• Korean Journal of Radiology
• /
• v.22 no.6
• /
• pp.983-993
• /
• 2021

Objective: To investigate the image quality of ultralow-dose CT (ULDCT) of the chest reconstructed using a cycle-consistent generative adversarial network (CycleGAN)-based deep learning method in the evaluation of pulmonary tuberculosis. Materials and Methods: Between June 2019 and November 2019, 103 patients (mean age, 40.8 ± 13.6 years; 61 men and 42 women) with pulmonary tuberculosis were prospectively enrolled to undergo standard-dose CT (120 kVp with automated exposure control), followed immediately by ULDCT (80 kVp and 10 mAs). The images of the two successive scans were used to train the CycleGAN framework for image-to-image translation. The denoising efficacy of the CycleGAN algorithm was compared with that of hybrid and model-based iterative reconstruction. Repeated-measures analysis of variance and Wilcoxon signed-rank test were performed to compare the objective measurements and the subjective image quality scores, respectively. Results: With the optimized CycleGAN denoising model, using the ULDCT images as input, the peak signal-to-noise ratio and structural similarity index improved by 2.0 dB and 0.21, respectively. The CycleGAN-generated denoised ULDCT images typically provided satisfactory image quality for optimal visibility of anatomic structures and pathological findings, with a lower level of image noise (mean ± standard deviation [SD], 19.5 ± 3.0 Hounsfield unit [HU]) than that of the hybrid (66.3 ± 10.5 HU, p < 0.001) and a similar noise level to model-based iterative reconstruction (19.6 ± 2.6 HU, p > 0.908). The CycleGAN-generated images showed the highest contrast-to-noise ratios for the pulmonary lesions, followed by the model-based and hybrid iterative reconstruction. The mean effective radiation dose of ULDCT was 0.12 mSv with a mean 93.9% reduction compared to standard-dose CT. Conclusion: The optimized CycleGAN technique may allow the synthesis of diagnostically acceptable images from ULDCT of the chest for the evaluation of pulmonary tuberculosis.

• Journal of The Korean Association For Science Education
• /
• v.29 no.5
• /
• pp.477-491
• /
• 2009

The purpose of this study is to analyze activities of mentally retarded students studying science within inclusive classes from the aspect of activity sharing to investigate ways of improving their involvement in the tasks. For this study, three mentally retarded students and their peer group in inclusive classes were observed and videotaped for 12 science class sessions about forces and waves. There were many cases in which task involvement of mentally retarded students changed according to three degrees of their activity sharing: well-synchronized, delayed and estranged. When degrees of activity sharing were estranged or delayed, task involvement of the mentally retarded students faded from activeness to passiveness. When the degree of activity sharing was well-synchronized, the mentally retarded students showed interest in learning and were able to participate in science class more actively. Different patterns of activity sharing of mentally retarded students between teacher-centered activities and student-centered activities were observed. In most cases of teacher-centered activities, the monotonous pace could deprive the mentally retarded students of their chance to catch up. As a result, their delayed degrees of activity sharing were faded into estranged degrees. In many cases of student-centered activities, various pacing according to the groups or students could provide mentally retarded students with a chance to catch up, so they could be well-synchronized. In one case of teacher-centered activity, the mentally retarded students were well-synchronized with the teacher's repeated explanations and well-matched illustrations on the blackboard and textbooks. In some cases of student-centered activities, students were well-synchronized with positive relations with and appropriate intervention by other students. In conclusion, various approaches to encourage activity sharing of mentally retarded students with normal ones should be pursued to improve task involvement and academic achievement of mentally retarded students.

• The Korean Journal of Nuclear Medicine
• /
• v.37 no.2
• /
• pp.73-82
• /
• 2003

Objectives: A new software (Cardiac SPECT Analyzer: CSA) was developed for quantification of volumes and election fraction on gated myocardial SPECT. Volumes and ejection fraction by CSA were validated by comparing with those quantified by Quantitative Gated SPECT (QGS) software. Materials and Methods: Gated myocardial SPECT was peformed in 40 patients with ejection fraction from 15% to 85%. In 26 patients, gated myocardial SPECT was acquired again with the patients in situ. A cylinder model was used to eliminate noise semi-automatically and profile data was extracted using Gaussian fitting after smoothing. The boundary points of endo- and epicardium were found using an iterative learning algorithm. Enddiastolic (EDV) and endsystolic volumes (ESV) and election fraction (EF) were calculated. These values were compared with those calculated by QGS and the same gated SPECT data was repeatedly quantified by CSA and variation of the values on sequential measurements of the same patients on the repeated acquisition. Results: From the 40 patient data, EF, EDV and ESV by CSA were correlated with those by QGS with the correlation coefficients of 0.97, 0.92, 0.96. Two standard deviation (SD) of EF on Bland Altman plot was 10.1%. Repeated measurements of EF, EDV, and ESV by CSA were correlated with each other with the coefficients of 0.96, 0.99, and 0.99 for EF, EDV and ESV respectively. On repeated acquisition, reproducibility was also excellent with correlation coefficients of 0.89, 0.97, 0.98, and coefficient of variation of 8.2%, 5.4mL, 8.5mL and 2SD of 10.6%, 21.2mL, and 16.4mL on Bland Altman plot for EF, EDV and ESV. Conclusion: We developed the software of CSA for quantification of volumes and ejection fraction on gated myocardial SPECT. Volumes and ejection fraction quantified using this software was found valid for its correctness and precision.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.151-171
• /
• 2015

This study examined the concepts of the Internet of Things(IoT), the major issue and IoT trend in the domestic and international market. also reviewed the advent of IoT era which caused a 'Paradigm Shift'. This study proposed a solution for the appropriate corresponding strategy in terms of Enterprise. Global competition began in the IoT market. So, Businesses to be competitive and responsive, the government's efforts, as well as the efforts of companies themselves is needed. In particular, in order to cope with the dynamic environment appropriately, faster and more efficient strategy is required. In other words, proposed a management strategy that can respond the IoT competitive era on tipping point through the vision of paradigm shift. We forecasted and proposed the emergence of paradigm shift through a comparative analysis of past management paradigm and IoT management paradigm as follow; I) Knowledge & learning oriented management, II) Technology & innovation oriented management, III) Demand driven management, IV) Global collaboration management. The Knowledge & learning oriented management paradigm is expected to be a new management paradigm due to the development of IT technology development and information processing technology. In addition to the rapid development such as IT infrastructure and processing of data, storage, knowledge sharing and learning has become more important. Currently Hardware-oriented management paradigm will be changed to the software-oriented paradigm. In particular, the software and platform market is a key component of the IoT ecosystem, has been estimated to be led by Technology & innovation oriented management. In 2011, Gartner announced the concept of "Demand-Driven Value Networks(DDVN)", DDVN emphasizes value of the whole of the network. Therefore, Demand driven management paradigm is creating demand for advanced process, not the process corresponding to the demand simply. Global collaboration management paradigm create the value creation through the fusion between technology, between countries, between industries. In particular, cooperation between enterprises that has financial resources and brand power and venture companies with creative ideas and technical will generate positive synergies. Through this, The large enterprises and small companies that can be win-win environment would be built. Cope with the a paradigm shift and to establish a management strategy of Enterprise process, this study utilized the 'RTE cyclone model' which proposed by Gartner. RTE concept consists of three stages, Lead, Operate, Manage. The Lead stage is utilizing capital to strengthen the business competitiveness. This stages has the goal of linking to external stimuli strategy development, also Execute the business strategy of the company for capital and investment activities and environmental changes. Manege stage is to respond appropriately to threats and internalize the goals of the enterprise. Operate stage proceeds to action for increasing the efficiency of the services across the enterprise, also achieve the integration and simplification of the process, with real-time data capture. RTE(Real Time Enterprise) concept has the value for practical use with the management strategy. Appropriately applied in this study, we propose a 'IoT-RTE Cyclone model' which emphasizes the agility of the enterprise. In addition, based on the real-time monitoring, analysis, act through IT and IoT technology. 'IoT-RTE Cyclone model' that could integrate the business processes of the enterprise each sector and support the overall service. therefore the model be used as an effective response strategy for Enterprise. In particular, IoT-RTE Cyclone Model is to respond to external events, waste elements are removed according to the process is repeated. Therefore, it is possible to model the operation of the process more efficient and agile. This IoT-RTE Cyclone Model can be used as an effective response strategy of the enterprise in terms of IoT era of rapidly changing because it supports the overall service of the enterprise. When this model leverages a collaborative system among enterprises it expects breakthrough cost savings through competitiveness, global lead time, minimizing duplication.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.7
• /
• pp.1216-1221
• /
• 2022

Ships tend to be larger to increase the efficiency of cargo transportation. Larger ships lead to increased travel time for ship workers, increased work intensity, and reduced work efficiency. Problems such as increased work intensity are reducing the influx of young people into labor, along with the phenomenon of avoidance of high intensity labor by the younger generation. In addition, the rapid aging of the population and decrease in the young labor force aggravate the labor shortage problem in the maritime industry. To overcome this, the maritime industry has recently introduced technologies such as an intelligent production design platform and a smart production operation management system, and a smart autonomous logistics system in one of these technologies. The smart autonomous logistics system is a technology that delivers various goods using intelligent mobile robots, and enables the robot to drive itself by using sensors such as lidar and camera. Therefore, in this paper, it was checked whether the mobile robot could autonomously drive to the stop sign by detecting the passage way of the ship deck. The autonomous driving was performed by detecting the passage way of the ship deck through the camera mounted on the mobile robot based on the data learned through Nvidia's End-to-end learning. The mobile robot was stopped by checking the stop sign using SSD MobileNetV2. The experiment was repeated five times in which the mobile robot autonomously drives to the stop sign without deviation from the ship deck passage way at a distance of about 70m. As a result of the experiment, it was confirmed that the mobile robot was driven without deviation from passage way. If the smart autonomous logistics system to which this result is applied is used in the marine industry, it is thought that the stability, reduction of labor force, and work efficiency will be improved when workers work.

• Journal of Korean society of Dental Hygiene
• /
• v.10 no.2
• /
• pp.345-359
• /
• 2010

Objectives : The purpose of this study was to correlation between the index of dental caries in primary teeth and the habits of diet and snack which are expected to influence on the index. The subjects of this study were 165 parents of the children who visited a pediatric dental hospital located in Gyeong-gi do from Jun. 15th to Sep. 26th, 2009, and the self-report questionnaire survey was performed. Methods : A questionnaire used in a previous study was revised and completed for this study and it consisted of 15 items on general characteristic, nine items on dietary habit, and five items on snack intake habit. The collected data was analyzed using SPSS program and findings are as follows Results : 1. The index of dental caries in primary teeth by ages was that children of four years old has 4~5 with 27.5%, children of five years old has 2~3 and 4~5 with 33.3% and children of six years old has 1 and 8~9 with 25.6%, showing a statistically significant(${\chi}^2$=37.72, p<.01). 2. The frequency of brushing teeth was found to have statistically significant negative correlation with the number of primary teeth with dental caries (${\chi}^2$=61.20, p<.001). 3. The frequency of taking snack was found to have statistically significant positive correlation with the number of primary teeth with dental caries (${\chi}^2$=51.42, p<.001). 4. The desirability of dietary habit was found to have statistically significant negative correlation with the number of primary teeth with dental caries (${\chi}^2$=36.51, p<.001). 5. The frequency of taking biscuit was found to have statistically significant positive correlation with the number of primary teeth with dental caries (${\chi}^2$=67.74, p<.001). 6. The frequency of taking bread was found to have statistically significant positive correlation with the number of primary teeth with dental caries (${\chi}^2$=29.63, p<.01). 7. The frequency of taking caramel and candy was found to have statistically significant positive correlation with the number of primary teeth with dental caries (${\chi}^2$=38.85, p<.001). 8. The frequency of taking soft drinks was found to have statistically significant positive correlation with the number of primary teeth with dental caries (${\chi}^2$=52.92, p<.001). 9. The frequency of taking ice-creams was found to have statistically significant positive correlation with the number of primary teeth with dental caries (${\chi}^2$=75.07, p<.001). Conclusions : Those findings show that the children with undesirable dietary habit and higher frequency of taking snack have higher index of dental caries in primary teeth, therefore, it is considered that the regular brushing teeth and establishment of desirable dietary habit are very important for keeping health oral cavity. It is recommended that the continuous concern and repeated learning are needed in house and group of rearing infants so that the children take foods of fruits which have function of self-purification than the food of carbohydrates which has high adhesion and level of sweetness.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.2
• /
• pp.121-127
• /
• 2015

A reduction of motor performance due to brain disorders can be screened by evaluating force tracking capabilities (FTCs). Existing studies have examined FTCs mainly using simple sinusoidal waves, of which repeated profiles have a critical limitation due to a learning effect in force tracking. The present study examined the effects of personal factors (age and gender) and sinusoidal wave factors (central force and complexity) on FTCs of healthy adults using composite sinusoidal wave profiles (CSWPs). FTCs were measured using Finger $Touch^{TM}$ for 30 seconds and quantified in terms of time within the target range (TWR, accuracy measure) and relative RMSE (RRMSE, variability measure). A total of 90 healthy adults in 20s to 70s with the equal gender ratio participated in the experiment consisting of combinations of 2 central force levels (6 N and 10 N) and 2 complexity levels (approximate entropy, ApEn = 0.03 and 0.06) of CSWPs. Significantly decreased FTCs (lower TWR and higher RRMSE) were found in aged adults, females, the low central force, and the high complexity. The detailed FTC decrements include a 43% reduced TWR and a 85% increased RRMSE of older adults in 70s as compared to those in 20s, a 17% reduced TWR and a 17% increased RRMSE of female as compared to those of male, a 30% reduced TWR and a 108% increased RRMSE at central force = 6N when compared to those at central force = 10N, and a 19% reduced TWR and a 30% increased RRMSE at ApEn = 0.06 as compared to those at ApEn = 0.03. The characteristics of FTCs for CSWPs can be of use in establishing an assessment protocol of motor performance for screening brain disorders.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.8
• /
• pp.315-320
• /
• 2014

Composition is a creative activity of a composer in order to express his or her emotion into melody based on their experience. However, it is very hard to implement an automatic composition program whose composition process is the same as the composer. On the basis that the creative activity is possible from the imitation we propose a method to implement an automatic composition system using the learning capability of ANN(Artificial Neural Networks). First, we devise a method to convert a melody into time series that ANN can train and then another method to learn the repeated melody with melody bar for correct training of ANN. After training of the time series to ANN, we feed a new time series into the ANN, then the ANN produces a full new time series which is converted a new melody. But post processing is necessary because the produced melody does not fit to the tempo and harmony of music theory. In this paper, we applied a tempo post processing using tempo post processing program, but the harmony post processing is done by human because it is difficult to implement. We will realize the harmony post processing program as a further work.

• Journal of Korea Spatial Information System Society
• /
• v.10 no.2
• /
• pp.63-79
• /
• 2008

With the recent development of advanced GIS and complex spatial analysis technologies, the more sophisticated technologies are being required to support the advanced knowledge for solving geographical or spatial problems in various decision support systems. In addition, necessity for research on scientific crime investigation and forensic science is increasing particularly at law enforcement agencies and investigation institutions for efficient investigation and the prevention of crimes. There are active researches on geographic profiling to predict the base location such as criminals' residence by analyzing the spatial patterns of serial crimes. However, as previous researches on geographic profiling use simply statistical methods for spatial pattern analysis and do not apply a variety of spatial and temporal analysis technologies on serial crimes, they have the low prediction accuracy. Therefore, this paper identifies the typology the spatio-temporal patterns of serial crimes according to spatial distribution of crime sites and temporal distribution on occurrence of crimes and proposes STA-BLP(Spatio-Temporal Analysis based Base Location Prediction) algorithm which predicts the base location of serial crimes more accurately based on the patterns. STA-BLP improves the prediction accuracy by considering of the anisotropic pattern of serial crimes committed by criminals who prefer specific directions on a crime trip and the learning effect of criminals through repeated movement along the same route. In addition, it can predict base location more accurately in the serial crimes from multiple bases with the local prediction for some crime sites included in a cluster and the global prediction for all crime sites. Through a variety of experiments, we proved the superiority of the STA-BLP by comparing it with previous algorithms in terms of prediction accuracy.

• Journal of The Korean Association For Science Education
• /
• v.35 no.4
• /
• pp.677-689
• /
• 2015

The purpose of this study is to derive suggestions and implications to strengthen the science curriculum continuity of Korea through comparative analysis with focus on the continuity of science curriculum in six countries (Taiwan, the United Kingdom, Finland, the United States, Canada, Korea). Original and Korean translations of the national curriculums of each country gathered from NCIC comparatively analyzed the contents of the 'Moon' and 'Rock cycle' based on features of curriculum configuration, vertical, and lateral connectivity. As a result, it was found that the concepts of Big Ideas or Cross-cutting Concept was utilized internationally to strengthen the linkage between grades or subjects. In particular, dealing with the aspect of the system was important. In the comparison of countries for the content, Korea deals with the most frequency on the 'Moon' and 'Rock cycle'. The contents of the chapter about the moon were simply repeated from elementary to high school levels with some variation. Korean science curriculum holds different perspectives and contents about the Rock cycle compared to other countries. In conclusion, Korea's curriculum requires appropriate tools to strengthen curriculum linkage and by doing so, it will be able to take advantage of the systems approach. Moreover, it is important to constitute the curriculum based on a sufficient understanding of the learning development of students according to their grade levels for the effective application of the curriculum.