• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1790-1796
• /
• 2021

A large amount of image data sets are required for image deep learning, and there are many differences in the method of obtaining images and constructing image data sets depending on the type of object. In this paper, we presented a method of constructing an image data set for deep learning and analyzed the performance that varies depending on the object to be tracked. We took a video by rotating the object, and then created a data set by segmenting the video using the proposed data set construction method. As a result of performance analysis, detection rate was more than 95%, and detection rate of objects with little change in shape was higher performance. It is considered that it is effective to use the data set construction method presented in this paper for a situation in which it is difficult to obtain image data and to track an object with little change in shape within a video.

• Journal of Wetlands Research
• /
• v.18 no.2
• /
• pp.132-147
• /
• 2016

In this study the Microwave Imaging Radiometer using Aperture Synthesis (MIRAS) sensor onboard the Soil Moisture Ocean Salinity (SMOS) and Advanced Microwave Scanning Radiometer 2 (AMSR2) sensor onboard the Global Change Observation Mission-Water (GCOM-W1) based soil moisture retrievals were revised to obtain better accuracy of soil moisture and higher data acquisition rate over East Asia. These satellite-based soil moisture products are revised against a reference land model data set, called Global Land Data Assimilation System (GLDAS), using Cumulative Distribution Function (CDF) matching and regression approach. Since MIRAS sensor is perturbed by radio frequency interferences (RFI), the worst part of soil moisture retrieval, East Asia, constantly have been undergoing loss of data acquisition rate. To overcome this limitation, the threshold of RFI, DQX, and composite days were suggested to increase data acquisition rate while maintaining appropriate data quality through comparison of land surface model data set. The revised MIRAS and AMSR2 products were compared with in-situ soil moisture and land model data set. The results showed that the revising process increased correlation coefficient values of SMOS and AMSR2 averagely 27% 11% and decreased the root mean square deviation (RMSD) decreased 61% and 57% as compared to in-situ data set. In addition, when the revised products' correlation coefficient values are calculated with model data set, about 80% and 90% of pixels' correlation coefficients of SMOS and AMSR2 increased and all pixels' RMSD decreased. Through our CDF-based revising processes, we propose the way of mutual supplementation of MIRAS and AMSR2 soil moisture retrievals.

• Journal of the Korean Home Economics Association
• /
• v.46 no.9
• /
• pp.137-146
• /
• 2008

This study was conducted in order to spread out lower body 3D scan data of men in their twenties. The aim was to achieve slacks pattern with ease allowance through comparison with existing flat patterns. For conversion of 3D scan data into 20 pattern, reference lines were established by using Rapid Foam in 3D shape analysis software. 2C-AN program and Yuka CAD were used to convert 20 pattern earned with straight posture of 3D scan data into slacks pattern by using Triangle Simplification & Runge-Kutta Method. In order to achieve this we needed to set a line 9cm below the hip line, to array vertex of each block to crease line while maintaining the horizontal line. And then we needed to set ease allowance in back crotch and to set waist circumference or hip circumference ease allowance in side seam of slacks. Results showed that long front crotch length can be achieved if 3D scan data is compared with 20 existing flat pattern. Slacks pattern that raise front crotch by about 1.5cm compared to back crotch and also possess ease allowance in back crotch area are great in appearance evaluation.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.2
• /
• pp.113-119
• /
• 2008

The World Wide Web is a dynamic collection of pages that includes a huge number of hyperlinks and huge volumes of usage informations. The resulting growth in online information combined with the almost unstructured web data necessitates the development of powerful web data mining tools. Recently, a number of approaches have been developed for dealing with specific aspects of web usage mining for the purpose of automatically discovering user profiles. We analyze sequence data, such as web-logs, protein sequences, and retail transactions. In our approach, we propose the clustering algorithm for sequence data using rough set theory. We present a simple example and experimental results using a splice dataset and synthetic datasets.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.57-58
• /
• 2022

Concrete mix design is used as essential data for the quality of concrete, analysis of structures, and stable use of sustainable structures. However, since most of the formulation design is established based on the experience of experts, there is a lack of data to base it on. are suffering Accordingly, in this study, the purpose of this study is to build a predictive model to use the concrete mixing factor as basic data for calculation using the DNN technique. As for the data set for DNN model learning, OPC and ternary concrete data were collected according to the presence or absence of admixture, respectively, and the model was separated for OPC and ternary concrete, and training was carried out. In addition, by varying the number of hidden layers of the DNN model, the prediction performance was evaluated according to the model structure. The higher the number of hidden layers in the model, the higher the predictive performance for the prediction of the mixing elements except for the compressive strength factor set as the output value, and the ternary concrete model showed higher performance than the OPC. This is expected because the data set used when training the model also affected the training.

• Journal of Navigation and Port Research
• /
• v.48 no.2
• /
• pp.109-115
• /
• 2024

To develop a shipping company insolvency prediction model, we sampled shipping companies that closed between 2005 and 2023. In addition, a closed company and a normal company with similar asset size were selected as a paired sample. For this study, data of a total of 82 companies, including 42 closed companies and 42 general companies, were obtained. These data were randomly divided into a training set (2/3 of data) and a testing set (1/3 of data). Training data were used to develop the model while test data were used to measure the accuracy of the model. In this study, a prediction model for Korean shipping insolvency was developed using financial ratio variables frequently used in previous studies. First, using the LASSO technique, main variables out of 24 independent variables were reduced to 9. Next, we set insolvent companies to 1 and normal companies to 0 and fitted logistic regression, LDA and QDA model. As a result, the accuracy of the prediction model was 82.14% for the QDA model, 78.57% for the logistic regression model, and 75.00% for the LDA model. In addition, variables 'Current ratio', 'Interest expenses to sales', 'Total assets turnover', and 'Operating income to sales' were analyzed as major variables affecting corporate insolvency.

• Journal of the Korea Society for Simulation
• /
• v.5 no.1
• /
• pp.1-12
• /
• 1996

We propose a new approach to classifying a time series data into one of the autoregressive moving-average (ARMA) models. It is bases on two pattern recognition concepts for solving time series identification. The one is an extended sample autocorrelation function (ESACF). The other is a neural network-driven decision tree classifier(NNDTC) in which two pattern recognition techniques are tightly coupled : neural network and decision tree classfier. NNDTc consists of a set of nodes at which neural network-driven decision making is made whether the connecting subtrees should be pruned or not. Therefore, time series identification problem can be stated as solving a set of local decisions at nodes. The decision values of the nodes are provided by neural network functions attached to the corresponding nodes. Experimental results with a set of test data and real time series data show that the proposed approach can efficiently identify the time seires patterns with high precision compared to the previous approaches.

• The Korean Journal of Applied Statistics
• /
• v.21 no.3
• /
• pp.523-535
• /
• 2008

Initial work of microarray data analysis focused on identification of differentially expressed genes, and recently, the focus has moved to discovering significant sets of functionally related genes. We describe some problems of GSEA and PAGE, and propose a modified method to identify significant gene sets. The results based on a simulated experiment and real data analysis using a set of publicly available data show the superiority of the newly proposed method, GSA-AT, in detecting significant pathways with the accurate prediction.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.21 no.1
• /
• pp.57-61
• /
• 1984

This paper deals with the selection of minimal test instruction set for microprocessor data processing test. This test method is based on a function description of the instructions which are obtained from the data given by the user's manual. Selecting procedure is done in 3 steps: 1) a test execution graphs are represented on the instructions which are grouped functionally, 2) the essential graphs, the eliminable graphs, the eliminable graphs, and the eligible graphs are built, 3) optimal test instruction set from the essential graphs and the eligible graphs is defined. In the case of INTEL 8048, 50 test instructions can be selected optimally from 8048 instruction repertories (96 instructions)

• Korean Journal of Computational Design and Engineering
• /
• v.3 no.4
• /
• pp.243-250
• /
• 1998

In parametric surface interpolation, the choice of the parameter values to the set of scattered points makes a great deal of difference in the resulting surface. A new method is developed and tested for the parametrization in NURBS surface global interpolation. This method uses the parameter value at the maximal value of relevant rational basis function, to assign the parameter values to the arbitrary set of design data. This method gives us several important advantages in geometric modeling, the freedom of the selection of knot values, the feasible transformation of the data set to the matrix, the possibility of affinite transformation between the design data and generated surface, etc.