• The Journal of the Korea Contents Association
• /
• v.20 no.7
• /
• pp.86-96
• /
• 2020

Based on the use cases of image recognition technology, this study looked at how artificial intelligence plays a role in image recognition technology. Through image recognition technology, satellite images can be analyzed with artificial intelligence to reveal the calculation of oil storage tanks in certain countries. And image recognition technology makes it possible for searching images or products similar to images taken or downloaded by users, as well as arranging fruit yields, or detecting plant diseases. Based on deep learning and neural network algorithms, we can recognize people's age, gender, and mood, confirming that image recognition technology is being applied in various industries. In this study, we can look at the use cases of domestic and overseas image recognition technology, as well as see which methods are being applied to the industry. In addition, through this study, the direction of future research was presented, focusing on various successful cases in which image recognition technology was implemented and applied in various industries. At the conclusion, it can be considered that the direction in which domestic image recognition technology should move forward in the future.

• Journal of Korean Society for Atmospheric Environment
• /
• v.28 no.6
• /
• pp.656-665
• /
• 2012

Recently, yearly production of SRF (Solid Recovered Fuel) as an alternative fuel has been rapidly increasing because of the limited waste disposal, rise in oil prices and reduction of greenhouse gas emission. However, SRF using facilities are excluded from the National Air Pollutant Emission Estimation because SRF using facilities are not yet included among the SCC (Source Classification Code). The purpose of this research was to estimate the emission and emission factor of SRF using facilities' PM and $NO_x$, in order to investigate whether or not they are included in the National Air Pollutant Emission Estimation. The emission factors of SRF using facilities' PM and $NO_x$ are calculated as 0.216 kg/ton, and 3.970 kg/ton, and the emission was estimated based on the yearly total SRF usage of 2011. The results above was 18.7% for PM and 12.8% for $NO_x$ emissions from combustion facility (SCC2) in manufacturing industry combustion (SCC1) of CAPSS. If CAPSS estimate the emission by adding SCC on unlisted SRF in case of Boiler (SCC3) fuel, both PM and $NO_x$'s emissions would increase by 15.8% and 11.3% compare to the emissions for the existing combustion facility. As a result, emissions caused by SRF should be considered when calculating the National Air Pollutant Emission Estimation. In addition, further researches to develop emission factor and improve subdivided SCC should be done in the future, for the accurate and reliable estimation of National Emission.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.11
• /
• pp.2037-2042
• /
• 2017

The manufacturing facility is generally operated by a pre-set program under the existing factory automation system. On the other hand, the manufacturing facility must decide how to operate autonomously in Industry 4.0. Determining the operation mode of the production facility itself means, for example, that it detects the abnormality such as the deterioration of the facility at the shop-floor, prediction of the occurrence of the problem, detection of the defect of the product, In this paper, we propose a manufacturing process modeling using a queue for detection of manufacturing process abnormalities at the shop-floor, and detect abnormalities in the modeling using SVM, one of the machine learning techniques. The queue was used for M / D / 1 and the conveyor belt manufacturing system was modeled based on ${\mu}$, ${\lambda}$, and ${\rho}$. SVM was used to detect anomalous signs through changes in ${\rho}$.

• Journal of Korean Society on Water Environment
• /
• v.23 no.5
• /
• pp.766-775
• /
• 2007

The use of toxic chemicals was extended as the industry in Korea has grown dramatically during the last three decades. However, list of toxic substances and limit concentrations in the water environment are not consistent within management of ambient water, drinking water and industrial effluent. This article suggests the systematic framework to classify toxic substances in the water environment and deriving their effluent limits. The most important factor for decision-making to classify toxic substances is whether their concentrations in the water environment are higher than the reference concentrations, estimated by considering human health risk and ecological risk. Using a risk-based reference concentration, the ambient water quality criterion, it is possible to derive the regulatory limit concentrations of toxic substances in drinking water and in industrial effluent. The goal concentrations in the effluent, which guarantee the human and ecological safety, should be determined with scientific investigation, balancing environmental benefit and economical effect, considering availability of treatment technology and identifying characteristics of wastewater from different industries.

• International Commerce and Information Review
• /
• v.8 no.3
• /
• pp.299-321
• /
• 2006

The purpose of this study was to analyze export competitiveness of Korean auto parts and Chinese auto parts in U.S. market by using Index of Export Bias and Market Comparative Advantage Index. For attaining the purpose of study, we classified the auto parts which exported to U.S. market and the imported products by using the six units classification of the Harmonized System(HS). Analyzing period was 1998-2005. The analysis of Korean results of MCA indicated that the Korean auto parts which gained export competitiveness in the U.S. market were HS Code No. 8708.94, 8708.99, 8708.92. The products which will have export competitiveness in the U.S. market would be HS Code No. 8708.93, 8708.39, 8708.60 respectively. On the other hand, the results indicated that the Chinese auto parts which gained export competitiveness in the U.S. market were HS Code No. 8708.70, 8708.31, 8708.91, 8708.60, 8708.39. From this study, we find the following strategies for successful advancing into the U.S. and world market. i) Linking strategy through working cooperation with local auto firms, government and academic world. ii) Advance strategy of auto firm accompany by module working and system auto parts firm. iii) Retention strategy of large technical institution established by auto parts firms and taking cooperation of auto firms iv) Settlement strategy for having weaken competitive article and production field. v) Cost-cutting strategy through strengthening logistics cooperation system between auto parts firms and auto firms. vi) Active invitation strategy of foreign investment under quickly cooperating of government.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.3
• /
• pp.90-98
• /
• 2011

The recognition and classification of paddy rice disease are of major importance to the technical and economical aspect of agricultural industry over the world. Computer vision techniques are used to diagnose rice diseases and to efficiently manage crops. Segmentation of lesions is the most important technique to detect paddy rice disease early and accurately. A new Gaussian Mean (GM) method was proposed to segment paddy rice diseases in various color spaces. Different color spaces produced different results in segmenting paddy diseases. Thus, this empirical study was conducted with the motivation to determine which color space is best for segmentation of rice disease. It included five color spaces; NTSC, CIE, YCbCr, HSV and the normalized RGB(NRGB). The results showed that YCbCr was the best color space for optimal segmentation of the disease lesions with 98.0% of accuracy. Furthermore, the proposed method demonstrated that diseases lesions of paddy rice can be segmented automatically and robustly.

• Journal of IKEEE
• /
• v.5 no.2 s.9
• /
• pp.190-200
• /
• 2001

This paper is addressed to welding defect feature vector selection and implementation method of welding defect classifier using fuzzy techniques. We compare IAV, zero-crossing number as time domain analysis, power spectrum coefficient as frequency domain, histogram as both domain for welding defect feature selection. We choose histogram as feature vector by graph analysis and find out that maximum frequent occurrence number and section of corresponding signal scale in relative histogram show obvious difference between normal welding and voiding with penetration depth defect. We implement a fuzzy welding defect classifier using these feature vector, test it to verify its effectiveness for 695 welding data frame which consist of 4000 sampled data. As result of test, correct classification rate is 92.96%. Lab experimental results show a effectiveness of fuzzy welding defect classifier using relative histogram for practical Laser welding monitoring system in industry.

• Korea Journal of Hospital Management
• /
• v.13 no.4
• /
• pp.119-145
• /
• 2008

The objectives of this study were to inspect how the law effected on hospital employment system and which policy and strategy are needed to cope with the present situation as the law regarding irregular workers law has enacted for a year. To grasp the changes of employment style in hospital, 56 hospitals among 311 general hospitals were questioned in this study. And employment policy and strategy were developed by referencing examples of developed nations and other industries. The survey showed that the wage and welfare level of irregular workers in hospitals was improved compared to that in the other industries. But there were still much discrimination between regular and irregular workers. The policy direction of government is, first of all, to follow the principle of equal treatment to equal value of labour. The first feasible policy is to enforce social security. The second one is an employment promotion policy which reduces or exempts hospitals employing irregular workers from tax and insurance fee. The third one is to extend employment contract period to 3 years. and finally there are policies to permit more dispatched jobs and to expand the social insurance coverage. The strategies to solve the problem of irregular workers are as follows; 1) performance wage system, 2) guaranteeing employment by unlimited contract, 3) creating new category of workers, 4) the wage system of management by object, 5) the method of job classification. This study has a meaning in the point that it was studied on hospital which is special industrial part and analyzed the changes after enacting irregular workers law and presented management strategy for countermeaure program. In this study, it was expected to contribute to decisions-making in hospital management, especially when using human resources.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.22 no.1
• /
• pp.33-44
• /
• 2020

The purpose of this study is to guide the research direction for securing the competitiveness of the textile industry by analyzing the trends of patent technology development for flexible materials and platform technologies of domestic and overseas textiles used for wearable devices. The study is based on patents from Korea (KIPO), USA (USPTO), Japan (JPO), Europe (EPO), PCT (WO), and China (SIPO), which were registered as of December 31, 2017. The analysis utilized 3,643 patents acquired from the WINTELIPS search DB. The technology classification system for patent analysis was divided into evangelist-based textile technology developments: human body (AA), fiber attachment patch development (AB), and service platform development (AC). The analysis findings are as follows: 1. The development of flexible materials and platform technologies for textile-based wearable devices has increased since 2000. In particular, China (SIPO) had the most patents. 2. In China, Japan, and Korea, most patent applicants are applied for by natives, but the US has a high proportion of foreigners applying for patents. 3. As for the amount of development of the evangelist-based textile technology (AA) was the most common with 1,203 (33%) cases. As a result of the above IP historical analysis, it can be seen that as a result of the global competition, domestic companies need to acquire IRP and standard technology, and promote commercialization by applying their products to smart wearables devices and other products.

• Journal of The Korean Association For Science Education
• /
• v.1 no.1
• /
• pp.15-27
• /
• 1978

First: The common points from "syllabus" period to that of "Course of study" are as follows: 1) with no introduction explained. the "Syllabus" or "Course of study" was made to be completed in accordance with the allotment of time (unit). 2) To teach how to rear animals and grow plants, and to make specimens with collected samples formed a great significant field of learning, which meant giving more emphasis on learning classification, life-centered education and basic field of learning than discipline-centered education. 3) The reason why the field of applied biology was emphasized on was that both periods had ideals in Common to educate persons more necessary and useful to the society than to major the pure academic field. 4) Both periods mainly dealt with problems of diseases, and physical health discussed all over the world in 1950's which accounts for necessity of the society to free from ignorance. Second; "The first curriculum period" and "the second one" are observed as follows: 1) The former took the unit (credit) system for the first time. It tried to lay down the conceptual hierarchy with "Biology I" and "II" divided, while "Biolgy I" is better systematized than "Biology II". 2) Discipline-centered education and structure fo knowledge are put more emphasis on especially in "the 2nd curriculum period". 3) And also in this period are included serious problems such as urgency of pollution, importance of nature conservation, population due to the development of industry. 'Third; With the recent curriculum laid down, experiments and teaching contents of subjects are put in harmony with each other and accordingly the process of Inquiry is laid emphasis on. Fourth; It is necessary to set up conceptual sequence and scope effectively in the curriculum.