• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• Journal of Food Hygiene and Safety
• /
• v.36 no.1
• /
• pp.42-50
• /
• 2021

Along with the rapid growth of the food service industry, food safety requirements and hygiene are increasing in importance in restaurants and hotels. Accordingly, there is a need for quick and practical monitoring techniques to determine hygiene status in the field. In this study, we investigated 5 domestic 5-star hotels specifically, personal hygiene (hands of workers), cooking utensils (knife, cutting board, food storage container, slicing machine blade, ice-maker scoop) and other facilities (refrigerator handle, sink). In addition, we examined the hygiene management status of customer contact points (tongs for buffet, etc.) to derive the correlation between the ATP values as a, a verification method. As a result of our five-hotel survey, we found that cooking utensils and personal hygiene were relatively sanitary compared to other inspection items (cookware 92.2%, personal hygiene 91.4%, facilities and equipment 76.19%, customer contact items 88.6%). According to our ATP-based mothod, kitchen utensils (51 ± 45 RLU/25㎠) were relatively clean compared to other with facilities and equipment (167 ± 123 RLU/25㎠). In the present study, we also evaluated the usefulness of the ATP bioluminescence method for monitoring surface hygiene at hotel restaurants. After correlation analysis of surveillance of hygienic status points and ATP assay, most results showed negative and high correlation (-0.64--0.89). Our ATP assay (92 ± 67 RLU/25㎠) of each item after cleaning showed signigicantly reduced results compared to the ATP assay (1020 ± 1254 RLU/25㎠) for normal status, thereby indicating its suitability as a tool to verify the validity of cleaning. By our results, ATP bioluminescence could be used as an effective tool for visual numerical evaluation of invisible contaminants.

• Journal of Sericultural and Entomological Science
• /
• no.12
• /
• pp.37-45
• /
• 1970

The processing management forms of our country's filature factories in 1969 are summarized as follows. (1) About 80％ of total cocoon collection is made within 5 days involving peak day, and 10％ of cocoon collection is finished until 3 days before and after the peak day, (2) About 92％ of alive cocoons transported on unpaved road, and about 40％ of the cocoons purchased by all factories are loaded on trucks from common selling station which is far beyond 40km, therefore a new packing system of alive cocoons to drop the damage of cocoon qualities, should be taken. (3) 22％ of all factories in our. country have only low-temperature cocoon drying machine. Therefore the installment of hot-air cocoon drying machine is required urgently. (4) In view of cocoon qualities in our country, the grouping method of cocoon for reeling. taken by about 50％ of the factories at percent, which classify cocoons for reeling as high group (1,2,3,4 grades) and low group(5,6 grades), will have to be replaced by the method tat classify them high group (1,2 grades) middle group (3,4 grades), low group (5,6 grades). (5) The .ratio of cocoon assorting stood about 10％ in multi-ends reeling, about 15％ in automatic reeling, conclusively, the ratio of cocoon assorting for automatic reeling was higher tan that for multi-ends reeling. One person's ability for a day in cocoon assorting reaches to about 80-100kg. (6) Cocoon cooking condition requires the increase of the cooking time, the pressure and temperature used to be prolonged as much as the qualities of cocoons are material cocoon ior automatic and double cocoon machines are treated uncompletely. (7) Automatic silk reeling is being performed at 1-2$^{\circ}C$ lower in reeling water temperature and operated at about twice velocity. (8) The temperature and humidity of rereeling room stood at 25$^{\circ}C$, 67.2％ R.H and 32.3$^{\circ}C$, 51.9％ R.H of rereeling machine are showed, Average rereeling velocity is 233m/min and large reefs charged for one person are 7.5 reels and form of skein used in all factories is double skein. (9) About 73％ of water sources for filature used under-earth water. About 48％ of all filature factories in our country have not yet water purifying equipments. Installation of the equipment for these factories seems to be urgent, (10) Denier .balance, sizing reel, seriplane, are being used in most factories as self-inspection apparatus. (11) More than 90％ of the factories use the vacum tank in rereeling process and about 20％ of them use it in cocoon cooing process (12) Only 21％ of the factories use chemicals in filature process. About all them use "Seracol 100" in cocoon cooking process and "Seracol 500" in rereeling process, (13) Above survey results explain each all factories show large difference in the processing management. Therefore, it is believed that intercommunication through seminar or technical exchange will contribute to the production evaluation of cocoon in our filature industry.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.307-325
• /
• 2023

Due to the prolonged COVID-19 pandemic, the frequency of people who are tired of living indoors visiting nearby mountains and national parks to relieve depression and lethargy has exploded. There is a place where thousands of people who came out of nature stop walking and breathe and rest, that is the mineral spring. Even in mountains or national parks, there are about 600 mineral springs that can be found occasionally in neighboring parks or trails in the metropolitan area. However, due to irregular and manual water quality tests, people drink mineral water without knowing the test results in real time. Therefore, in this study, we intend to develop a model that can predict the quality of the spring water in real time by exploring the factors affecting the quality of the spring water and collecting data scattered in various places. After limiting the regions to Seoul and Gyeonggi-do due to the limitations of data collection, we obtained data on water quality tests from 2015 to 2020 for about 300 mineral springs in 18 cities where data management is well performed. A total of 10 factors were finally selected after two rounds of review among various factors that are considered to affect the suitability of the mineral spring water quality. Using AutoML, an automated machine learning technology that has recently been attracting attention, we derived the top 5 models based on prediction performance among about 20 machine learning methods. Among them, the catboost model has the highest performance with a prediction classification accuracy of 75.26%. In addition, as a result of examining the absolute influence of the variables used in the analysis through the SHAP method on the prediction, the most important factor was whether or not a water quality test was judged nonconforming in the previous water quality test. It was confirmed that the temperature on the day of the inspection and the altitude of the mineral spring had an influence on whether the water quality was unsuitable.

• Korean Journal of Veterinary Research
• /
• v.21 no.2
• /
• pp.151-159
• /
• 1981

An investigation on various causes of milking disturbances resulting from injuries and abnormalities of mammary system were made in 2,179 Holstein cows. To perform this investigation, 69 dairy farms of the suburban area of Seoul city, Gyeonggi-do and Chungnam provinces were andomly selected and subjected. Diagnosis was made by means of inspection and palpation of teat, insertion of teat canula, checking milk machines, anamneses and farm records. This investigation was, actively done from March 1977 to February 1979, The results obtained were summerized as follows; 1. It was found that 446 cows, accounting for 20.48% of 2,179 cows inspected, had supernumerary teats. Among them 53.59% had one, 43.72% had two, 2.47% had three, and 0.22% had four supernumerary teats, respectively. 2. Dry off quarters were found in 158 quarters which turned out to be 1.8% of 8,716 quarters inspected. Among dry off quarters, 62.02% seemed to be caused by mastitis, 30.37% by acquired teat obstructions, and 7.59% by congenital blind teats and glands respectively. 3. Teat sphincter stenosis was found in 154 teats of 50 cows, which represents 1.76% of 8,716 teats and 2.29% of 2,179 cows inspected, respectively. Among 154 teats with teat sphincter stenosis, 138 teats (85.7%) of 33 cows were found to be congenital and revealed highest incidence. 4. Loose sphincter was found in 78 teats of 36 cows, which figure 0.89% of 8,7l6 teats and 1.69% of 2,179 cows inspected, respectively. Among 78 teats with loose sphincter, 52 teats (66.66%) of 13 cows were found to be congenital and revealed highest incidence. 5. Injured teat tip caused by over milking of milk machine, was found in 229 teats of 156 cows, which figure 2.63% of 8,716 teats and 7.15% of 2,179 cows observed, respectively. 6. Other miscellaneous injuries and congenital abnormalities of teats and udders were diagnosed as follows: The teat laceration was found in 34 teats (0.39% of 8,716 teats), fissure of teat skin in 24 teats (0.28% of 8,716 teats), stricture of teat cistern in 21 teats (0.24% of 8,716 teats), teat fistula in 12 teats (0.14% of 8,716 teats), papillomas on testes in 8 teats (0.09% of 8,716 teats). Knothole orifice in 7 teats (0.08% of 8,716 teats), subcutaneous abscess of udder in 5 quarters (0.05% of 8,716 teats), membraneous obstruction of teat cistern in 4 teats (0.05% of 8,716 teats), and congenital short teat in 8 teats (0.09% of 8,716 teats), respectively.

• Korean Journal of Cognitive Science
• /
• v.21 no.2
• /
• pp.309-338
• /
• 2010

In this paper, we studied the brain-computer interface (BCI). BCIs help severely disabled people to control external devices by analyzing their brain signals evoked from motor imageries. The findings in the field of neurophysiology revealed that the power of $\beta$(14-26 Hz) and $\mu$(8-12 Hz) rhythms decreases or increases in synchrony of the underlying neuronal populations in the sensorymotor cortex when people imagine the movement of their body parts. These are called Event-Related Desynchronization / Synchronization (ERD/ERS), respectively. We implemented a BCI-based mouse interface system which enabled subjects to control a computer mouse cursor into four different directions (e.g., up, down, left, and right) by analyzing brain signal patterns online. Tongue, foot, left-hand, and right-hand motor imageries were utilized to stimulate a human brain. We used a non-invasive EEG which records brain's spontaneous electrical activity over a short period of time by placing electrodes on the scalp. Because of the nature of the EEG signals, i.e., low amplitude and vulnerability to artifacts and noise, it is hard to analyze and classify brain signals measured by EEG directly. In order to overcome these obstacles, we applied statistical machine-learning techniques. We could achieve high performance in the classification of four motor imageries by employing Common Spatial Pattern (CSP) and Linear Discriminant Analysis (LDA) which transformed input EEG signals into a new coordinate system making the variances among different motor imagery signals maximized for easy classification. From the inspection of the topographies of the results, we could also confirm ERD/ERS appeared at different brain areas for different motor imageries showing the correspondence with the anatomical and neurophysiological knowledge.

• Fire Science and Engineering
• /
• v.29 no.2
• /
• pp.84-91
• /
• 2015

The purpose of this study is to suggest the reasonable model of the caliber in suction nozzle, the pressure of suction nozzle, and the flow rate about foam system of line proportioner type using in the pumpcar. To test this, the experimental study was accomplished on the ground of the standards for the Performance Certification and Product Inspection of Foam Fire-extinguishing Chemical Mixing Machine. Aqueous Film Forming Foam in 3% and pipe type air foam nozzle with line proportioner FE 40 type were used. Test result showed that the pressure of suction nozzle within the limits between 0.25 MPa and 0.35 MPa was appropriate when the caliber in suction nozzle is 4 mm. Also, the pressure of suction nozzle within the limits between 0.45 MPa and 0.60 MPa was appropriate in the higher pressure than 4 mm when the caliber in suction nozzle is 5 mm.

• Land and Housing Review
• /
• v.8 no.3
• /
• pp.189-200
• /
• 2017

The work breakdown structure and the precedence relations by work activity are very important because they are the basic data for estimating the construction duration in the construction work. However, there is no standard to accurately estimate the construction duration since the size of the school facilities construction is smaller than the general construction work. Therefore, some schools are unable to open in March or September and the delay of the construction duration can cause damage to the students. To solve this problem, this study developed a work breakdown structure of school facilities construction work and analyzed the precedence relations by work activities. The work breakdown structure of the school facilities construction is composed of three steps. The operations corresponding to level 1 and level 2 are as follows. (1) 2 preparatory work categories; preparation period and temporary construction. (2) 17 architectural work categories; temporary construction, foundation & pile work, reinforced concrete work, steel roof work, brick work, plaster work, tile work, stone work, waterproof construction, wood work, interior construction, floor work, metal work, roof work, windows construction, glazing work and paint construction. (3) 7 mechanic and fire work categories; outside trunk line work, plumbing work, air-conditioning equipment work, machine room work, city gas plumbing work, sanitation facilities and inspection & test working. (4) 4 civil work categories; wastewater work, drainage work, pavement work and other work. (5) 1 landscaping work categories; planting work. The work breakdown structure was derived from interviews with experts based on the milestones and detailed statements of existing school facilities. The analysis of precedence relations by school facilities work activity utilized PDM(Precedence Diagramming Method)which does not need a dummy and the relations were applied using FS(Finish to Start), FF(Finish to Finish), SS(Start to Start), SF(Start to Finish). The analysis of this study shows that if one work activity is delayed, the entire construction duration may be delayed because the majority of the works are FS relations. Therefore, it is necessary to use the Lag at the appropriate time to estimate the standard construction duration of the school facility construction. Lag is a term used only in the PDM method and it is used to define the relationship between the predecessor and the successor in creating the network milestone. And it means the delay time applied to the two work activities. The results of this study can reasonably estimate the standard construction duration of school facilities and it will contribute to the quality of the school facilities construction.

• Journal of Biomedical Engineering Research
• /
• v.40 no.5
• /
• pp.215-221
• /
• 2019

The respiratory medical device is a medical device that delivers optimal oxygen or a certain amount of humidification to a patient by delivering artificial respiration to a patient through a machine when the patient has lost the ability to breathe spontaneously. These include respirators for use in chronic obstructive pulmonary disease and anesthesia or emergency situations, and positive airway pressure devices for treating sleep apnea, and as the population of COPD (chronic obstructive pulmonary disease) and elderly people worldwide surge, the market for the respiratory medical devices it is getting bigger. As the demand for both airway pressure devices, there is a problem that the ventilator standard is applied because the reference standard has not been established. Therefore, the boundaries between the items are blurred due to the purpose, intended use, and method of use overlapping similar items in a respiratory medical device. In addition, for both airway pressure devices, there is a problem that the ventilator standard is applied because the reference standard has not been established. Therefore, in this study, we propose clear classification criteria for the respiratory medical devices according to the purpose, intended use, and method of use and provide safety and performance evaluation guidelines for those items to help quality control of the medical devices. And to contribute to the rapid regulating and improvement of public health. This study investigated the safety and performance test methods through the principles of the respiratory medical device, national and international standards, domestic and international licensing status, and related literature surveys. The results of this study are derived from the safety and performance test items in the individual ventilator(ISO 80601-2-72), the International Standard for positive airway pressure device (ISO 80601-2-70), The safety and performance of humidifiers (ISO 80601-2-74) and the safety evaluation items related to home healthcare environment (IEC 60601-1-11), In addition, after reviewing the guidelines drawn up through expert consultation bodies including manufacturers and importers, certified test inspection institutions, academia, etc., the final guidelines were established through revision and supplementation. Therefore, in this study, we propose guidelines for evaluating the safety and performance of the respiratory medical device in accordance with growing technology development.

• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.93-108
• /
• 2023

In manufacturing productivity analysis, understanding the intricate interplay among factors like facility performance, layout design, and workforce allocation within the production line is imperative. This paper introduces a simulation-based methodology tailored to food manufacturing, progressively expanding scenarios to analyze production enhancement. The target system is a food processing plant, encompassing production processes, including warehousing, processing, subdivision, packaging, inspection, loading, and storage. First, we analyze the target system and design a simulation model according to the actual layout arrangement of equipment and workers. Then, we validate the developed model reflecting the real data obtained from the target system, such as the workers' working time and the equipment's processing time. The proposed model aims to identify optimal factor values for productivity gains through incremental scenario comparisons. To this end, three stages of simulation experiments were conducted by extending the equipment and worker models of the subdivision and packaging processes. The simulation experiments have shown that productivity depends on the placement of skilled workers and the performance of the packaging machine. The proposed method in this study will offer combinations of factors for the specific production requirements and support optimal decision-making in the real-world field.