• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.185-197
• /
• 2022

Recently, deep learning networks with high performance for object recognition are emerging. In the case of object recognition using deep learning, it is important to build a training data set to improve performance. To build a data set, we need to collect and label the images. This process requires a lot of time and manpower. For this reason, open data sets are used. However, there are objects that do not have large open data sets. One of them is data required for license plate detection and recognition. Therefore, in this paper, we propose an artificial license plate generator system that can create large data sets by minimizing images. In addition, the detection rate according to the artificial license plate arrangement structure was analyzed. As a result of the analysis, the best layout structure was FVC_III and B, and the most suitable network was D2Det. Although the artificial data set performance was 2-3% lower than that of the actual data set, the time to build the artificial data was about 11 times faster than the time to build the actual data set, proving that it is a time-efficient data set building system.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.2
• /
• pp.385-391
• /
• 2022

Quality evaluation of beef carcasses is an important issue in the livestock industry. Recently, through the AI monitor system based on artificial intelligence, the quality manager can receive help in making accurate decisions based on the analysis of beef carcass images or result information. This artificial intelligence dataset is an important factor in judging performance. Existing datasets may have different surface orientation or resolution. In this paper, we proposed a two-stage classification model that can efficiently manage the grades of beef carcass image using deep learning. And to overcome the problem of the various conditions of the image, a new dataset of 1,300 images was constructed. The recognition rate of deep network for 5-grade classification using the new dataset was 72.5%. Two-stage evaluation is a method to increase reliability by taking advantage of the large difference between grades 1++, 1+, and grades 1 and 2 and 3. With two experiments using the proposed two stage model, the recognition rates of 73.7% and 77.2% were obtained. As this, The proposed method will be an efficient method if we have a dataset with 100% recognition rate in the first stage.

• Journal of Platform Technology
• /
• v.11 no.2
• /
• pp.26-38
• /
• 2023

This paper is a study on a transport robot capable of autonomously driving to a destination using a QR code in an indoor environment. The transport robot was designed and manufactured by attaching a lidar sensor so that the robot can maintain a certain distance during movement by detecting the distance between the camera for recognizing the QR code and the left and right walls. For the location information of the delivery robot, the QR code image was enlarged with Lanczos resampling interpolation, then binarized with Otsu Algorithm, and detection and analysis were performed using the Zbar library. The QR code recognition experiment was performed while changing the size of the QR code and the traveling speed of the transport robot while the camera position of the transport robot and the height of the QR code were fixed at 192cm. When the QR code size was 9cm × 9cm The recognition rate was 99.7% and almost 100% when the traveling speed of the transport robot was less than about 0.5m/s. Based on the QR code recognition rate, an experiment was conducted on the case where the destination is only going straight and the destination is going straight and turning in the absence of obstacles for autonomous driving to the destination. When the destination was only going straight, it was possible to reach the destination quickly because there was little need for position correction. However, when the destination included a turn, the time to arrive at the destination was relatively delayed due to the need for position correction. As a result of the experiment, it was found that the delivery robot arrived at the destination relatively accurately, although a slight positional error occurred while driving, and the applicability of the QR code-based destination self-driving delivery robot was confirmed.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.9
• /
• pp.11-19
• /
• 2009

A RAM-based Neural Net(RBNN) which has multi-discriminators is more effective than RBNN with a discriminator. Experience Sensitive Cumulative Neural Network and 3-D Neuro System(3DNS) that accumulate the features point improved the performance of BNN, which were enabled to train additional and repeated patterns and extract a generalized pattern. In recognition process of Neural Net with multi-discriminator, the selection of class was decided by the value of MRD which calculates the accumulated sum of each class. But they had a saturation problem of its memory cells caused by learning volume increment. Therefore, the decision of MRD has a low performance because recognition rate is decreased by saturation. In this paper, we propose the method which improve the MRD ability. The method consists of the optimum MRD and the matching ratio prototype to generalized image, the cumulative filter ratio, the gap of prototype response MRD. We experimented the performance using NIST database of NIST without preprocessor, and compared this model with 3DNS. The proposed MRD method has more performance of recognition rate and more stable system for distortion of input pattern than 3DNS.

• Journal of Korean Society for Atmospheric Environment
• /
• v.29 no.6
• /
• pp.811-817
• /
• 2013

A two-stage bioreactor system using sulfur-oxidizing bacteria was studied to abate high strength hydrogen sulfide ($H_2S$) from biogas. The two-stage bioreactor consisted of a $H_2S$ absorption column (0.5 L) and a microbial oxidation column (1 L) in series, and the liquid medium was continuously recirculated through the columns. The objectives of this study were to determine the feasibility of the bioreactor for biogas desulfurization and to investigate the effect of the medium circulation rate on the system performance. An averaged concentration of $H_2S$ introduced to the bioreactor was 530 ppm, corresponding to an overall loading rate of $44.4g/m^3/hr$. During the initial 20 days period at the medium recirculation rate of 8 reactor volumes per hour (12 L/hr), the dissolved oxygen (DO) concentration in the oxidation column was 6 mg/L, while the DO in the absorption column was 0.5 mg/L showing that the oxygen contents of the biogas stream was not altered. Because of the biological oxidation of $H_2S$ in the oxidation column, the sulfate concentration increased from 200 mg/L to 5,600 mg/L in the liquid medium. The removal efficiency of $H_2S$ was greater than 99% in the initial operation period. After the initial period, the medium recirculation rate between the two columns was stepwise changed eight times from 1.0 to 40 vol/hr (1.5~60 L/hr). At the recirculation rate of faster than 4 vol/hr, the $H_2S$ removal efficiencies were found to be high, but the efficiency declined at the lower recirculation rates than the threshold.

• The Journal of the Korea Contents Association
• /
• v.13 no.2
• /
• pp.431-439
• /
• 2013

The purpose of this study is to analyze the apartment investment performance including the risk and to verify the presence or absence of regional characteristics. This study made an analysis on the apartment investment performance by dividing it into long and short-term basis. Data collection period is 10 years from 2002 to 2012 and target area includes Gangnam and Gangbuk (southern and northern area of Seoul) and 6 metropolitan cities. For evaluating the investment performance, this study used the earning rate of 5 year 1st class national housing bond as the risk-free rate of return and 1~2 year interest rate of fixed deposit for calculating lease profit. The results of study are as follows, Treynor's Index was used in long investment performance evaluation because of regional characters non-existing in Seoul and Incheon whereas Jensen's Index was used in evaluating because of regional characters existing in 5 metropolitan cities. And Jensen's Index was used in short-term evaluation of all districts as existing regional characters in all districts. Short-term performance considering regional characteristics yielded different results of simple evaluation. Therefore, in case of simple rate of return to evaluate the performance, the recognition of that can be distorted.

• Journal of Korean Academy of Nursing
• /
• v.37 no.2
• /
• pp.185-191
• /
• 2007

Purpose. The purpose of this study was to develop and evaluate an error reporting promoting program(ERPP) to systematically reduce the incidence rate of nursing errors in operating room. Methods. A non-equivalent control group non-synchronized design was used. Twenty-six operating room nurses who were in one university hospital in Busan participated in this study. They were stratified into four groups according to their operating room experience and were allocated to the experimental and control groups using a matching method. Mann-Whitney U Test was used to analyze the differences pre and post incidence rates of nursing errors between the two groups. Results. The incidence rate of nursing errors decreased significantly in the experimental group compared to the pre-test score from 28.4% to 15.7%. The incidence rate by domains, it decreased significantly in the 3 domains-"compliance of aseptic technique", "management of document", "environmental management" in the experimental group while it decreased in the control group which was applied ordinary error-reporting method. Conclusion. Error-reporting system can make possible to hold the errors in common and to learn from them. ERPP was effective to reduce the errors of recognition-related nursing activities. For the wake of more effective error-prevention, we will be better to apply effort of risk management along the whole health care system with this program.

• Journal of the Korean Society of Food Culture
• /
• v.16 no.5
• /
• pp.483-491
• /
• 2001

Traditional Korean beverage can be divided into Jang, Gahl Soo, Mi Su, Soo Jung Gwa, Shick Hae, Tahng, Hwa Chae, Sook Su, and Tea according to ingredients and how it is proccessed. The purpose of this study was to investigate the Korean beverage percetpion and to analyze the factors (sociodemographic factors and life-style related factors) which influence percetpion of Korean beverage. Questionnaries were hand delivered to 2,200 subject residing in Seoul and 1,884 questionnaris were collected : resulting in 84% response rate. Statistical data analysis was completed using SAS Package program for the analysis of covariance(ANOCOVA).The results are as follows: (a) Survey on Korean beverage perception showed that the recognition rates of ShickHae(58.4%), Cition Tea(53.5%), Sung Nung(48.7%) and Soo Jung Gwa(40.8%) were high, whereas those for Tahng, Jang, and Gahl Soo were low.(b) About 40% of respondents performing 4 kinds of Korean traditional ceremony a year The percentage that reported they purchased Korean beverages was 44.0%, higher than the 38.5% that answered they made Korean beverage at home.(c) In analyzing the factors which influence beverage perception, the sociodemographic factors variously influenced perception rate depending on beverage. Age and sex had influenced on perception rate of Shick Hae and Donggulre Tea. Income level influenced on the perception rate of Sung Nung and Citron Tea. Sociodemograhpic factors like senior over 50s, female and extended family size had positive influence on the perception rate.

• Women's Health Nursing
• /
• v.20 no.3
• /
• pp.185-194
• /
• 2014

Purpose: The aim of this study was to assess health-related behavior of pregnant women and breastfeeding mothers by investigating relevant risk factors. Methods: Data of 10,396 women (age 19 to 49 years) from the Korea National Health and Nutrition Examination Survey report from 2007 to 2012 was used to analyze factors associated with health-related behavior. The subjects were divided into pregnant women; breastfeeding mothers; and non-pregnant women. Bottle feeding mothers were excluded. Results: Current smoking rate including self-reported smoker and/or positive cotinine urine test were lower for pregnant or breast-feeding group than non-pregnant group. Heavy-drinking was not different among groups while monthly drinking rate was higher in non-pregnant group. Rate of stress recognition was lower in pregnant and breast-feeding group than non-pregnant group. Rate of experience for depressive symptoms and rate of suicidal ideation were not different among groups. Conclusion: Pregnant women and breast-feeding mothers maintain a good pattern of health- related behavior compared to non-pregnant women. However, substantial proportion of pregnant women and breast-feeding mothers continue to drink and smoke. This shows the need for a plan that will modify health-related behavior.

• Korean Journal of Community Nutrition
• /
• v.5 no.4
• /
• pp.586-597
• /
• 2000

The nutrition knowledge and food attitude of obese children were assessed and compared with their normal children counterparts to provide information for nutrition education programs. One hundred forty six obese children and 92 normal children from the fourth to sixth grade in Bucheon and Anyang elementary schools of Kyeong-gi Province were selected for the study. A multiple choice questionnaire, including 12 items of general nutrition knowledge and 13 items of weight control, were used to test the nutrition knowledge of children. The results of this study are as follows : 1) 57.5% of male and 40.9% of female obese children had experience with weight control, but the rate of correct answers on the nutrition knowledge test ranged from 53% to 58%, which does not show any significant difference between the two groups. The rate of correct answers on items conrerning 'general nutrition knowledge' and 'nutrition knowledge for weight control' did not show any significant difference among the two groups. 2) Obese male students showed a higher rate of correct answers(59.2%) on items of 'the proper food selection for obese children', compared with their counterparts and also obese female students showed a higher rate of correct answers(88.6%) on 'physical exercise', compared with their counterparts. 3) The rate of correct answers on nutrition knowledge of 'basic food groups', 'the functions of iron and vitamins', 'the concept of energy', and 'the principle of weight change' were lower than 40%. 4) The obese children frequently did not have breakfast, overate during lunch in many cases, and had low recognition on knowledge that was necessary to weight control. 5) Only 30.9% and 22.7% of male and female obese children replied that they would participate in weight control programs. However, 53.6% of males and 68.2% of females did not show any concern in participating the programs. From these results, it was suggested that it is necessary to motivate the obese to participate in weight-control program. When developing nutrition education programs for the obese, the contents of the questions that showed a low correct answering rates should be emphasized.