• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.538-540
• /
• 2021

In this paper, we proposed a smart target detection system that detects and recognizes a designated target to provide relative motion information when performing a target detection mission of a drone. The proposed system focused on developing an algorithm that can secure adequate accuracy (i.e. mAP, IoU) and high real-time at the same time. The proposed system showed an accuracy of close to 1.0 after 100k learning of the Google Inception V2 deep learning model, and the inference speed was about 60-80[Hz] when using a high-performance laptop based on the real-time performance Nvidia GTX 2070 Max-Q. The proposed smart target detection system will be operated like a drone and will be helpful in successfully performing surveillance and reconnaissance missions by automatically recognizing the target using computer image processing and following the target.

• Journal of Gastric Cancer
• /
• v.18 no.2
• /
• pp.182-188
• /
• 2018

Purpose: Despite the fact that there are several reports of single-port laparoscopic distal gastrectomy (SPDG), no analysis of its learning curve has been described in the literature. The aim of this study was to investigate the favorable factors for SPDG and to analyze the learning curve of SPDG. Materials and Methods: A total of 125 cases of SPDG performed from November 2011 to December 2015 were enrolled. All operations were performed by 2 surgeons (surgeon A and surgeon B). The moving average method was used for defining the learning curve. All cases were divided into 10 cases in a sequence, and the mean operative time and estimated blood loss data were extracted from each group. Results: Surgeon A performed 68 cases (female-to-male sex ratio, 91.1%:8.82%), and surgeon B performed 57 cases (female-to-male sex ratio, 61.4%:38.5%). The operative time of surgeon B significantly decreased after 30 cases ($157.8{\pm}38.4$ minutes vs. $118.1{\pm}34.5$ minutes, P=0.003); that of surgeon A did not significantly decrease before and after around 30 cases ($160.8{\pm}51.6$ minutes vs. $173.3{\pm}35.2$ minutes, P=0.6). The subgroup analysis showed that the operative time significantly decreased in the patients with body mass index (BMI) of <$25kg/m^2$ (<$25kg/m^2$:${\geq}25kg/m^2$, $159.3{\pm}41.7$ minutes: $194.25{\pm}81.1$ minutes; P=0.001). Conclusions: Although there was no significant decrease in the operative time for surgeon A, surgeon B reached the learning curve upon conducting 30 cases of SPDG. BMI of <$25kg/m^2$ was found to be a favorable factor for SPDG.

• Journal of the Korea Convergence Society
• /
• v.11 no.2
• /
• pp.241-252
• /
• 2020

The purpose of this research is to study the effect of soldiers' self-development during military service on returning university students' self-directed learning and job preparation Behavior. The object of this study are 323 students among second, third and fourth graders of about 15 universities' nationalwide by online stratified clusterrandom sampling. SPSS 25.0 program was used for data analysis and factor analysis, frequency analysis, independent t-test, one way ANOVA, multiple regression analysis were done. The rusult are as follows :First, self-directed learning and job preparation behavior according to personal characters have meaningful differences in university location, grade, degree of self-development during military service, degree of self-development during military service, self-development during military service, e-learning study during military service, gaining credits during military service, gaining national licence during military service and receiving money for self-development during military service. Second, The experience of self-development during military service has meanigful difference in returnig university students' self-directed learning and job preparation behavior.

• Geomechanics and Engineering
• /
• v.33 no.2
• /
• pp.203-209
• /
• 2023

One major advantage of ground penetrating radar (GPR) over other field test methods is its ability to obtain subsurface images of roads in an efficient and non-intrusive manner. Not only can the strata of pavement structure be retrieved from the GPR scan images, but also various irregularities, such as cracks and internal cavities. This article introduces a deep learning-based approach, focusing on detecting subsurface cracks by recognizing their distinctive hyperbolic signatures in the GPR scan images. Given the limited road sections that contain target features, two data augmentation methods, i.e., feature insertion and generation, are implemented, resulting in 9,174 GPR scan images. One of the most popular real-time object detection models, You Only Learn One Representation (YOLOR), is trained for detecting the target features for two types of subsurface cracks: bottom cracks and full cracks from the GPR scan images. The former represents partial cracks initiated from the bottom of the asphalt layer or base layers, while the latter includes extended cracks that penetrate these layers. Our experiments show the test average precisions of 0.769, 0.803 and 0.735 for all cracks, bottom cracks, and full cracks, respectively. This demonstrates the practicality of deep learning-based methods in detecting subsurface cracks from GPR scan images.

• 대한공업교육학회지
• /
• v.34 no.2
• /
• pp.267-285
• /
• 2009

The collaborative learning has been considered as an efficient teaching model and under the recent basic learning environment, even face-to-face classroom circumstance rapidly increases the courses of blended learning which utilize the merits of e-learning environment. Nonetheless, the study on the strategy for systematic blended learning is quite scarce. In this study, the survey was done for developing the blended learning strategy, based on the collaborative learning model at the face-to-face environment and judging the satisfaction on the courses which the model was applied to. The survey consists of demographic questions, satisfaction in the whole courses, satisfaction in the collaborative learning under the blended learning environment and satisfaction in the blended learning strategy and support tools applied to each step of the learning. The result of this study is as follows. First, in response to the question that the blended learning can complement the face-to-face classroom courses, the respondents represented average 4.09 at 5-point Likert scale. And to the question whether the collaborative learning is more efficient under the blended learning environment than the face-to-face classroom, the response corresponds to 4.06 scale on the average. Second, as for the satisfaction in the blended learning strategy and support tools applied to the each step of the blended learning, the satisfaction degree is analyzed as high as over 4.0 on the average toward all the questions. Third, regarding the support tools used for the blended learning strategy, the learners consider the tools as most helpful in order of chatting, team community, mail & note and archive. Lastly, I would like to suggest that the study result should be highly reflected in constructing the collaborative learning module of learning control system in the future.

• Journal of the Korean Society of School Health
• /
• v.32 no.2
• /
• pp.67-76
• /
• 2019

Purpose: The purpose of this study was to explore self-directed learning ability and its affecting factors among undergraduate students. Methods: A descriptive cross-sectional study design was used. Using a convenience sampling method, data were collected from 196 undergraduate students enrolled in one national university. Negative psychological tendency (i.e. Type D personality), academic engagement, and self-directed learning ability were assessed using a structured questionnaire. Data were analyzed by descriptive statistics, t-test, and analysis of covariance, Pearson's correlation coefficients, and stepwise multiple linear regression, using SPSS/WIN 23.0 program. Results: The mean age of the students was $21.61{\pm}2.40years$ and 56.6% were male students. Approximately, one third (n=67, 34.2%) of the students had Type D personality. The average scores of academic engagement and self-directed learning ability were $3.01{\pm}1.14$ and $3.46{\pm}0.50$, respectively. After controlling for sociodemographic variables, the Type D personality and academic engagement were significant predictors of self-directed learning ability (${\beta}=.64$, p<.001; ${\beta}=-.13$, p=.021, respectively). This model explained 53.6% of the variance in self-directed learning ability. Conclusion: The study identified that Type D personality and academic engagement affect self-directed learning ability of undergraduate students, one in a negative way, the other in a positive way. Educators and educational policy makers need to make efforts to include interventions and strategies that increase academic engagement and change negative psychological dispositions such as D-type personality in the undergraduate education curriculum.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.2 no.1
• /
• pp.52-57
• /
• 2010

Using the Operating Systems course that is offered by online, a blended learning mixed up with face-to-face lecture and e-learning for O.S. course has been carried out. In order to find a efficient management way of the blended learning, we build up two groups: one group named 01 takes a class which consists of two hours face-to-face lecture and one hour online study per week and the other group named 02 takes a class which consists of two hours online study and one hour face-to-face lecture. According to the result of a mid-term examination, the Cohen's d between two groups is 0.165. It means the small effect size. The 01 group has higer average and smaller variance than 02 group. However, 02 group has more students who earn high score than 01 group. In conclusion, if students can well carry out the self-regulated learning, then the blended learning mixed up with 02 group style is suitable. Otherwise, face-to-face lecture or the blended learning like 01 group style is suitable.

• Journal of Fisheries and Marine Sciences Education
• /
• v.21 no.4
• /
• pp.543-555
• /
• 2009

The characteristic of Web 2.0 is openness, participation, share, cooperation and creation. The purpose of this article was to identify learner based knowledge creation strategy through UCC in Web 2.0, to develop UCC by university students and to make systematic UCC process. This article suggested knowledge creation strategy with UCC learning Community of Practice(CoP). UCC was developed by 25 students who registered e-learning in "P" university and conducted interview with students and experts to analyze the contents which related with research questions. Systematic process for developing educational UCC was consisted of sectors such as idea creation, design, development, implementation and evaluation. Main developing process steps were as follows: making subject$\rightarrow$seeking information$\rightarrow$selecting data$\rightarrow$designing contents$\rightarrow$making story board$\rightarrow$planning of filming$\rightarrow$filming$\rightarrow$digitalizing$\rightarrow$editing$\rightarrow$reviewing final product$\rightarrow$implementing$\rightarrow$evaluating. For learner based knowledge creation through UCC, educational institutions have to provide platform for learners' need, and learners create diverse ideas with UCC CoP. This article suggested knowledge creation strategy with sharing collective intelligence through process of UCC design, development, implement and evaluation.

• Journal of Korea Technology Innovation Society
• /
• v.17 no.2
• /
• pp.380-420
• /
• 2014

We increasingly see the importance of employees acquiring enough expert capability or innovation capability to prepare for ever growing uncertainties in their operation domains. However, despite the above circumstances, there have not been an enough number of researches on how operational input components for employees' innovation outcome, innovation activities such as acquisition, exercise and promotion effort of employee's innovation capability, and their resulting innovation outcome interact with each other. This trend is believed to have been resulted because most of the current researches on innovation focus on the units of country, industry and corporate entity levels but not on an individual corporation's innovation input components, innovation outcome and innovation activities themselves. Therefore, this study intends to avoid the currently prevalent study frames and views on innovation and focus more on the strategic policies required for the enhancement of an organization's innovation capabilities by quantitatively analyzing employees' innovation outcomes and their most suggested relevant innovation activities. The research model that this study deploys offers both linear and structural model on the trio of learning, innovation capability and innovation outcome, and then suggests the 4 relevant hypotheses which are quantitatively tested and analyzed as follows: Hypothesis 1] The different levels of innovation capability produce different innovation outcomes (accepted, p-value = 0.000<0.05). Hypothesis 2] The different amounts of learning time produce different innovation capabilities (rejected, p-value = 0.199, 0.220>0.05). Hypothesis 3] The different amounts of learning time produce different innovation outcomes. (accepted, p-value = 0.000<0.05). Hypothesis 4] the innovation capability acts as a significant parameter in the relationship of the amount of learning time and innovation outcome (structural modeling test). This structural model after the t-tests on Hypotheses 1 through 4 proves that irregular on-the-job training and e-learning directly affects the learning time factor while job experience level, employment period and capability level measurement also directly impacts on the innovation capability factor. Also this hypothesis gets further supported by the fact that the patent time absolutely and directly affects the innovation capability factor rather than the learning time factor. Through the 4 hypotheses, this study proposes as measures to maximize an organization's innovation outcome. firstly, frequent irregular on-the-job training that is based on an e-learning system, secondly, efficient innovation management of employment period, job skill levels, etc through active sponsorship and energization community of practice (CoP) as a form of irregular learning, and thirdly a model of Yί=f(e, i, s, t, w)+${\varepsilon}$ as an innovation outcome function that is soundly based on a smart system of capability level measurement. The innovation outcome function is what this study considers the most appropriate and important reference model.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.60.2-61
• /
• 2017

A Convolutional Neural Network(CNN) is one of the well-known deep-learning methods in image processing and computer vision area. In this study, we apply CNN to two kinds of flare forecasting models: flare classification and occurrence. For this, we consider several pre-trained models (e.g., AlexNet, GoogLeNet, and ResNet) and customize them by changing several options such as the number of layers, activation function, and optimizer. Our inputs are the same number of SOHO)/MDI images for each flare class (None, C, M and X) at 00:00 UT from Jan 1996 to Dec 2010 (total 1600 images). Outputs are the results of daily flare forecasting for flare class and occurrence. We build, train, and test the models on TensorFlow, which is well-known machine learning software library developed by Google. Our major results from this study are as follows. First, most of the models have accuracies more than 0.7. Second, ResNet developed by Microsoft has the best accuracies : 0.77 for flare classification and 0.83 for flare occurrence. Third, the accuracies of these models vary greatly with changing parameters. We discuss several possibilities to improve the models.