• Applied Biological Chemistry
• /
• v.22 no.1
• /
• pp.18-23
• /
• 1979

To prepare the objective quality control index of red pepper powder, the relationships among the color appearance, capsanthin red pigment and the contamination of coliform bacteria were studied and summarized as followings; 1. Visual method by human eyes was inadequate to grade the quality of red pepper powder, because of the different personal color evaluation. 2. Grading upon capsanthin contents are well agreed with the color appearance of the red pepper powder. Therefore, color appearance can be correlated with the capsanthin content. 3. Color appearance of the red pepper can be numerically expressed with Hunter-value a/b; Capsanthin $content(mg/g-red pepper)=0.257{\times}10^{0.703}(a/b)$ and it can be used as an index of the quality control of red pepper powder. 4. There was no distinct correlation between the comtamination of coliform bacteria and the color value.

• The Journal of the Korea Contents Association
• /
• v.16 no.12
• /
• pp.458-467
• /
• 2016

An expert search method using a large amount of academic data that can provide users with representative research results and advice is required. Since the existing expert search methods perform the expert search based on user profile or activity information, they have a problem that it is hard to discriminate the expert when we do not know the user profile or activity information. In this paper, we propose an academic expert search method using the importance and quality of a paper. The importance of a paper is computed by considering its scarcity and up-to-date topics. The quality of a paper is evaluated by considering the number of citations, IF of Journal, recency and author relations. To show the superiority of the proposed method, we compare it with the existing scheme through the performance evaluation in terms of recall and precision.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.3
• /
• pp.30-35
• /
• 2002

This study is for developing an algorithm to detect defects of manufactured textile fiber. We used CCD Video Input Equipments in order to capture fiber textile images. Though most of the fiber manufacturing procedures consist of automatic systems, present textile detecting systems are depending on manual inspection system. However this method is not very economical. Therefore we can expect high production rate in the fiber manufacturing area if we could develop and utilize an image processing algorithm to inspect defects of textile fiber. The study was aimed at and achieved development of an detecting algorithm using image processing methods and related mechanical system which enable to detect missing of threads, mixing of unnecessary materials, polluted areas, scars, and colour differences in the textile. Through this study we could devise a manless system for detection of fiber textile and Provide possibilities which apply the image Processing techniques to the other manufacturing inspection systems.

• Journal of Digital Convergence
• /
• v.19 no.9
• /
• pp.209-215
• /
• 2021

Data quality management is an important issue these days. Improve data quality by providing consistent metadata. This study presents algorithms that facilitate standard word dictionary management for consistent metadata management. Algorithms are presented to automate synonyms management of database metadata through web dictionary crawling. It also improves the accuracy of the data by resolving homonym distinction issues that may arise during the web dictionary crawling process. The algorithm proposed in this study increases the reliability of metadata data quality compared to the existing passive management. It can also reduce the time spent on registering and managing synonym data. Further research on the new data standardization partial automation model will need to be continued, with a detailed understanding of some of the automatable tasks in future data standardization activities.

• Journal of Korean Society of Archives and Records Management
• /
• v.22 no.1
• /
• pp.43-59
• /
• 2022

Electronic public records are classified simultaneously as production, a preservation period is granted, and after a certain period, they are transferred to an archive and preserved. This study intends to find a way to improve the efficiency in classifying transferred records and maintain consistent standards. To this end, the current record classification work process carried out by the National Archives of Korea was analyzed, and problems were identified. As a way to minimize the manual work of record classification by converging the required improvement, the process of identifying outlier candidates based on a list consisting of classified information of the transferred records was proposed and systemized. Furthermore, the proposed outlier discrimination process was applied to the actual records transferred to the National Archives of Korea. The results were standardized and constructed as a training data format that can be used for machine learning in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.4 no.1
• /
• pp.27-30
• /
• 2003

Amethyst is a precious stone in Korea. As natural quartz are usually mixed with smoky quartz, amethyst, and milky quartz, we need to evaluate the amount of the amethyst quantitatively in ores. Although the optical evaluation with bare eyes has been common in assay so far, we propose that the diamagnetic property and microstructural difference characterization be the solution for the evaluating the quartz ores. In addition, FTIR (Fourier transformation infra-red) could help to identify the amethyst transparency. We report that we could evaluate the amethyst quantitatively with M-H hysteresis characterization, transmission electron microscopy (TEM) observation and FTIR characterization.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.27-35
• /
• 2024

This study deals with a method of combining image generation using Semi Supervised Learning based on GAN (Generative Adversarial Network) and image classification using ResNet50. Through this, a new approach was proposed to obtain more accurate and diverse results by integrating image generation and classification. The generator and discriminator are trained to distinguish generated images from actual images, and image classification is performed using ResNet50. In the experimental results, it was confirmed that the quality of the generated images changes depending on the epoch, and through this, we aim to improve the accuracy of industrial accident prediction. In addition, we would like to present an efficient method to improve the quality of image generation and increase the accuracy of image classification through the combination of GAN and ResNet50.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.6
• /
• pp.7-20
• /
• 2017

The advancement of cloud and big data and the considerable growth of traffic have increased the complexity and problems in the management inefficiency of existing networks. The software-defined networking (SDN) environment has been developed to solve this problem. SDN enables us to control network equipment through programming by separating the transmission and control functions of the equipment. Accordingly, several studies have been conducted to improve the performance of SDN controllers, such as the method of connecting existing legacy equipment with SDN, the packet management method for efficient data communication, and the method of distributing controller load in a centralized architecture. However, there is insufficient research on the control of SDN in terms of the quality of network-using applications. To support the establishment and change of the routing paths that meet the required network service quality, we require a mechanism to identify network requirements based on a contract for application network service quality and to collect information about the current network status and identify the violations of network service quality. This study proposes a method of identifying the quality violations of network paths through ontology to ensure the network service quality of applications and provide efficient services in an SDN environment.

• Journal of Food Hygiene and Safety
• /
• v.37 no.1
• /
• pp.15-20
• /
• 2022

The purpose of this study was to compare the conventional culture method, enzyme immune method and the PCR method using species-specific primer in the analysis on the Salmonella spp. found in domestically distributed pet foods. For the study, Salmonella spp. were detected from 175 samples. From the conventional culture method and the PCR method, two samples (jerky and corn gluten) were determined as positive. Also, from the enzyme immune method, one sample (corn gluten) was test-positive. The study revealed that application of the PCR method with species-specific primer allows better distinguishment between the species of the strain collected from the samples than the conventional culture method and/or the enzyme immune method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.05a
• /
• pp.401-404
• /
• 2008

In livestock, diagnosis of disease is found on body temperature variation like a human. In case of cattle, body temperature variation can estimate disease that milk fever, toxication, diarrhea, dyspepsia, chronic enteritis, influenza, pneumonia, anthrax. So we are suggested the temperature measurement system for livestock. This system will be useful to a stock farmer and alternative that a worker.