• Journal of the Korea Society of Computer and Information
• /
• v.25 no.3
• /
• pp.27-32
• /
• 2020

In this paper, we propose an algorithm to measure the accumulated status of scrap boxes where metal scraps are accumulated. The accumulated status measuring is defined as a multi-class classification problem, and the method with deep learning classify the accumulated status using only the scrap box image. The learning was conducted by the Transfer Learning method, and the deep learning model was NASNet-A. In order to improve the accuracy of the model, we combined the Random Forest classifier with the trained NASNet-A and improved the model through post-processing. Testing with 4,195 data collected in the field showed 55% accuracy when only NASNet-A was applied, and the proposed method, NASNet with Random Forest, improved the accuracy by 88%.

• Journal of Ship and Ocean Technology
• /
• v.11 no.4
• /
• pp.21-28
• /
• 2007

Recently the importance of the utilization of engineering data is gradually increasing. Engineering data contains the experiences and know-how of experts. Data mining technique is useful to extract knowledge or information from the accumulated existing data. This paper deals with generating optimal polynomials using genetic programming (GP) as the module of Data Mining system. Low order Taylor series are used to approximate the polynomial easily as a nonlinear function to fit the accumulated data. The overfitting problem is unavoidable because in real applications, the size of learning samples is minimal. This problem can be handled with the extended data set and function node stabilization method. The Data Mining system for the ship design based on polynomial genetic programming is presented.

• The Plant Pathology Journal
• /
• v.32 no.6
• /
• pp.537-544
• /
• 2016

We developed a model, termed D-PSA-K, to estimate the accumulated potential damage on kiwifruit canes caused by bacterial canker during the growing and overwintering seasons. The model consisted of three parts including estimation of the amount of necrotic lesion in a non-frozen environment, the rate of necrosis increase in a freezing environment during the overwintering season, and the amount of necrotic lesion on kiwifruit canes caused by bacterial canker during the overwintering and growing seasons. We evaluated the model's accuracy by comparing the observed maximum disease incidence on kiwifruit canes against the damage estimated using weather and disease data collected at Wando during 1994-1997 and at Seogwipo during 2014-2015. For the Hayward cultivar, D-PSA-K estimated the accumulated damage as approximately nine times the observed maximum disease incidence. For the Hort16A cultivar, the accumulated damage estimated by D-PSA-K was high when the observed disease incidence was high. D-PSA-K could assist kiwifruit growers in selecting optimal sites for kiwifruit cultivation and establishing improved production plans by predicting the loss in kiwifruit production due to bacterial canker, using past weather or future climate change data.

• BMB Reports
• /
• v.36 no.6
• /
• pp.558-564
• /
• 2003

In microarray data mining, one of the key problems is how to handle weak signals. Based on a bent piecewise linear accumulated distribution generally found in the microarray data, a new detectable threshold finding method is proposed to filter genes with unreliable information in this paper. More reliable and reproducible data is produced for the subsequent data mining.

• Journal of Wetlands Research
• /
• v.12 no.3
• /
• pp.99-106
• /
• 2010

In this study unit hydrograph and infiltration capacity curves have been determined based on rainfall-runoff data for the upper Ansung stream basin. Infiltration capacity curve also has been computed based on measurements of accumulated infiltration. Accumulated infiltration curve which has close relationship with unit hydrograph has been found in adopting the following two approach methods. In the first method the mean infiltration capacity with infiltration index method and the Kostiakov accumulation infiltration curves have been computed based on hydrological data for the GongDo gauging station of the upper Ansung stream basin. In the second method the accumulation curve has been determined through directly observed infiltration data for four points in the upper basin and has been compared with the infiltration capacity curves by three observed rainfall-runoff event.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2006.04a
• /
• pp.185-191
• /
• 2006

As development of information technology, companies stress the need of knowledge management. Companies construct ERP system including knowledge management. But, it is not easy to formalize knowledge in organization. They experience that constructing information system help knowledge management. Now, we focus on engineering knowledge. Because engineering data contains experts' experience and know-how in its own, engineering knowledge is a treasure house of knowledge. Korean shipyards are leader of world shipbuilding industry. They have accumulated a store of knowledges and data. But, they don't have data minning tool to utilize accumulated data. This paper treats development of data minning tools for the utilization of shipbuilding knowledge based on genetic programming (GP).

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.3
• /
• pp.63-70
• /
• 2018

In this work, we analyze the relationship between the accumulated mileage of hybrid electric vehicle(HEV) and the data provided from vehicle parts. Data were collected while traveling over 70,000 Km in various paths. The data collected in seconds are aggregated for 10 minutes and characterized in terms of centrality, variability, normality, and so on. We examined whether the statistical properties of vehicle parts are different for each cumulative mileage interval of a hybrid car. When the cumulative mileage interval is categorized into =< 30,000, <= 50,000, and >50,000, the statistical properties are classified by the mileage interval as 82.3% accuracy. This indicates that if the data of the vehicle parts is collected by operating the hybrid vehicle for 10 minutes, the cumulative mileage interval of the vehicle can be estimated. This makes it possible to detect the abnormality of the vehicle part relative to the accumulated mileage. It can be used to detect abnormal aging of vehicle parts and to inform maintenance necessity.

• Proceedings of the KSR Conference
• /
• 2007.11a
• /
• pp.57-64
• /
• 2007

RIMS（Rolling Stock Information Maintenance System)　was installed in structure which it can analyze the data base in need of credibility maintenance. So it could accumulate real data without repulsion of working spot. Information system was installed not following to system but following to working spot. The development of RIMS project was started from March 29, 2001 and it has been operating from October 12, 2004 in Chang-dong Car depot for light maintenance in charge subway line4. So substantial data base was accumulated for three years. This study calculated all RAMS data by analyzing data base accumulated in RIMS and used in dada base about credibility maintenance and found investigation of propriety, expectation of the life cycle cost, the improvement plan on credibility of sorts of cars and formation about the cycle of repairing and maintenance. This got MKBSF MKBF and MTBF about devices and sorts of line4 Rolling Stocks for it.

• Proceedings of the KSR Conference
• /
• 2007.11a
• /
• pp.143-150
• /
• 2007

RIMS（Rolling Stock Information Maintenance System)　was installed in structure which it can analyze the data base in need of credibility maintenance. So it could accumulate real data without repulsion of working spot. Information system was installed not following to system but following to working spot. The development of RIMS project was started from March 29, 2001 and it has been operating from October 12, 2004 in Chang-dong Car depot for light maintenance in charge subway line4. So substantial data base was accumulated for three years. This study calculated all RAMS data by analyzing data base accumulated in RIMS and used in dada base about credibility maintenance and found investigation of propriety, expectation of the life cycle cost, the improvement plan on credibility of sorts of cars and formation about the cycle of repairing and maintenance. This got MKBSF MKBF and MTBF about devices and sorts of line4 Rolling Stocks for it.

• Atmosphere
• /
• v.23 no.2
• /
• pp.143-160
• /
• 2013

The effect of 3DVAR (Three Dimension Variational data Assimilation) was examined by comparing observation and the simulations of CNTL (to which data assimilation was not applied) and ALL (to which data assimilation was applied using ground observation data and radar data) for the case of a heavy snowfall event (case A) of 11-12 February 2011 in the Yeongdong region. In case A, heavy snow intensively came in the Yeongdong coastal region rather than Daegwallyeong, in particular, around the Gangneung and Donghae regions with total precipitation in Bukgangneung at approximately 91 mm according to the AWS observation. It can be seen that compared to CNTL, ALL simulated larger precipitation along the Yeongdong coastline extending from Sokcho to Donghae while simulating smaller precipitation for inland areas including Daegwallyeong. On comparison of the total accumulated precipitations from simulations of CNTL and ALL, and the observed total accumulated precipitation, the positive effect of the assimilation of ground observation data and radar data could be identified in Bukgangneung and Donghae, on the other hand, the negative effect of the assimilation could be identified in the Daegwallyeong and Sokcho regions. In order to examine the average accuracy of precipitation prediction by CNTL and ALL for the entire Gangwon region including the major points mentioned earlier, the three hour accumulated precipitation from simulations of CNTL and ALL were divided into 5, 10, 15, 20, 25 and 30 mm/3hr and threat Scores were calculated by forecasting time. ALL showed relatively higher TSs than CNTL for all threshold values although there were some differences. That is, when considered generally based on the Gangwon region, the accuracy of precipitation prediction from ALL was improved somewhat compared to that from CNTL.