• International journal of advanced smart convergence
• /
• v.6 no.3
• /
• pp.17-21
• /
• 2017

In this paper, the service execution accuracy was compared by ontology based rule inference method and machine learning method, and the amount of data at the point when the service execution accuracy of the machine learning method becomes equal to the service execution accuracy of the rule inference was found. The rule inference, which measures service execution accuracy and service execution accuracy using accumulated data and pattern matching on service results. And then machine learning method measures service execution accuracy using cross validation data. After creating a confusion matrix and measuring the accuracy of each service execution, the inference algorithm can be selected from the results.

• Journal of Korean Society for Quality Management
• /
• v.42 no.2
• /
• pp.221-234
• /
• 2014

Purpose: The Purpose of this study is to develop a model for predicting agent churn group in the cosmetics industry. We develope two models, pattern model and matrix model, which are compared regarding the prediction accuracy of churn agents. Finally, we try to conclude if there is statistically significant difference between two models by empirical study. Methods: We develop two models using the part of RFM(Recency, Frequency, Monetary) method which is one of customer segmentation method in traditional CRM study. In order to ensure which model can predict churn agents more precisely between two models, we used CRM data of cosmetics company A in China. Results: Pattern model and matrix model have been developed. we find out that there is statistically significant differences between two models regarding the prediction accuracy. Conclusion: Pattern model and matrix model predict churn agents. Although pattern model employed the trend of monetary mount for six months, matrix model that used the amount of sales per month and the duration of the employment is better than pattern model in prediction accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.6
• /
• pp.1282-1287
• /
• 2005

The accuracy of chip alignment in inferior product inspection of COG(Chip On Glass) to be measured a few micro unit is very important role since the accuracy of chip inspection depends on chip alignment. In this paper, we propose the area segmentation pattern matching method to enhance the accuracy of chip alignment. The area segmentation pattern matching method compares, and matches correlation coefficients between the characteristic features within the detailed area and the areas. The three areas of pattern circumference are learned to minimize the matching error by bad pattern. The proposed method has advantage such as reduction of matching time, and enhanced accuracy since the characteristic features are searched within the segmented area.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.2
• /
• pp.269-278
• /
• 2006

This paper presents the new hybrid data mining technique using error pattern, modeling of improving classification accuracy. The proposed method improves classification accuracy by combining two different supervised learning methods. The main algorithm generates error pattern modeling between the two supervised learning methods(ex: Neural Networks, Decision Tree, Logistic Regression and so on.) The Proposed modeling method has been applied to the simulation of 10,000 data sets generated by Normal and exponential random distribution. The simulation results show that the performance of proposed method is superior to the existing methods like Logistic regression and Discriminant analysis.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.481-486
• /
• 1994

An image processing and pattern recognition program was developed in order to recognize the nummerinc displays on gas flow meters. the testing process of the accuracy of gas flow meters are to be automated, using the developed software. There are already many known pattern recognition algorithms for recognition of the letters. To upgrade the recognization accuracy, four different algorithms are applied in sequentially in the software. An calculation method to assign the weighting factors for the result of each algorithm was developed. It showed 98% accuracy by the pattern recognition of displaying numbers of gas mwters of 33 differnt types. This pattern recognition system is to be integrated in a industry.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.17 no.3
• /
• pp.1-6
• /
• 2018

Micro prism pattern is applying in order to get increase of luminance, control the light, and so forth especially in optics and display industry. Most patterns are fabricated by lithography, planning, and EDM, but they have limitations on the productivity or the unit cost of produce. However, ultra precision mold is one of the processes able to replace it, and assure high productivity required by industries. In this investigation, micro prismatic end-milling is suggested in order to fabricate the pattern effectively. Micro prism pattern having $100{\mu}m$ of pitch and height was machined on STD-11. After machining, the flank and boundary wear on micro end mill were measured and analyzed, as well as burr formation and dimensional accuracy of fabricated pattern were evaluated. Thus the optimal cutting conditions were derived.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.6
• /
• pp.131-137
• /
• 2007

In metal casting process, it is very difficult to predict the form accuracy of cast part and reduce repeatability error. In this study, the variations of form accuracy were measured in the process of metal cast prototyping, where RP part is manufactured from CAD model in the first, and then, wax part is cast in the vacuum environment using the RP part as master model, and finally metal prototype is cast using ceramic mold and the wax part as pattern. To investigate the variations of form accuracy, the averages and standard deviations of error distribution of the parts measured by 3D scanner were compared. It was observed that the biggest shrinkage is generated during the extraction of wax part in the second step and the biggest deterioration of form accuracy is generated during the metal part casting in the last step.

• Progress in Medical Physics
• /
• v.7 no.1
• /
• pp.53-64
• /
• 1996

Purpose: The purposes of this paper are to develop a theoretical basis that the beam directions should be considered when the mechanical accuracy of teletherapy machine is evaluated by the star pattern test, to develop methods using asymmetric field in length to simulate beam direction for the case that beam direction does not appear on film. Method: In evaluating mechanical rotational accuracy of the gantry of teletherapy unit by the star pattern test, the direction of radiation beams was considered. A star pattern using some narrow beams was made. Density profiles at 10cm far from estimated gantry axis on the star pattern were measured using an optical densitometer. On each profile, one coordimate of a beam axis was determined. A pair of coordinates on a beam axis form an equation of the axis. Assume that a unit vector equation omitted is with same direction as radiation beam and a vector equation omitted is a vector directing to the beam axis from the estimated gantry axis. Then, a vector product equation omitted ${\times}$ equation omitted is an area vector of which the absolute value is equal to the distance from the estimated gantry axis to the beam axis. The coordinate of gantry axis was obtained by using least-square method for the area vectors relative to the average of whole area vectors. For the axis, the maximum of absolute value of area vectors would be an accuracy of the gantry rotation axis. For the evaluation of mechanical accuracies of collimator and couch axes for which beam direction could not be depicted on a star pattern test film, narrow beams asymmetric in field length was used to simulate beam direction. Result: For a star test pattern to evaluate the mechanical accuracy of rotational axes of a telectherapy machine, the result considering beam direction was different from that ignoring beam direction. For the evaluation of mechanical accuracies of collimator and couch axes by means of a star pattern test, narrow asymmetric beams could simulate beam direction. Conclusion: When a star pattern test is used to evaluate the mechanical accuracy of a teletherapy unit, beam direction must be considered or simulated, and quantitatively evaluated.

• Journal of the Korean Geographical Society
• /
• v.42 no.1 s.118
• /
• pp.1-14
• /
• 2007

This study aimed to evaluate weather forecast accuracies of minimum temperature, maximum temperature, precipitation and sky cover by the localized land forecast areas over South Korea Average forecast accuracy score of precipitation was the lowest while that of sky cover was the highest during the study period Overall forecast accuracy scores for Gangwon-do was the lowest while those for Gyeongsangnam-do and Gyeongsangbuk-do were higher than other areas. The frequencies of perfect forecast(eight points) by seasons, were the highest during winter and the lowest during summer. pressure pattern analyses for days when forecast accuracy scores were poor, showed that precipitation forecast accuracy scores were lower due to the movement of the stationary fronts during summers. When continental polar air masses expanded, forecast accuracy of temperature became greatly lower during autumns and winters As the migratory anticyclone pattern rapidly moved, forecast accuracy became lower during springs and autumns. Forecast accuracies were compared by wind directions at 850hPa for the Young-dong region where forecast accuracy was the lowest. Forecast accuracy scores on minimum and maximum temperatures were low when winds were westerlies and forecast accuracy scores of precipitation were low when winds were easterlies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.10
• /
• pp.2679-2691
• /
• 2012

In this paper, a high accuracy stereo reconstruction method for surgery instruments positioning is proposed. Usually, the problem of surgical instruments reconstruction is considered as a basic task in computer vision to estimate the 3-D position of each marker on a surgery instrument from three pairs of image points. However, the existing methods considered the 3-D reconstruction of the points separately thus ignore the structure information. Meanwhile, the errors from light variation, imaging noise and quantization still affect the reconstruction accuracy. This paper proposes a method which takes the structure information of surgical instruments as constraints, and reconstructs the whole markers on one surgical instrument together. Firstly, we calibrate the instruments before navigation to get the structure parameters. The structure parameters consist of markers' number, distances between each markers and a linearity sign of each instrument. Then, the structure constraints are added to stereo reconstruction. Finally, weighted filter is used to reduce the jitter. Experiments conducted on surgery navigation system showed that our method not only improve accuracy effectively but also reduce the jitter of surgical instrument greatly.