify the specular portraits of PVC pattern especially from the patient. In this paper, we propose a new method to extract the characteristics of PVC pattern by applying K-means machine learning algorithm on Heart Rate Variability depicted in Poinecare plot. For the quantitative analysis to distinguish the trend of cluster patterns between normal sinus rhythm and PVC beat, the Euclidean distance measure was sought between the clusters. Experimental simulations on MIT-BIH arrhythmia database draw the fact that the distance measure on the cluster is valid for differentiating the pattern-traits of PVC beats. Therefore, we proposed a method that can offer the simple remedy to identify the attributes of PVC beats in terms of K-means clusters especially in the long-period Electrocardiogram(ECG).

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1993년도 하계학술대회 논문집 A
• /
• pp.439-441
• /
• 1993

A tire tread pattern recognition scheme of which the pattern recognition algorithm is designed based on the fuzzy hierarchical clustering method is proposed and compared with the scheme based on the conventional FCM. The features are extracted from the binary images of the tire tread patterns. In the proposed scheme, the protoypes are obtained more easily and schematically than obtained prototypes using FCM. The experimental results of classification for the practical situations are given and shows the usefulness of the proposed scheme.

• 대기
• /
• 제29권4호
• /
• pp.451-461
• /
• 2019

Medium-range forecast is highly dependent on ensemble forecast data. However, operational weather forecasters have not enough time to digest all of detailed features revealed in ensemble forecast data. To utilize the ensemble data effectively in medium-range forecasting, representative weather patterns in East Asia in this study are defined. The k-means clustering analysis is applied for the objectivity of weather patterns. Input data used daily Mean Sea Level Pressure (MSLP) anomaly of the ECMWF ReAnalysis-Interim (ERA-Interim) during 1981~2010 (30 years) provided by the European Centre for Medium-Range Weather Forecasts (ECMWF). Using the Explained Variance (EV), the optimal study area is defined by 20~60°N, 100~150°E. The number of clusters defined by Explained Cluster Variance (ECV) is thirty (k = 30). 30 representative weather patterns with their frequencies are summarized. Weather pattern #1 occurred all seasons, but it was about 56% in summer (June~September). The relatively rare occurrence of weather pattern (#30) occurred mainly in winter. Additionally, we investigate the relationship between weather patterns and extreme weather events such as heat wave, cold wave, and heavy rainfall as well as snowfall. The weather patterns associated with heavy rainfall exceeding 110 mm day^-1 were #1, #4, and #9 with days (%) of more than 10%. Heavy snowfall events exceeding 24 cm day^-1 mainly occurred in weather pattern #28 (4%) and #29 (6%). High and low temperature events (> 34℃ and < -14℃) were associated with weather pattern #1~4 (14~18%) and #28~29 (27~29%), respectively. These results suggest that the classification of various weather patterns will be used as a reference for grouping all ensemble forecast data, which will be useful for the scenario-based medium-range ensemble forecast in the future.

• 전기학회논문지
• /
• 제67권1호
• /
• pp.114-123
• /
• 2018

This paper concerns a design and learning method of softmax function neural networks based on K-means clustering. The partial discharge data Information is preliminarily processed through simulation using an Epoxy Mica Coupling sensor and an internal Phase Resolved Partial Discharge Analysis algorithm. The obtained information is processed according to the characteristics of the pattern using a Motor Insulation Monitoring System program. At this time, the processed data are total 4 types that void discharge, corona discharge, surface discharge and slot discharge. The partial discharge data with high dimensional input variables are secondarily processed by principal component analysis method and reduced with keeping the characteristics of pattern as low dimensional input variables. And therefore, the pattern classifier processing speed exhibits improved effects. In addition, in the process of extracting the partial discharge data through the MIMS program, the magnitude of amplitude is divided into the maximum value and the average value, and two pattern characteristics are set and compared and analyzed. In the first half of the proposed partial discharge pattern classifier, the input and hidden layers are classified by using the K-means clustering method and the output of the hidden layer is obtained. In the latter part, the cross entropy error function is used for parameter learning between the hidden layer and the output layer. The final output layer is output as a normalized probability value between 0 and 1 using the softmax function. The advantage of using the softmax function is that it allows access and application of multiple class problems and stochastic interpretation. First of all, there is an advantage that one output value affects the remaining output value and its accompanying learning is accelerated. Also, to solve the overfitting problem, L2-normalization is applied. To prove the superiority of the proposed pattern classifier, we compare and analyze the classification rate with conventional radial basis function neural networks.

• 전기학회논문지
• /
• 제65권9호
• /
• pp.1486-1492
• /
• 2016

This study presents the electrical load forecasting and error correction method using a real building load pattern, and the way to manage the energy storage system with forecasting results for economical load operation. To make a unique pattern of target load, we performed the Hierarchical clustering that is one of the data mining techniques, defined load pattern(group) and forecasted the demand load according to the clustering result of electrical load through the previous study. In this paper, we propose the new reference demand for improving a predictive accuracy of load demand forecasting. In addition we study an error correction method for response of load events in demand load forecasting, and verify the effects of proposed correction method through EMS scheduling simulation with load forecasting correction.

• 한국의류학회지
• /
• 제44권6호
• /
• pp.1053-1069
• /
• 2020

This study examined the sales pattern relationship with respect to product attributes to propose sales forecasting for fashion products. We analyzed 537 SKU sales data of T-shirts in the domestic sports brand using SAS program. The sales pattern of fashion products fluctuated and were influenced by exogenous factors; therefore, we removed the influence of exogenous factors found to be price discounts and holiday effects as a result of regression analysis. In addition, it was difficult to predict sales using the sales patterns of the same product since fashion products were released as new products every year. Therefore, the forecasting model was proposed using sales patterns of related product attributes when attributes were considered descriptive variables. We classified sales patterns using K-means clustering in order to explain the relationship between sales patterns and product attributes along with creating a decision tree classifier using attributes as input and sales patterns as output. As a result, the sales patterns of T-shirts were clustered into six types that featured the characteristic shape of peak and slope. It was also associated with the combination of product attributes and their values in regards to the proposed sales pattern prediction model.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2020년도 추계학술대회
• /
• pp.54-55
• /
• 2020

4차 산업혁명으로 인공지능, 사물인터넷, 빅데이터 등의 기술이 조선 해운 산업에 매우 밀접하게 연관 되고 있고 이는 자율운항선박의 탄생을 가져왔다. 현재 선박의 기술적 특성상 속력을 갑자기 낮출 수 없으므로 항만에 접안하기 위해 예인선의 도움, 도선사의 승선, 육상관제센터의 선박 컨트롤 등 복잡한 커뮤니케이션을 필요로 한다. 본 연구에서는 자율운항선박이 도입될 경우 선박이 입항하기 위한 컨트롤 기준을 어떻게 설정할지 해결하고자 클러스터링 분석을 사용하였다. 입항 선박의 축적된 AIS 데이터를 기반으로 입항 패턴을 정량적으로 단계화하고자 K-Means 클러스터링을 사용했고 SOG(Speed over Ground), COG(Course over Ground), ROT(Rate of Turn)를 사용하여 입항 단계를 6개로 구분하였다.

• 정보처리학회논문지D
• /
• 제13D권7호
• /
• pp.1027-1038
• /
• 2006

대용량 데이터베이스에서의 추천시스템은 많은 문제점들을 지니고 있으므로, 대규모 인터넷 쇼핑몰에 적합한 추천 시스템 구조와 데이터 마이닝 기법의 필요성이 요구되고 있다. 따라서 본 논문에서는 k-mean 클러스터링과 순차 패턴 기법을 이용한 VLDB(very large database) 기반의 상품 추천 시스템을 설계 및 구현한다. 본 논문에서는 사용자의 정보를 일괄처리하고 다양한 카테고리를 계층적으로 정의하며, 탐색엔진에 순차 패턴 마이닝 기법을 이용한다. 예측 모델을 만들기 위하여 사용자의 로그 데이터 중에서 카테고리에 대한 사용자의 선호도를 추출하여 이용한다. 본 논문에서는 실험과 성능 평가를 위하여 국내 인터넷 쇼핑몰에서 30일 동안 수집한 실제 데이터를 이용한다. 또한 성능평가를 위하여 추천 예측 정확율(PRP: Predictive Recommend Precision), 추천 예측 재현율(PRR: Predictive Recommend Recall), 정확도 인수(PF1 : Predictive Factor One-measure)를 제안하여 사용한다. 성능평가 결과 가장 빠른 추천시간 및 학습시간은 O(N)이었고, 다양한 실험에서의 측도들의 값이 상당히 우수하였다.

• 한국정보처리학회논문지
• /
• 제2권5호
• /
• pp.619-625
• /
• 1995

본 연구에서는 역전파(backpropagationlk)학습 알고리즘에 대체될 수 있는 전방향 학습 알고리즘에 준하는 혼합 인식모형을 구성한다. 본 알고리즘은 Nikhil R. Pal (1993)이 제안한 GLVQ(Generalized Learning Vector Quantization)를 이용하여 패턴을 클러스터링 한 다음 비유사성(dissimilarity)을 가진 패턴끼리 재구성(regrouping) 하여 단순 퍼셉트론(simple perceptron)을 이용하여 group별 학습을 한다. 일반적으로 역전파학습인 학습시간이 많이 소요된다는 단점이 있다［1］. 본 알고리즘의 특징으로 는 feed-forward학습이기 때문에 학습시간이 단축될 뿐만 아니라 전체 패턴을 그룹별 로 나누어 학습을 하기 때문에 인식률도 향상 시킬 수 있다. 본 알고리즘에 적용한 데 이타는 250개의 ASCII코드를 16$\times$8격자에 정규화시킨 비트 패턴(bit pattern)을 이용 하였다. 실험결과 250개의 패턴을 10개의 클러스터로 나누어 학습을 시켰을 때 각 클 러스터별 평균반복횟수 94.7회만에 250개의 ASCII코드를 100% 인식할 수 있었다.