• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.198-221
• /
• 2021

After large-scale reforestation in the 1960s and 1970s, forests in Korea have gradually been aging. Net ecosystem CO₂ exchange of old-growth forests is theoretically near zero; however, it can be a CO₂ sink or source depending on the intervention of disturbance or management. In this study, we report the CO₂ budget dynamics of the Gwangneung deciduous old-growth forest (GDK) in Korea and examined the following two questions: (1) is the preserved GDK indeed CO₂ neutral as theoretically known? and (2) can we explain the dynamics of CO₂ budget by the common mechanisms reported in the literature? To answer, we analyzed the 15-year long CO₂ flux data measured by eddy covariance technique along with other biometeorological data at the KoFlux GDK site from 2006 to 2020. The results showed that (1) GDK switched back-and-forth between sink and source of CO₂ but averaged to be a week CO₂ source (and turning to a moderate CO₂ source for the recent five years) and (2) the interannual variability of solar radiation, growing season length, and leaf area index showed a positive correlation with that of gross primary production (GPP) (R²=0.32~0.45); whereas the interannual variability of both air and surface temperature was not significantly correlated with that of ecosystem respiration (RE). Furthermore, the machine learning-based model trained using the dataset of early monitoring period (first 10 years) failed to reproduce the observed interannual variations of GPP and RE for the recent five years. Biomass data analysis suggests that carbon emissions from coarse woody debris may have contributed partly to the conversion to a moderate CO₂ source. To properly understand and interpret the long-term CO₂ budget dynamics of GDK, new framework of analysis and modeling based on complex systems science is needed. Also, it is important to maintain the flux monitoring and data quality along with the monitoring of coarse woody debris and disturbances.

• Journal of Korea Water Resources Association
• /
• v.56 no.6
• /
• pp.403-417
• /
• 2023

In this research, a methodology was developed for constructing an appropriate rainfall image database for estimating rainfall intensity based on CCTV video. The database was constructed in the Large-Scale Climate Environment Chamber of the Korea Conformity Laboratories, which can control variables with high irregularity and variability in real environments. 1,728 scenarios were designed under five different experimental conditions. 36 scenarios and a total of 97,200 frames were selected. Rain streaks were extracted using the k-nearest neighbor algorithm by calculating the difference between each image and the background. To prevent overfitting, data with pixel values greater than set threshold, compared to the average pixel value for each image, were selected. The area with maximum pixel variability was determined by shifting with every 10 pixels and set as a representative area (180×180) for the original image. After re-transforming to 120×120 size as an input data for convolutional neural networks model, image augmentation was progressed under unified shooting conditions. 92% of the data showed within the 10% absolute range of PBIAS. It is clear that the final results in this study have the potential to enhance the accuracy and efficacy of existing real-world CCTV systems with transfer learning.

• Journal of The Korean Association of Information Education
• /
• v.17 no.2
• /
• pp.101-113
• /
• 2013

The rapid spread of smart devices initiated by the launch of iPhone and the development of state-of-the-art communication technology have opened up a new chapter for today's age, accelerating a paradigm shift. It is defined as 'the smart era' that is characterized by a DNA of mobile. The meaning of the term 'smart' depends on in which field it is used and who uses it, but the term is basically based on 'human being,' namely people. Accordingly, people should take the initiative in this smart era, and what only people can do will become more important for that reason. In addition, there will be a drastic progress in today's technology, which is expected to make human life more convenient and to even make it possible to read human sentiment and emotion. Such social changes have affected education as well, and the education sector is making preparations for the introduction of 'smart education,' as there is a consensus that an absolutely new paradigm shift is mandatory. Smart education is not merely to introduce smart devices, ICT technology and SNS in education. New competent people are required in globalization age, and smart education is to attempt a new education to nurture new competent people. In this study, 4C (that were creativity, collaboration, contents and curation) were suggested as the key factors of smart education, and in which direction smart education should be led in our country was discussed.

• The Journal of the Korea Contents Association
• /
• v.18 no.6
• /
• pp.353-363
• /
• 2018

According to the Digi Capital forecast, the global augmented reality market is expected to grow rapidly by 2020 to reach 150 billion dollars. In particular, high value added effects are expected in education. As ICT advances, digital textbooks are also leading innovative education by adding interactive functions. Advanced countries, including the U.S., are already using digital textbooks that use augmented reality technology in their classes. In line with this technological outlook, the ministry proposed a design plan that applies augmented reality technology to middle school science 1 digital textbooks. A study on middle school science 1 digital textbooks showed that each unit provided short videos. In addition, an investigation into the augmented reality class case showed that it was difficult to establish experimental equipment, lack of equipment (devices), and 3D design contents that did not continue despite the excellence of learning effects. Based on this demand, we designed an augmented reality scenario and system configuration to be applied to the instrument-specific experiments of middle school science 1 digital textbooks to explore and explore the contents of augmented reality by students. This research will replace the dangerous experiments and time consuming experiments for teachers and students by applying augmented reality to science subjects that are essential for the development of digital textbooks.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.403-410
• /
• 2020

In addition to the research on noise removal and super-resolution using the data restoration (Output result) function of Autoencoder, research on the performance improvement of clustering using the dimension reduction function of autoencoder are actively being conducted. The clustering function and data restoration function using Autoencoder have common points that both improve performance through the same learning. Based on these characteristics, this study conducted an experiment to see if the autoencoder model designed to have excellent data recovery performance is superior in clustering performance. Skip connection technique was used to design autoencoder with excellent data recovery performance. The output result performance and clustering performance of both autoencoder model with Skip connection and model without Skip connection were shown as graph and visual extract. The output result performance was increased, but the clustering performance was decreased. This result indicates that the neural network models such as autoencoders are not sure that each layer has learned the characteristics of the data well if the output result is good. Lastly, the performance degradation of clustering was compensated by using both latent code and skip connection. This study is a prior study to solve the Hanja Unicode problem by clustering.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.336-344
• /
• 2021

The purpose of this study was to identify the self-awareness of smartphone dependence among undergraduate students and their response to the same. The data was drawn from a survey on smartphone overdependence conducted by the Ministry of Science and information and communications technology (ICT) and the National Information Society Agency in 2017. The responses of 1,735 undergraduate students were analyzed by frequency, percentage, mean, standard deviation, minimum-maximum value, ��2-test, independent t-test, Pearson's correlation coefficient, and stepwise multiple regression analysis. The results indicated that 22.3% of participants were at risk of smartphone dependence, and 63.6% of them were unaware of their dependence on smartphones. The perception of smartphone dependence was significantly associated with a higher risk of smartphone dependence (��=.35, p=.000) and the increasing use of applications such as games (��=.19, p=.000), television/video (��=.11, p=.000), and learning (��=.11, p=.000). Of the participants with dependence awareness, only a few knew about the existence of centers to prevent smartphone and internet dependence. Moreover, they rarely utilized these centers. However, the participants felt the need for more counseling agencies (26.8%), programs for dealing with oneself (23.2%), information about smartphone dependence (14.9%), and help to overcome dependence (10.9%). These findings show the need to establish public services so that students can easily access correct information on smartphone dependence and address this problem.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.32 no.6
• /
• pp.561-568
• /
• 2020

Wave measurements using X-band radar have many advantages compared to other wave gauges including wave-rider buoy, P-u-v gauge and Acoustic Doppler Current Profiler (ADCP), etc.. For example, radar system has no risk of loss/damage in bad weather conditions, low maintenance cost, and provides spatial distribution of waves from deep to shallow water. This paper presents new methods for estimating significant wave heights of X-band marine radar images using Artificial Neural Network (ANN). We compared the time series of estimated significant wave heights (Hs) using various estimation methods, such as signal-to-noise ratio (${\sqrt{SNR}}$), both and ${\sqrt{SNR}}$ the peak period (TP), and ANN with 3 parameters (${\sqrt{SNR}}$, TP, and Rval > k). The estimated significant wave heights of the X-band images were compared with wave measurement using ADCP(AWC: Acoustic Wave and Current Profiler) at Hujeong Beach, Uljin, Korea. Estimation of Hs using ANN with 3 parameters (${\sqrt{SNR}}$, TP, and Rval > k) yields best result.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.408-416
• /
• 2022

The new millennium is characterized by an unprecedented breakthrough in knowledge and information and communication technologies, and the challenges of the XXI century require modernized paradigms of interaction in all spheres of life. Education continues to play a key role in national and global growth. The key role of education and its leadership in developing creative potential, as the main paradigm of the countries' stability, have significantly influenced educational centers. The developers of educational programs use information technologies as an incentive to develop creative potential of educational process. Professional training of the educational candidate is enhanced by the use of information technologies, so the educational applicants should develop technological skills to be productive members of society. Using the latest achievements in the field of information technologies for the organization of the educational process helps to form the operational style of education applicants' thinking, which provides the ability to acquire skills of processing information, that is presented in the text, graphic, tabular form, and increase the level of general and informational culture necessary for better orientation in the modern information space. The purpose of the research is to determine the effectiveness of information technologies as an incentive to develop creative potential of educational process on the basis of the survey, to establish advantages and ability to provide high-quality education in the context of using information technologies. Methods of research: comparative analysis; systematization; generalization, survey. Results. Based on the survey conducted among students and teachers, it has been found out that the teachers use the following information technologies for the development of creative potential of the educational process: to provide video and audio communication process (100%), Moodle (95,6%), Duolingo (89,7%), LinguaLeo (89%), Google Forms (88%) and Adobe Captivate Prime (80,6%). It is determined that modular digital learning environments (97,9%), interactive exercises tools (96,3%), ICT for video and audio communication (96%) and interactive exercises tools (95,1%) are most conducive to the development of creative potential of the educational process. As a result of the research, it was revealed that implementation of information technologies for the development of creative potential of educational process in educational institutions is a complex process due to a large number of variables, which should be taken into account both on the educational course and on the individual level. It has been determined that the using the model of implementation information technologies for the development of creative potential in educational process, which is stimulated due to this model, benefits both students and teachers by establishing a reliable bilateral connection between teacher and education applicant.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Journal of The Korean Association For Science Education
• /
• v.42 no.4
• /
• pp.417-428
• /
• 2022

This study analyzed the frequency and level of scientific practices presented in secondary science textbooks. A total of 1,378 student activities presented in 14 middle school science textbooks and 5 high school integrated science textbooks were analyzed, using the definition and level of scientific practice suggested in the NGSS. Findings show that most student activities focus on three practices. Compared to the textbooks for the previous science curriculum, the practice of 'obtaining, evaluating, and communicating information' was more emphasized, reflecting societal changes due to ICT development. However, the practice of 'asking a question', which can be an important element of student-led science learning, was still rarely found in textbooks, and 'developing and using models', 'using math and computational thinking' and 'arguing based on evidence' were not addressed much. The practices were mostly elementary school level except for the practice of 'constructing explanations'. Such repeated exposures to a few and low level of practices mean that many future citizens would be led to a naïve understanding of science. The findings imply that it is necessary to emphasize various practices tailored to the level of students. In the upcoming revision of the science curriculum, it is necessary to provide the definition of practices that are not currently specified and the expected level of each practice so that the curriculum can provide sufficient guidance for textbook writing. These efforts should be supported by benchmarking of overseas science curriculum and research that explore students' ability and teachers' understanding of scientific practices.