• 산업경영시스템학회지
• /
• 제43권2호
• /
• pp.33-38
• /
• 2020

Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.

• KEPCO Journal on Electric Power and Energy
• /
• 제2권1호
• /
• pp.61-69
• /
• 2016

Understanding load patterns and customer classification is a basic step in analyzing the behavior of electricity consumers. To achieve that, there have been many researches about clustering customers' daily load data. Nowadays, the deployment of advanced metering infrastructure (AMI) and big-data technologies make it easier to study customers' load data. In this paper, we study load clustering from the view point of yearly and daily load pattern. We compare four clustering methods; K-means clustering, hierarchical clustering (average & Ward's method) and DBSCAN (Density-Based Spatial Clustering of Applications with Noise). We also discuss the relationship between clustering results and Korean Standard Industrial Classification that is one of possible labels for customers' load data. We find that hierarchical clustering with Ward's method is suitable for clustering load data and KSIC can be well characterized by daily load pattern, but not quite well by yearly load pattern.

• 한국안전학회지
• /
• 제22권6호
• /
• pp.81-86
• /
• 2007

The purpose of this study is to provide foot classification on 30 generation young men and women by factor analysis and cluster analysis. The sample for this work was chosen from data which were collected and measured by Size Korea during two years($2003{\sim}2004$). In order to analyze and compare features of the foot of men and women, analysis was performed about 871 subjects(male: 422, female: 449) on 24 body parts including height, width, thickness, circumference, length and angle. According to the result of factor analysis about measured data, there were seven factors and six factors for men and women respectively. After cluster analysis, data for men and women were commonly divided by three types for utilization of research results. Type 1 and type 3 had wide distribution about men. Type 2 had wide distribution about women. The results of this study can be applied in manufacturing and design of comfortable shoes and socks.

• 한국산학기술학회논문지
• /
• 제10권7호
• /
• pp.1668-1672
• /
• 2009

본 연구에서는 피조콘관입시험 결과를 활용한 토질분류법 중 가장 일반적으로 사용되고 있는 Robertson 방법과 최근 발표된 최신 분류법인 Schneider 방법을 비교분석하였다. 이를 위하여 경기해안 지역의 연약지반을 대상으로 두 방법 및 통일분류법의 토질분류 결과를 고찰하였다. 연구결과, 두 방법에 의한 결과 차이는 크지 않았으나 전반적으로 Schneider 방법이 점토지역에서, Robertson 방법이 사질토에서 보다 정밀한 결과를 보였다. 보다 신뢰도 높은 토질분류를 위하여 콘 시험의 데이터베이스, 정규화된 콘저항치, 간극수압 및 배수조건에 대한 심층 연구가 필요하다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2015년도 추계학술발표대회
• /
• pp.1388-1389
• /
• 2015

Electropulsegraphy is a medical device that was invented by an orient medical physician and a few engineers to help the physicians to diagnose patients in more systematic way by analyzing waveforms generated from the device. Data generated form the device has been collected for over several decades, and undergoes functional upgrades today. The device generates 33 waveforms that reflect the states of patients. As one of those upgrading efforts, we strive to develop an intelligent algorithm that makes the diagnostic process automatically, which was previously done manually for a long period of time. The logistic regression algorithm is used for our classification problems, which is one of those well-known algorithms for various classification problems such as character recognition systems. Out of the 33 waveforms, we only use 5 waveform data (Type1 toType5) as training data sets to estimate the parameters of the logistic regression. And the parameters are used to classify waveform inputs chosen at random.

• Journal of Information Processing Systems
• /
• 제15권5호
• /
• pp.1179-1191
• /
• 2019

We design an ingenious view-pooling method named learning-based multiple pooling fusion (LMPF), and apply it to multi-view convolutional neural network (MVCNN) for 3D model classification or retrieval. By this means, multi-view feature maps projected from a 3D model can be compiled as a simple and effective feature descriptor. The LMPF method fuses the max pooling method and the mean pooling method by learning a set of optimal weights. Compared with the hand-crafted approaches such as max pooling and mean pooling, the LMPF method can decrease the information loss effectively because of its "learning" ability. Experiments on ModelNet40 dataset and McGill dataset are presented and the results verify that LMPF can outperform those previous methods to a great extent.

• 한국산업융합학회 논문집
• /
• 제26권6_2호
• /
• pp.1055-1062
• /
• 2023

Globally, the need for remanufacturing or reusing ships and various mechanical parts continues to increase due to environmental problems including global warming. Research on remanufacturing is being carried out in many areas. However, research on inspection and classification to identify the performance or degree of wear of mechanical parts is insufficient. In particular, studies on the inspection-ability and classification-ability of mechanical parts equipped with various materials and complex forms are highly required. Remanufacturing must be considered from the stage of design to extend the life cycle of mechanical parts. Particularly, it is very important to perform research for evaluating the degree of ease to inspect and classify various sorts of wear or deterioration of parts caused by long-term use easily. In this study, the degree of ease in inspecting or classifying mechanical parts for remanufacturing is defined as inspection-ability and classification-ability. In fact, to remanufacture old parts, inspection-ability and classification-ability should be reflected from the stage of design. The purpose of this study is to evaluate the inspection-ability and classification-ability of ships and various mechanical parts. This researcher has presented the quantitative evaluation procedure of inspection-ability and classification-ability, derived the factors and ranges that influence each of the details of easiness, assigned scores according to the ranges of the factors, and calculated weights. Lastly, this study presents the procedure of scoring to evaluate the overall weights of inspection-ability and classification-ability and also inspection-ability and classification-ability quantitatively.

• 산업경영시스템학회지
• /
• 제36권2호
• /
• pp.25-31
• /
• 2013

This paper analyzed the management quality activities and performance based on industrial types. We divided the business into four industrial types, manufacturing industry, service industry, medical institution and public enterprise. We analyzed the differences of the elements of management quality in industrial types. The results show that leadership, measurement, analysis and knowledge management and workforce focus categories are not significant and strategic planning, customer and market focus, process management and performance categories are significant. This paper proposes the directions of management quality activities and performance according to industrial types based on these results.

• 한국콘텐츠학회논문지
• /
• 제20권6호
• /
• pp.256-266
• /
• 2020

산업의 공간적 입지에 대한 분포 패턴 분석은 관련된 공간정책 및 계획의 수립에 있어 매우 중요한 역할을 한다. 이러한 분석에 있어 먼저 고려되어야 하는 것은 어떠한 분석지표와 공간단위를 활용하는가에 있는데, 이는 지표와 공간단위에 따라 그 해석이 달라질 수 있기 때문이다. 이에 본 연구는 먼저 공간적 자기상관을 고려한 다양한 산업집적 지표들을 고찰하고 관련 지표에 따른 산업집적의 지역유형을 구분하며, 다음으로 개별입지, 그리드, 행정구역 등의 다양한 공간단위별 산업집적을 분석하는 방법론을 제시하여 뿌리산업에 대해 실증분석 하는 것을 목표로 한다. 실증분석 결과를 보면 공간단위에 있어서 그리드 단위가 행정구역 단위보다 세밀한 미시적 분석이 가능함을 알 수 있었고, 공간단위의 설정에 따라 발생할 수 있는 해석상의 차이와 같은 한계를 극복할 수 있는 것으로 기대된다. 지역유형 구분에 있어서는 울산광역시, 부산광역시, 창원시를 축으로 하는 동남권과 인천광역시, 화성시, 안산시를 축으로 하는 수도권 서부축이 뿌리산업의 산업집적 클러스터 지역유형으로 분석되었다.

• 한국IT서비스학회지
• /
• 제11권4호
• /
• pp.25-37
• /
• 2012

In recent year, the u-City construction projects which integrate IT technology into urban infrastructures are being pushed forward by many local governments. These projects contain various purposes in an aspect of regional economy : to reinforce a competitiveness of region by increasing efficiency of urban managements and to revitalize regional economy by stimulating the regional high-tech industries that related to u-City construction. In this context, regional economic impact assessment of u-City construction projects is particularly important because, it give us information about effectiveness of u-City construction policy as a stimulus of regional high-tech industries and the policy feasibility of u-City construction projects that can be a base of public projects. However, it is challenging to assess the impact of u-City projects on regional economy properly due to a lack of understanding about industrial classification, and specific industrial inputs related to u-City construction. In this study, we suggest u-City industrial classifications, and specific-industrial inputs induced by u-City construction projects based on associated legislations, business report for a u-City construction, and results from previous studies. Using these classification and industrial input, we also investigate the regional economic impacts of a u-City construction project in Wha-sung and Dong-tan cities employing Input-output analysis. The empirical results suggests that u-City industries have relatively high in production inducement, and value added inducement compared to input of other industrial sectors. These results indicate that regional economic impact of a Wha-sung and Dong-tan u-City construction project are relatively high, but economic impacts of u-City construction projects vary according to the regional industrial structure, and the specific expense accounts of u-City construction projects.