• The Journal of the Convergence on Culture Technology
• /
• v.4 no.2
• /
• pp.197-204
• /
• 2018

One of the hottest issues in our 21st century is AI. Just as the automation of manual labor has been achieved through the Industrial Revolution in the agricultural society, the intelligence information society has come through the SW Revolution in the information society. With the advent of Google 'Alpha Go', the computer has learned and predicted its own machine learning, and now the time has come for the computer to surpass the human, even to the world of Baduk, in other words, the computer. Machine learning ML (machine learning) is a field of artificial intelligence. Machine learning ML (machine learning) is a field of artificial intelligence, which means that AI technology is developed to allow the computer to learn by itself. The time has come when computers are beyond human beings. Many companies use machine learning, for example, to keep learning images on Facebook, and then telling them who they are. We also used a neural network to build an efficient energy usage model for Google's data center optimization. As another example, Microsoft's real-time interpretation model is a more sophisticated translation model as the language-related input data increases through translation learning. As machine learning has been increasingly used in many fields, we have to jump into the AI industry to move forward in our 21st century society.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.18 no.4
• /
• pp.293-302
• /
• 2008

Lead chromate is made by sodium dichromate and lead acetate, and has being used widely in the part of pigment, paints, inks, plastics and so on. Even though lead chromate has health hazards which like both lead and chromium, there are a few study about pigment workplaces using lead chromate in Korea. The purpose of this study is to evaluate workers' exposure levels and airborne lead and chromium concentration in the pigment workplaces using lead chromate. There are 20 workers in the total 5 workplaces. 10 workers(50%) have been exposed to lead and 3 workers(15%) have been exposed to chromium, which exceeded the American Conference of Governmental Industrial Hygienists(ACGIH) Threshold Limit Value (Pb: $0.05\;mg/m^3$, Cr: $0.012\;mg/m^3$) and Korean Ministry of Labor's Standard. Geometric mean (GM) of airborne lead was highest in pigment ($0.0421\;mg/m^3$), paint ($0.0020\;mg/m^3$) and PVC coloring ($0.0007\;mg/m^3$), respectively(p<0.05). The result of airborne chromium concentration was paint ($0.0033\;mg/m^3$), paint ($0.0004\;mg/m^3$) and PVC coloring ($0.0003\;mg/m^3$). Also the lead and chromium concentration in the manual process is each 30 times and 10 times higher than the value in automatic process(p<0.01). In the classified process by detail, the concentration of airborne lead was $0.0638\;mg/m^3$ in grinding & packaging, mixture & after-measuring ($0.0436\;mg/m^3$), filtration & drying ($0.0402\;mg/m^3$), lead nitrate & dissolution($0.0129\;mg/m^3$), pigment commitment & mixture ($0.0013\;mg/m^3$) and dispersion & grinding ($0.0010\;mg/m^3$) (p<0.05). Moreover the concentration of a sample in weighting & packaging was $0.0023\;mg/m^3$. The concentration of lead in workers' blood was pigment (15.12 ug/dl), paint (4.74 ug/dl) and PVC coloring (2.50 ug/dl), and some samples have exceeded biological exposure limit. In conclusion, the depending on their work industry and process, workers have been exposed to the high lead chromate.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.65 no.2
• /
• pp.151-155
• /
• 2020

This study was conducted to determine the effects of the selection of an appropriate sowing method in on ginseng growth, and the results are as follows. SAS (semi-automatic sower), commonly used by direct seeding farms, provides fast operation speed but results in high labor cost, while (Hooper Seeder Sowing) offers fast operation speed and high germination rate, but leads to increased laborer's fatigue. Daily working area per sower was 6,611 ㎡ for a motor type, and the operation time to sow 3,305 ㎡ was 15 hours for broadcast planting, and 8 hours for SAS. The germination rate of 1-year-old ginseng according to direct seeding was 69.1% for the treatment plot under broadcast planting, followed by 66.4% and 67.3% for manual sower and hoop sower, respectively, and the germination rate of SAS was the lowest at 64.2%. In addition, there were no differences in shoot and root growth of 1-year-old ginseng among the sowing methods. Therefore, the sowing method can be chosen depending on the economic size of ginseng farmers. That broadcast sowing (BS) is appropriate for small scale farmers, while motor-driven seeder sowing (MDS) for direct seeding is more suitable for large scale farmers.

• Archives of design research
• /
• v.19 no.5 s.67
• /
• pp.55-64
• /
• 2006

As digital systems were introduced to automotive design in the mid 1980s, the design process has adopted many digital programs to save time compared to the conventional hand drafting. Digital technology was introduced not only to satisfy the reeds of the global environment, as the number of automobiles exported to many different parts of the world has increased, but also to save time and effort in developing several models of quality automobiles. Therefore, every automotive manufacturer in the world has expanded its virtual reality(VR) studio to establish visualization systems that visualize automobiles in the actual size and a co-operation system that enables simultaneous feedback from all of its design studios around the world. Unlike the existing design reviewing methos, the new improved feedback system is assessed as a reasonable method to evaluates and understand how the automobiles are actually manufactured in simulation. It is especially helpful when advanced products and concept cars require fast results. Other strengths of the new system include shorter development period, cost efficiency, no more manual labor, various designs within a short period of time, and realistic visualization of concepts. Large-scale products, including automobiles, need to be projected in the actual size and high clarity through the Power-wall System and are examined in a virtual space called a Cave. Therefore, it took much time to establish digital infrastructure. An infrastructure would constantly require system improvement and performance enhancement, but it is certain that now is the right time for the take-off to utilizing the strengths of digital design and improve the weaknesses. In this respect, this study provided an understanding of the importance of digital design based on digital reinforcements and examined an effective utilization of digital technology for an efficient development of automobiles in the future.

• 대한공업교육학회지
• /
• v.39 no.2
• /
• pp.81-100
• /
• 2014

This study developed training program to educate professional workers for software industry with growing importance in this area as software industry takes more parts in Korean economy. Additionally, this study developed the program based on national competency standards(NCS) using structured on the job training(S-OJT), For this study, we reviewed economic index about software industry such as economic ratio and the influx of the workforce. Also literature review for S-OJT was conducted to explore its concept for better application of the concept to the program development. In addition, this study used training program development manual suggested by Korean Department of Labor. We selected specific job which needs training program to be developed based on thorough needs analysis for a company A. Previously developed NCS and other documents were reviewed and focus group interviews were conducted to find out core knowledge and skills for the job. 44 training programs were developed and objective of each program, hours, contents and methods were also suggested. Additionally detailed program name, education system, road map and operation strategy were developed and suggested. The result of this study is expected to contribute to other industry and jobs which are facing to the development of NCS based education program by suggesting detailed stage of development process. For more animated development of education program using NCS, the effect of the program should be tested in the future. For the test, appropriate evaluation methods and measures should be developed as well.

• Women's Health Nursing
• /
• v.17 no.3
• /
• pp.225-242
• /
• 2011

Purpose: The purpose of this study was to identify students' experiences of performance and their satisfaction with clinical nursing practice in Women's health nursing. Methods: Data was collected using questionnaire consisting of 104; 89,; and 82 nursing activities with 12; 10; and 7 domains for delivery floor, obstetric, and gynecologic wards retrospectively. Five hundred ninety nursing students from 10 four year and one three year colleges, were recruited and selected for data collection. Results: Site specific core nursing activities among top 15 items of performed experience were: interpreting fetal monitoring; massage for pain reduction; breathing technique; perineal pad change; non stress test; manual check for uterine contraction; and position change for the delivery floor. Experiences of clinical nursing practice for the obstetric ward and the gynecologic ward were identified and ranked as well. Observation of delivery, measurement & test during labor and observation of anesthesia and operation were the highest ranked activity domains of satisfaction for delivery floor, obstetric and gynecologic wards retrospectively. Conclusion: Discussions are needed to standardize curriculum for clinical practice in women's health nursing initiated at the level of Korean Society of Womens' Health Nursing by reflecting this result. Strategic approaches are emphasized in order to enhance a collaboration between clinical fields and colleges.

• Journal of agricultural medicine and community health
• /
• v.5 no.1
• /
• pp.16-27
• /
• 1980

Five hundred seventeen farmers(214 males and 303 females), over age 30 and living in Suh San County, Unsan township, were examined to determine the prevalence of peasants syndrome. Using the health interview questionnaire, the farmers were asked whether they had any of eight subjective symptoms during the past one month before the survey, October 1979. Those symptoms reported were scored based on a pre-determined point system. The farmers with high symptom scores(7 points or more) were further examined by the liver function test. In addition, all the sample(517 cases) were subjected to the examination of urinalysis and blood pressure. The liver function test is also undertaken for those farmers with high symptome scores(7 points or more) and those with abnormal findings in urinalysis and blood pressure. The results are summarized below: 1) 156 out of 517 farmers(30.2%) have had seven points or more of the symptom scores. Among the eight major symptoms, 72% of the farmers complained of lumbago. 2) The prevalence of peasant's syndrome were higher among females and the older age group. The symptom scores of this syndrome were slightly higher among women who have had many children (e. g. 4 or more). 3) The prevalence of peasant's syndrome was also related to the level of one's education-the lower education groups were found to have higher symptom scores of this syndrome. This may be due to the fact that the lower education groups are more exposed to manual labor. 4) The points of the peasants syndrome were higher in hypertensive farmers and those with abnormal findings of urinaly sis. 5) It was reported, in Japan, that those with high scores of the syndrome are more likely to have an abnormal findings in the liver function test. However, in this study it was observed that there was no significant difference between those with high scores of the syndrome (7 points or more) and those with low score of the syndrome(6 points or less) in the prevalence of abnormal liver function. As this study indicates that the point system given for the peasant's syndrome is closely related to the high bleod pressure and abnormal urinalysis(and to some extent to the abnormal liver function), there is a need to study peasant's syndrome more extensively. Such an effort will serve to detect varonic disease conditions among farmer's towards better management of farmer's health, which is vitally important for rural development in Korea.

• Journal of the Korea Computer Graphics Society
• /
• v.20 no.2
• /
• pp.1-11
• /
• 2014

The quality of 2D-to-3D conversion depends on the accuracy of the assigned depth to scene objects. Manual depth painting for given objects is labor intensive as each frame is painted. Specifically, a human is one of the most challenging objects for a high-quality conversion, as a human body is an articulated figure and has many degrees of freedom (DOF). In addition, various styles of clothes, accessories, and hair create a very complex silhouette around the 2D human object. We propose an efficient method to estimate visually pleasing depths of a human at every frame in a monocular video. First, a 3D template model is matched to a person in a monocular video with a small number of specified user correspondences. Our pose estimation with sequential joint angular constraints reproduces a various range of human motions (i.e., spine bending) by allowing the utilization of a fully skinned 3D model with a large number of joints and DOFs. The initial depth of the 2D object in the video is assigned from the matched results, and then propagated toward areas where the depth is missing to produce a complete depth map. For the effective handling of the complex silhouettes and appearances, we introduce a partial depth propagation method based on color segmentation to ensure the detail of the results. We compared the result and depth maps painted by experienced artists. The comparison shows that our method produces viable depth maps of humans in monocular videos efficiently.

• Journal of Biomedical Engineering Research
• /
• v.23 no.3
• /
• pp.235-241
• /
• 2002

The detection of tubercle bacilli (TB) from sputum smear is one of the fast and inexpensive methods for diagnosis of tuberculosis. For this method. sputum smears are usually flexed by heating and stained by acid-fast staining method, and then examined under an optical microscope. Two Procedures are commonly used fur TB staining. One is hot staining and the other is cold staining method. The Ziehl-Neelsen method which is a hot staining method is widely used in Korea because its stained color is more vivid However, the conventional automated stainer has to fix the sputum smear on a slide manually and the stain is not so vivid because it has not heating function. In an effort to save labor and minimize variations in manual staining Procedure. we developed an automated stainer with heating function. The entire staining process is fully automated. from fixation to final washing and drying. With the automated methods, five slides can be flexed and stained in 21 minutes at consistent high quality We compared the concordance rate between the two methods for 91 sputum samples to validate the stain quality of the developed automated stainer. As the results, the concordant rate between the two methods was 95% and there was no significant difference (p>0.05)

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.133-139
• /
• 2021

Currently, the process of constructing a high-definition road map has a high proportion of manual labor, so there are limitations in construction time and cost. Research to automate map production with high-definition road maps using artificial intelligence is being actively conducted, but since the construction of training data for the map construction is also done manually, there is a need to automatically build training data. Therefore, in this study, after converting to images using point clouds acquired by a mobile mapping system, the road marking areas were extracted through image reclassification and overlap analysis using thresholds. Then, a methodology was proposed to automatically construct training data for deep learning data for the high-definition road map through the classification of the polygon types in the extracted regions. As a result of training 2,764 lane data constructed through the proposed methodology on a deep learning-based PointNet model, the training accuracy was 99.977%, and as a result of predicting the lanes of three color types using the trained model, the accuracy was 99.566%. Therefore, it was found that the methodology proposed in this study can efficiently produce training data for high-definition road maps, and it is believed that the map production process of road markings can also be automated.