• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.1009-1018
• /
• 2022

Objective: This study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment. Materials and Methods: This retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI). Results: Of 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity. Conclusion: This study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.4
• /
• pp.437-444
• /
• 2020

A lunar rover's optical camera is used to provide navigation and terrain information in an exploration zone. However, due to the scant presence of atmosphere, the Moon has homogeneous terrain with dark soil. Also, in extreme environments, the rover has limited data storage with low computation capability. Thus, for successful exploration, it is required to examine feature detection and matching methods which are robust to lunar terrain and environmental characteristics. In this research, SIFT, SURF, BRISK, ORB, and AKAZE are comparatively analyzed with lunar terrain images from a lunar rover. Experimental results show that SIFT and AKAZE are most robust for lunar terrain characteristics. AKAZE detects less quantity of feature points than SIFT, but feature points are detected and matched with high precision and the least computational cost. AKAZE is adequate for fast and accurate navigation information. Although SIFT has the highest computational cost, the largest quantity of feature points are stably detected and matched. The rover periodically sends terrain images to Earth. Thus, SIFT is suitable for global 3D terrain map construction in that a large amount of terrain images can be processed on Earth. Study results are expected to provide a guideline to utilize feature detection and matching methods for future lunar exploration rovers.

• Journal of Korea Water Resources Association
• /
• v.32 no.1
• /
• pp.71-81
• /
• 1999

The objective of this study is to develop a model which can design an optimal pipe network system of least cost while satisfying all the design constraints including hydraulic constraints using a genetic algorithm technique. Hydraulic constraints interfaced with the simulation program(KYPIPE) checked feasible solution region. Genetic algorithm(GA) technique is a relatively new optimization technique. The GA is known as a very powerful search and optimization technique especially when solving nonlinear programming problems. The model developed in this study selects optimal pipe diameters in the form of commercial discrete sizes using the pipe diameters and the pumping powers as decision variables. The model not only determines the optimal diameters and pumping powers of pipe network system but also satisfies the discharge and pressure requirements at demanding nodes. The model has been applied to an imaginary and an existing pipe network systems. One system is adopted from journal papers which has been used as an example network by many other researchers. Comparison of the results shows compatibility of the model developed in this study. The model is also applied to a system in Goyang city in order to check the model applicability to finding of optimal pumping powers. It has been found that the developed model can be successfully applied to optimal design of pipe network systems in a relatively simple manner.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.3
• /
• pp.249-255
• /
• 2017

The finger vein recognition technology is a method to acquire a finger vein image by illuminating infrared light to the finger and to authenticate a person through processes such as feature extraction and matching. In order to recognize a finger vein, a 2D mask-based two-dimensional convolution method can be used to detect a finger edge but it takes too much computation time when it is applied to a low cost micro-processor or micro-controller. To solve this problem and improve the recognition rate, this study proposed an extraction method for the region of interest based on virtual core points and moving average filtering based on the threshold and absolute value of difference between pixels without using 2D convolution and 2D masks. To evaluate the performance of the proposed method, 600 finger vein images were used to compare the edge extraction speed and accuracy of ROI extraction between the proposed method and existing methods. The comparison result showed that a processing speed of the proposed method was at least twice faster than those of the existing methods and the accuracy of ROI extraction was 6% higher than those of the existing methods. From the results, the proposed method is expected to have high processing speed and high recognition rate when it is applied to inexpensive microprocessors.

• The Korean Journal of Physiology
• /
• v.5 no.2
• /
• pp.29-40
• /
• 1971

Oxygen consumption, pulmonary ventilation, heart rate, and breathing frequency were measured on 8 men walking on a treadmill carrying load of 9 kg on hand, back, or head. Besides measurements were made on subjects carrying loads of 2.6 kg each on both feet. The speed of level walking was 4, 5, and 5.5km/hr and a fixed speed off km/hr with grades of 0, 3, 6, and 9%. Comparisons were made between free walking without load and walking with various types of loads. The following results were obtained. 1. In level or uphill walking the changes in oxygen consumption, pulmonary ventilation, breathing frequency and heart rate were smallest in back load walking, and largest in hand load walking. The method of back load was most efficient and hand load was the least efficient. The energy cost in head load walking was smaller than that of in hand load walking. It was assumed that foot load costed more energy than hand load. 2. In level walking the measured parameters increased abruptly at the speed of 5.5 km/hr. Oxygen consumption in a free walking at 4 km/hr was 11.4ml/kg b.wt., and 13.1 ml/kg b.wt. 5.5 km/hr, and in a hand load walking at 4 km/hr was 13.9, and 18.8 ml/kg b. wt. at 5.5 km/hr. 3. In uphill walking oxygen consumption and other parameters increased abruptly at the grade of 6%. Oxygen consumption at 4 km/hr and 0% grade was 11.4 ml/kg b. wt., 13.6 at 6% grade, and 16.21/kg b. wt. at 9% grade in a free walking. In back load walking oxygen consumption at 4km/hr and 0% grade was 12.3 ml/kg b.wt.,14.9 at 6% grade, and 18.7 ml/kg b.wt. In hand load walking the oxygen consumption was the greatest, namely, 13.9 at 0% grade, 17.9 at 6%, and 20.0 ml/kg b. wt. at 9% grade. 4. Both in level and uphill walking the changes in pulmonary ventilation and heart rate paralleled with oxygen consumption. 5. The changes in heart rate and breathing frequency in hand load were characteristic. Both in level and uphill walk breathing frequency increased to 30 per minute when a load was held on hand and showed a small increase as the exercise became severe. In the other method of load carrying the Peak value of breathing frequency was less than 30 Per minute. Heart rate showed 106 beats/minute even at a speed of 4 km/hr when a load was held on hand, whereas, heart rate was between, 53 and 100 beats/minute in the other types of load carriage. 6. Number of strides per minute in level walking increased as the speed increased. At the speed floater than 5 km/hr number of strides per minute of load carrying walk was greater than that of free walking. In uphill walk number of strides per minute decreased as the grade increased. Number of strides in hand load walk was greatest and back load walk showed the same number of strides as the free walk.

• Journal of Korean Society of Water and Wastewater
• /
• v.13 no.2
• /
• pp.55-65
• /
• 1999

AF(anaerobic filter)/BAF(biological aerated filter) system and UASB(upflow anaerobic sludge blanket)/BAF system, of which system effluents were recirculated to the anaerobic reactors in each system, were operated in order to investigate the performance in simultaneous removal of organics and nitrogen in high-strength dairy wastewater. Advanced anaerobic treatment processes of AF and UASB were evaluated on applicability as pre-denitrification reactors, and BAF was also evaluated on the performance in oxidizing the remaining organics and ammonia nitrogen. At system HRTs of 4.0 to 4.5 days and recirculation ratios of one to three, the AF/BAF system could achieve more than 99% of organics removals and 64 to 78% of total nitrogen removals depending upon the recirculation ratio. Although the UASB/BAF system also showed more than 99% of organics removals, total nitrogen removals in the UASB/BAF system were 53 to 66% which are lower than those in the AF/BAF system at the corresponding recirculation ratios. Optimum recirculation ratios considering simultaneous removal of organics and nitrogen and cost-effectiveness, were in the range of two to three. The upflow AF packed with crossflow module media, as a primary treatment of the anaerobic reactor/BAF system, showed better performances in denitrification, SS removals, and gas production than the UASB. Higher loading rate of suspended solids from the UASB increased the backwashing times in the following BAF. Especially, at a recirculation ratio of three in the UASB/BAF system, the increase in head loss due to clogging in the BAF caused frequent backwashing, at least once d day. The BAF showed the high nitrification efficiency of average 99.2% and organics removals more than 90% at organics loading rate less than $1.4KgCOD/m^3/d$ and $COD/NH_3-N$ ratio less than 6.4. It was proved that the simplified anaerobic reactor/BAF system could maximize the organics removal and achieve high nitrogen removal efficiencies through recirculation of system effluents to the anaerobic reactor. The AF/BAF system can, especially, be a cost effective and competitive alternative for the simultaneous removal of organics ana nitrogen from wastewaters.

• Journal of Society of Preventive Korean Medicine
• /
• v.21 no.3
• /
• pp.1-10
• /
• 2017

Objectives : The purpose of this study is to investigate the practice patterns of traditional Korean medicine (TKM) doctors and the acceptance of payment model in order to develop a new TKM health insurance payment model linked with TKM clinical practice guidelines (CPGs). Methods : Lumbar herniated intervertebral disc (HIVD) and idiopathic facial palsy (IFP) were selected as a test diseases to develop a new TKM payment model. The level of benefit coverage in the National Health Insurance (NHI) was designed. The survey asked 228 TKM doctors about their practice patterns in HIVD and IFP patients and acceptance of new payment model. Results : Mean of medical cost for treatment of HIVD was 441,000 KW, mean of treatment period ranged from 4.9 to 17.5 weeks, and mean of number of treatment ranged from 14.6 to 50.4 HIVD patients. In the case of IFP, mean of medical cost for treatment of IFP was 468,000 KW, mean of treatment period was at least 4.2 and up to 15.9 weeks and mean of number of treatment ranged from 14.2 to 52 IFP patients. Conclusions : Current study suggests that mixed payment model of per-visit and episode-based model seem to be proper. The model 1 bundles both items which were covered and not covered by NHI in a rational way. The model 2 is based on the development and application of critical pathway. Lastly, model 3 suggests bundling of items covered by current NHI. Acceptance of TKM doctors is expected to be highest in the model 3.

• The Korean Journal of Financial Management
• /
• v.22 no.1
• /
• pp.1-36
• /
• 2005

In this study, we analyzed determinant factors of leverage ratio and debt maturity for Korean firms in the simultaneous equation system using 2SLS (two stage least square) method under assumption that two variables are jointly determined in the capital structure decision. As a result of the analysis, we found that leverage ratio and debt maturity are positively related. Also, as for determinant factors of debt maturity, agency cost hypothesis, asset maturity matching hypothesis, signalling and liquidity risk hypothesis are all generally supported, and further leverage ratio are significantly positively related with firm size, but negatively related with default risk. However, when we divided samples into groups according to bank debt level and Chaebul affiliation, with contrast to existing study which worked on similar issues with OLS, we found no evidence supporting the argument that the information asymmetry problem is less severe in firms with more bank debt, whereas information asymmetry and financial constraint problems are more severe in non-Chaebul affiliated firms.

• Journal of Families and Better Life
• /
• v.33 no.5
• /
• pp.1-24
• /
• 2015

The purpose of this study was to investigate the effects of Engel coefficient, Angel coefficient and Schwabe index influencing Household head's life satisfaction. For this study, the data from the 8th analysis of the 2013 Korea Welfare Panel Survey conducted by Korea Institute for Health and Social Affairs were used. For the sample, 903 male Household heads with children under the age of 18, were selected. For statistical analysis, SPSS program (Ver. 21.0) was used. And for statistical methods, frequency and percentile, mean and standard deviation, Pearson's correlation, one way analysis of variance, Duncan's multiple range tests, multiple regression analysis were used. The findings are as follows. First, as a results of analyzing the food costs, education costs and housing costs depending on Income Quintile, the food costs and education costs in the 5th Income Quintile compared with other Income Quintile, were highest. Also, the highest housing cost was in the 2nd Income Quintile, while the least housing cost was in the 1st Income Quintile. Second, by analyzing the differences of Engel coefficient, Angel coefficient and Schwabe index according to Income Quintile, the results show that Engel coefficient and Schwabe index decreases as Income Quintile increases, and Angel coefficient increases as Income Quintile becomes higher. Third, the level of HH's life satisfaction according to Income Quintile, 1st Income Quintile, 2nd Income Quintile, 4th Income Quintile, 3rd Income Quintile, 5th Income Quintile in order, increased. Fourth, as the result of analyzing the influence of Variables related to household and demographics about Engel coefficient, Angel coefficient and Schwabe index, it was shown that the variables effecting Engel coefficient, Angel coefficient, and Schwabe index are age, occupations, Number of workers, House ownership, Income Quintile. Fifth, As a result of analyzing the Variables effecting life satisfaction, especially while Schwabe index is not that significant, Engel coefficient and Angel coefficient are shown to have a significant influence. Therefore, the influence of Food costs and education costs can be confirmed.

• The Journal of the Korea Contents Association
• /
• v.9 no.9
• /
• pp.31-40
• /
• 2009

What are important in wireless sensor networks are reliable data transmission, energy efficiency of each node, and the maximization of network life through the distribution of load among the nodes. The present study proposed DSPR, a dynamic unique path routing machanism that considered these requirements in wireless sensor networks. In DSPR, data is transmitted through a dynamic unique path, which has the least cost calculated with the number of hops from each node to the sink, and the average remaining energy. At that time, each node monitors its transmission process and if a node detects route damage it changes the route dynamically, referring to the cost table, and by doing so, it enhances the reliability of the network and distributes energy consumption evenly among the nodes. In addition, when the network topology is changed, only the part related to the change is restructured dynamically instead of restructuring the entire network, and the life of the network is extended by inhibiting unnecessary energy consumption in each node as much as possible. In the results of our experiment, the proposed DSPR increased network life by minimizing energy consumption of the nodes and improved the reliability and energy efficiency of the network.