• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.21 no.4
• /
• pp.301-308
• /
• 2003

This study describes the methodology that improves the accuracy of the 3D object-space data extracted from IKONOS satellite images by improving the accuracy of a RPC(Rational Polynomial Coefficient) model. For this purpose, we developed the algorithm to adjust a RPC model, and could improve the accuracy of a RPC model with this algorithm and geographically well-distributed GCPs(Ground Control Points). Furthermore, when a RPC model was adjusted with this algorithm, the effects of geographic distribution and the number of GCPs on the accuracy of the adjusted RPC model was tested. The results showed that the accuracy of the adjusted RPC model is affected more by the distribution of GCPs than by the number of GCPs. On the basis of this result, the algorithm using pseudo_GCPs was developed to improve the accuracy of a RPC model in case the distribution of GCPs was poor and the number of GCPs was not enough to adjust the RPC model. So, even if poorly distributed GCPs were used, the geographically adjusted RPC model could be obtained by using pseudo_GCPs. The less the pseudo_GCPs were used -that is, GCPs were more weighted than pseudo_GCPs in the observation matrix-, the more accurate the adjusted RPC model could be obtained, Finally, to test the validity of these algorithms developed in this study, we extracted 3D object-space coordinates using RPC models adjusted with these algorithms and a stereo pair of IKONOS satellite images, and tested the accuracy of these. The results showed that 3D object-space coordinates extracted from the adjusted RPC models was more accurate than those extracted from original RPC models. This result proves the effectiveness of the algorithms developed in this study.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.6
• /
• pp.62-69
• /
• 2002

For improving the motion accuracy of hydrostatic table, corrective machining algorithm is proposed in this paper. The algorithm consists of three main processes. reverse analysis is performed firstly to estimate rail profile from measured linear and angular motion error, in the algorithm. For the next step, corrective machining information is decided as referring to the estimating rail profile. Finally, motion errors on correctively machined rail are analized by using motion error analysis method proposed in the previous paper. These processes can be iterated until the analized motion errors are satisfied with target accuracy. In order to verify the validity of the algorithm theoretically, motion errors by the estimated rail, after corrective machining, are compared with motion errors by true rail assumed as the measured value. Estimated motion errors show good agreement with assumed values, and it is confirmed that the algorithm is effective to acquire the corrective machining information to improve the accuracy of hydrostatic table.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.7
• /
• pp.43-50
• /
• 2012

Database for the information of the shape accuracy is constructed with the finite element stamping analysis of the center pillar member. Analyses are carried out in order to investigate the effect of tool compensation on the product quality previously performed by an expert in the press shop. The compensation procedure is provided with three sequences for improving shape accuracy of the member by reducing the amount of springback. The analysis result shows that shape inaccuracy in the product is caused by sagging and twisting phenomena from displacement of the section part due to excessive amount of springback. From the database with springback analyses, design modification guidelines are proposed for improving the shape accuracy. The guideline is directly applied to a member with the similar shape and the sound product is obtained successfully reducing the amount of springback.

• International Journal of Precision Engineering and Manufacturing
• /
• v.5 no.2
• /
• pp.60-67
• /
• 2004

For improving the motion accuracy of hydrostatic tables, a corrective machining algorithm is proposed in this paper. The algorithm consists of three main processes. The reverse analysis is performed firstly to estimate the rail profile from the measured linear and angular motion error, in the algorithm. For the next step, the corrective machining information is obtained based upon the estimated rail pronto. Finally, the motion errors on the correctively machined rail are analyzed by using the motion error analysis method. These processes are iterated until the analyzed motion errors are satisfactory within the target accuracy. In order to verify the validity of the algorithm theoretically, the motion errors calculated by the estimated rail after the corrective machining process, are compared with those by the true rail which is previously assumed as the initially measured value. The motion errors calculated using the estimated rail show good agreement with the assumed values, and it is shown that the algorithm is effective in acquiring the corrective machining information to improve the accuracy of hydrostatic tables.

• Journal of Internet Computing and Services
• /
• v.17 no.2
• /
• pp.49-57
• /
• 2016

Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving prediction accuracy. Bagging is one of the most popular ensemble learning techniques. Bagging has been known to be successful in increasing the accuracy of prediction of the individual classifiers. Bagging draws bootstrap samples from the training sample, applies the classifier to each bootstrap sample, and then combines the predictions of these classifiers to get the final classification result. Bootstrap samples are simple random samples selected from the original training data, so not all bootstrap samples are equally informative, due to the randomness. In this study, we proposed a new method for improving the performance of the standard bagging ensemble by optimizing bootstrap samples. A genetic algorithm is used to optimize bootstrap samples of the ensemble for improving prediction accuracy of the ensemble model. The proposed model is applied to a bankruptcy prediction problem using a real dataset from Korean companies. The experimental results showed the effectiveness of the proposed model.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.608-608
• /
• 2004

• Proceedings of the Korean Nuclear Society Conference
• /
• 2005.05a
• /
• pp.1138-1139
• /
• 2005

• Journal of KSNVE
• /
• v.5 no.4
• /
• pp.483-492
• /
• 1995

For evaluation of rotational accuracy performance of high speed machine tool spindle system, the characteristics of main spindle and tool motion behavior are presented by means of three point accuracy testing method. The results of experiments and analyses are as follows: (1) The high speed spindle rotational accuracy can be evaluated by the combination of the spindle and tool motion behavior. (2) The spindle motion behavior increases up to more that 4 times the tool motion behavior. (3) For the influence of oil viscosity on spindle and tool taper application, 32 cSt of oil viscosity showed the most satisfactory result for rotational accuracy. (4) In order to improve the rotational accuracy of high speed machine tool spindle system, it is needed to reduce the combination error. This can be achieved by improving the working accuracy and supplying the proper lubrication with contact area at the spindle and tool.

• The KIPS Transactions:PartC
• /
• v.16C no.5
• /
• pp.563-574
• /
• 2009

The merits of random substitutions are various applicability and security guarantee on the view point of privacy breach. However there is no research to improve the accuracy of random substitutions. In this paper we propose an algorithm for improving the accuracy of random substitutions by an advanced theoretical analysis about the standard errors. We examine that random substitutions have an unpractical accuracy level and our improved algorithm meets the theoretical results by some experiments for data sets having uniform and normal distributions. By our proposed algorithm, it is possible to upgrade the accuracy level under the same security level as the original method. The additional cost of computation for our algorithm is still acceptable and practical.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.89-98
• /
• 2024

In this paper, we propose a system for recommending lecture videos at the chapter level, addressing the balance between accuracy and processing speed in chapter-level video recommendations. Specifically, it has been observed that enhancing recommendation accuracy reduces processing speed, while increasing processing speed decreases accuracy. To mitigate this trade-off, a hybrid approach is proposed, utilizing techniques such as TF-IDF, k-means++ clustering, and Graph Neural Networks (GNN). The approach involves pre-constructing clusters based on chapter similarity to reduce computational load during recommendations, thereby improving processing speed, and applying GNN to the graph of clusters as nodes to enhance recommendation accuracy. Experimental results indicate that the use of GNN resulted in an approximate 19.7% increase in recommendation accuracy, as measured by the Mean Reciprocal Rank (MRR) metric, and an approximate 27.7% increase in precision defined by similarities. These findings are expected to contribute to the development of a learning system that recommends more suitable video chapters in response to learners' queries.