• Journal of the Korea Furniture Society
• /
• v.22 no.4
• /
• pp.323-329
• /
• 2011

In our country, domestic species can not be used as a structural member because we have not yet grading system. So, to utilize as a basic data of grading system, bending test and numerical modelling on structural member were conducted in this study. 35 of Douglas-fir, 2" ${\times}$ 6", span 2.4 m were tested for the bending properties, and Ansys software was used to analyze the numerical modelling on the structural members. The data of knots were inspected and applied in numerical modelling. To obtain the accuracy of analysis, nonlinear numerical analysis was carried out instead of linear numerical analysis. Ultimate load had a wide range from 4883N to 11,738 N, and maximum deformation also had a range from 26 mm to 68 mm. Average of ultimate load was 8,616 N, and that of maximum deformation was 48 mm. The distinctive features of failure types were simple tension type and cross-grain tension type. Ulitmate load and maximum deformation from numerical modelling were 7,504 N and 37 mm. The numerical modelling drawn by this study is available to all species, and reasonable prediction on the bending performance is possible with only some material properties.

• Journal of the Korean Society of Tobacco Science
• /
• v.17 no.1
• /
• pp.5-14
• /
• 1995

Efficient algorithms for the automatic classification of flue-cured tovacco ripeness and grading have been developed The ripeness of the tobacco was classified into 4 levels vased on the color. The lab-built simple RGB color measuring system was utilized for detecting the light reflectance of the tobacco leaves. The measured data were used far training the artificial neural network The performance of the trained network was also tested far the untrained samples. The spectrophotometer was used to detect the light reflectance and absorption of the graded tobacco leaves in the frequency ranges of the visible light The measured data and the statistical analysis was performed to investigate the light characteristics of the graded samples. The measured data were obtained from samples of 5 different grades directly without considering the leaf positions. Those data were used far training the artificial neural network The performance of the trained network was also tested far the untrained samples. The neural network based sensor information processing showed successful results for grading of tobacco leaves.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.425-427
• /
• 2022

The grade of glioma is important information related to survival and thus is important to classify the grade of glioma before treatment to evaluate tumor progression and treatment planning. Glioma grading is mostly divided into high-grade glioma (HGG) and low-grade glioma (LGG). In this study, image preprocessing techniques are applied to analyze magnetic resonance imaging (MRI) using the deep neural network model. Classification performance of the deep neural network model is evaluated. The highest-performance EfficientNet-B6 model shows results of accuracy 0.9046, sensitivity 0.9570, specificity 0.7976, AUC 0.8702, and F1-Score 0.8152 in 5-fold cross-validation.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.7 no.4 s.19
• /
• pp.26-35
• /
• 2004

The ASTP is the standard of the assessment ASRP that is monitoring the performance, reliability and safety characteristics of the ammunition items. The ASTP used in domestic now has applied to US Army's grade system and grading criteria so that it cause some problems. To resolve these problems of ASTP, we surveyed both the quality level of production and the field management of ammunition, which compared with grade system and classification criteria. As a result of study, we changed grade system from four steps to three steps and applied the Korean Military Specifications and the Malfunction Criteria to the classification criteria of grades. We are looking forward to improving the reliability and effectiveness of ASRP assessment by simplifying grade system and generalizing grading criteria of ASTP.

• Journal of Biosystems Engineering
• /
• v.23 no.6
• /
• pp.607-614
• /
• 1998

An automatic grading algorithm was developed to replace the manual trading of white ginseng. The algorithm consists of three consecutive stages, (a) image acquisition and preprocessing, (b) mathematical feature extraction, and (c) grade decision using artificial neural network. Mathematical features such as area ratio, mean and standard deviation of graylevel, skewness of graylevel histogram, and the number of run segment are extracted from five equally divided parts of ginseng. An artificial neural network model was used to classify white ginsengs into three categories. The performance of the algorithm was evaluated using 120 ginseng samples and the rate of successful classification was 74%.

• Journal of Biosystems Engineering
• /
• v.18 no.4
• /
• pp.358-370
• /
• 1993

In Korea, fruit grading has been mainly done manually, and manual grading depends on human sense. Thus it is subjected to human error and is not always as consistent as would be desired. Therefore, a study on the development of fruit grader was initiated to improve the consistency of fruit grading. The sensitivity for fruit weight of the conventional spring type weight grader has a tendency to decrease by physical characteristics of spring which is used as a weight sensing unit. This study was carried out to develop weight measuring device for establishing the base of weight sensing unit of electronic weight grader. This device consists of a weight sensor using load cell, data acquisition system, and a microcomputer containing program to calculate fruit weight. The weight measuring device using load cell was developed to increase sensitivity of fruit weight. The result of this study showed that the weight sensing unit of electronic weight grader contributed to the improvement of performance of weight measuring device.

• Computers and Concrete
• /
• v.10 no.1
• /
• pp.19-33
• /
• 2012

The performance of a concrete is significantly influenced by its mixture proportion and the coating thickness on aggregate surface. The concrete in this study is designed by estimating the blending ratio of aggregate using a densified mixture design algorithm (DMDA) based on an ideal grading curve and estimating the paste volume as the sum of the amount of paste needed to provide an assigned coating paste thickness. So as to obtain appropriate concrete amount, and thus can accurately estimate the property of concrete. Deduction of this mix design formula is simple and easy understanding, and meanwhile to obtain result is fast. This estimation model of mix design is expected to reward to industry and effectively upgrade concrete quality.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.773-779
• /
• 1996

Dried oak mushroom have complex and various visual features. Grading and sorting of dried oak mushrooms has been done by the human expert. Though actions involved in human grading looked simple, a decision making underneath the simple action comes from the result of the complex neural processing of the visual image. Through processing details involved in human visual recognition has not been fully investigated yet, it might say human can recognize objects via one of three ways such as extracting specific features or just image itself without extracting those features or in a combined manner. In most cases, extracting some special quantitative features from the camera image requires complex algorithms and processing of the gray level image requires the heavy computing load. This fact can be worse especially in dealing with nonuniform, irregular and fuzzy shaped agricultural products, resulting in poor performance because of the sensitiveness to the crisp criteria or specific ules set up by algorithms. Also restriction of the real time processing often forces to use binary segmentation but in that case some important information of the object can be lost. In this paper, the neuro net based real time recognition algorithm was proposed without extracting any visual feature but using only the directly captured raw gray images. Specially formated adaptable size of grids was proposed for the network input. The compensation of illumination was also done to accomodate the variable lighting environment. The proposed grading scheme showed very successful results.

• Land and Housing Review
• /
• v.5 no.2
• /
• pp.81-89
• /
• 2014

This paper presents various attempts to secure the floor impact sound insulation performance on the dry floor system of steel framed modular house that lately attracted domestic attention. Test results show that in the condition of using dry floor system of D31(D32), the light-weight impact noise performance records the top level in the floor impact sound insulation performance grading system. the heavy-weight floor impact noise performance meets the minimum sound level limit in the floor impact sound insulation performance grading system that enacted regulation on housing construction standards.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.05b
• /
• pp.25-29
• /
• 2004

Corona on polymer materials causes deterioration by the combined action of the discharge striking the surface and the action of certain chemical compounds that are formed by the discharges. In the design and manufacture of polymer insulators must be sufficiently large to avoid corona discharges, otherwise a shielding or corona ring (grading ring) needs to be installed on the insulator. To conduct this purpose, many researchers have investigated end-fitting of polymer insulator by voltage distribution simulation and electrical test. Grading rings are used to improve the performance of the insulator in multiple ways. They can reduce corona and associated audible noise and radio influence and television interference. The factors determining the uses of a grading ring are line voltage, geometry and dimensions of end fittings, geometry and dimensions of line hardware, and environmental conditions. In this paper, electrical property of polymer insulator with end-fitting design have been investigated by electrical field analysis, various end-fitting design, tracking wheel test, corona inception voltage and extinction voltage. Electrical field analysis is conducted by FEM program and various end-fitting is designed through this result. Designed end-fittings are manufactured and their performance is conducted by electrical performance test.