• Economic and Environmental Geology
• /
• v.30 no.5
• /
• pp.469-476
• /
• 1997

In the conventional velocity analysis, the peaks of a semblance panel are picked and the stacking velocities of the peaks are assumed as RMS velocities from which interval velocities are determined. This velocity analysis technique is correct only for horizontal homogeneous layes and incurs error in a layer whose velocity varies laterally. Tediousness of peak picking and error in velocity analysis can be reduced by automatic velocity analysis techniques. An automatic velocity analysis algorithm has been presented in order to improve these problems by considering the stacking velocity from the view point of interval velocity model and by relating the stacking velocity and the interval velocity with the traveltimes. In this paper, we apply the automatic velocity analysis method to simple models having lateral velocity anomaly to verify the effectivenesses and limits of this method. From the results of numerical experiments, we can determine the interval velocites without pickings of the stacking velocities in the one-dimensional velocity analysis and the general patterns of the laterally varying interval velocities appear in the two-dimensional case. However, the interval velocity and the depth of velocity anomaly determined by two-dimensional automatic velocity analysis are somewaht discrepant in those of the theoretical model.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.103.3-103
• /
• 2002

1. Introduction 2. Dynamic Model of Stacking Crane 3. The Path Plan of Stacking Crane 4. Design of Neural Network Predictive PID Controller 5. Result of Computer Simulation and Investigation 5. Conclusion

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1386-1394
• /
• 2022

As consumption of high-quality fruits increases and sales and packaging units become smaller, the demand for automatic fruit grading systems is increasing. Compared to other crops, the quality of fruit is determined by visual characteristics such as shape, color, and scratches, rather than just physical size and weight. Accordingly, this study presents a CNN model that can effectively extract and classify the visual features of fruits and a perceptron that classifies fruits using physical features, and proposes a stacking ensemble model that can effectively combine the classification results of these two neural networks. The experiments with AI Hub public data show that the stacking ensemble model is effective for grading fruits. However, the ensemble model does not always improve the performance of classifying all the fruit grading. So, it is necessary to adapt the model according to the kind of fruit.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.131.6-131
• /
• 2001

During the operation of crane system in container yard, it is necessary to control the crane trolley position and loop length so that the swing of the hanging container is minimized. Recently an automatic control system with high speed and rapid transportation is required. Therefore, we designed a controller to control the stacking crane system.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.721-726
• /
• 1989

A control system was developed for raw material yards of the works of a metal industry. It is devoted to the automatic operations of the raw material yards stackers, and to the improvement of the stacking method to stack granular coal uniformly. The system automatically controls the stacking operations without human intervention, and also prevents any collision between cranes, stackers, jibloaders and the level-roughing cranes.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2105-2107
• /
• 2001

During the operation of crane system in container yard, it is necessary to control the crane trolley position and loop length so that the swing of the hanging container is minimized. Recently an automatic control system with high speed and rapid transportation is required. Therefore, we designed a controller to control the Stack crane system.

• The Journal of Engineering Geology
• /
• v.5 no.3
• /
• pp.331-337
• /
• 1995

In estimating the azimuth of regional earthquakes with single -station three - component data, in some cases the result is dependent on the selection of waveforms, making the measurement subjective and inconvenient in automatic detection. In this paper an alternative approach is proposed in which the azimuth is measured from quite a long wave train by time - direction stacking technique. Test with digital waveform data from Korean seimic stations shows that the simple algorithm seems to be able to give a better estima- tion of azimuth of earthquakes at regional distances.

• The KIPS Transactions:PartB
• /
• v.11B no.5
• /
• pp.545-554
• /
• 2004

Combining multiple classifiers to obtain improved performance over the individual classifier has been a widely used technique. The task of constructing a multiple classifier system(MCS) contains two different Issues how to generate a diverse set of base-level classifiers and how to combine their predictions. In this paper, we review the characteristics of existing multiple classifier systems : Bagging, Boosting, and Slaking. For document classification, we propose new MCSs such as Stacked Bagging, Stacked Boosting, Bagged Stacking, Boosted Stacking. These MCSs are a sort of hybrid MCSs that combine advantages of existing MCSs such as Bugging, Boosting, and Stacking. We conducted some experiments of document classification to evaluate the performances of the proposed schemes on MEDLINE, Usenet news, and Web document collections. The result of experiments demonstrate the superiority of our hybrid MCSs over the existing ones.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.4
• /
• pp.109-119
• /
• 2004

Rapid prototyping (RP) technologies have been widely used to reduce the lead-time and development cost of new products. $VLM-_{ST}$ process has been developed to overcome the currently developed RP technologies such as a large building time, a high building cost, an additional post-processing and a large apparatus cost. $VLM-_{ST}$ process requires an additional human interaction due to the manual stacking and bonding. Hence, building time, building cost and the part quality are dependent on the skill of labor. A novel RP process, fully automated $VLM-_{ST}$ process ($VLM-_{ST}$), has been developed to improve building efficiency of the process and the human dependency of the part. The objective of this work is to propose a $VLM-_{ST}$ process and to develop an apparatus for implementation of the process. $VLM-_{ST}$ process and its apparatus have various technical novelties such as two step cutting using a rotating table, an automatic stacking method using two pilot holes and two reference shapes, a concept of automatic unit shape layer (AUSL), and an automatic bonding using the bonding roller and building magazine. In order to examine the efficiency and the applicability of the proposed process, various three-dimensional shapes, such as a piston, a human head shape and a human bust shape, were fabricated on the apparatus.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.62-65
• /
• 2003

VLM-ST process requires an additional human interaction due to the manual stacking and bonding. Hence, building time, building cost and the part quality are dependent on the skill of labor. In this present work, a novel rapid prototyping (RP) process, as an automatic VLM-ST (VLM-STA), has been proposed to improve building efficiency of VLM-ST process and reliability of products. The apparatus of VLM-STA is designed to embody the process. Several characteristics of the proposed process and the apparatus are discussed. In order to examine the efficiency and the applicability of the proposed process, various three-dimensional shapes, such as a piston and a human head shape, are fabricated on the apparatus.