• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.157-165
• /
• 2020

Aiming at the development of neural network and self-driving data set, it is also an idea to improve the performance of network model to detect moving objects by dividing the data set. In Darknet network framework, the YOLOv4 (You Only Look Once v4) network model was used to train and test Udacity data set. According to 7 proportions of the Udacity data set, it was divided into three subsets including training set, validation set and test set. K-means++ algorithm was used to conduct dimensional clustering of object boxes in 7 groups. By adjusting the super parameters of YOLOv4 network for training, Optimal model parameters for 7 groups were obtained respectively. These model parameters were used to detect and compare 7 test sets respectively. The experimental results showed that YOLOv4 can effectively detect the large, medium and small moving objects represented by Truck, Car and Pedestrian in the Udacity data set. When the ratio of training set, validation set and test set is 7:1.5:1.5, the optimal model parameters of the YOLOv4 have highest detection performance. The values show mAP50 reaching 80.89%, mAP75 reaching 47.08%, and the detection speed reaching 10.56 FPS.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.32 no.1
• /
• pp.5-33
• /
• 2021

This Study seeks for a plan for promotion of smartification of digital services for improving convenience in use and user services of public libraries in smart digital environment. Thus, in this Study, a survey on awareness of a plan for revitalization of digital data and smart libraries has been conducted for the persons in charge of digital data and librarians from public libraries. The result of this Survey are as follows: first, the introduction of smart libraries was effective by first implementing them in small and medium-sized cities with high interest in in information technology, and spreading them to public libraries in metropolitan cities and special autonomous cities; second, it is analyzed that the essential factor of success in introduction of smart libraries is the contents free from the terminals and the upgrade of computer equipment of users available for the use of these services. Terminals are to be individually utilized by smartphone users but it is necessary for upgrade and introduction of 5G which can secure the mobility of users including open type Wi-Fi; third, it is discovered that the information technology the applicability of which is expected to be easy while introducing smart libraries is RFID, which has been already generalized, and bigtata technology. The introduction of IoT technology in which the stakeholders of public libraries in metropolitan cities and special self-governing cities must be considered first.

• Korean Journal of Optics and Photonics
• /
• v.33 no.4
• /
• pp.146-158
• /
• 2022

The detector of a focal-plane-array mid-wave infrared (MWIR) camera has different response characteristics for each detector pixel, resulting in nonuniformity between detector pixels. In addition, image nonuniformity occurs due to heat generation inside the camera during operation. To solve this problem, in the process of camera manufacturing it is common to use a gain-and-offset table generated from a blackbody to correct the difference between detector pixels. One method of correcting nonuniformity due to internal heat generation during the operation of the camera generates a new offset value based on input frame images. This paper proposes a technique for dividing an input image into block image patches and generating offset values using only homogeneous patches, to correct the nonuniformity that occurs during camera operation. The proposed technique may not only generate a nonuniformity-correction offset that can prevent motion marks due to camera-gaze movement of the acquired image, but may also improve nonuniformity-correction performance with a small number of input images. Experimental results show that distortion such as flow marks does not occur, and good correction performance can be confirmed even with half the number of input images or fewer, compared to the traditional method.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.27 no.2
• /
• pp.49-70
• /
• 2022

Sea Surface Temperature (SST), one of the ocean features, has a significant impact on climate, marine ecosystem and human activities. Therefore, SST prediction has been always an important issue. Recently, deep learning has drawn much attentions, since it can predict SST by training past SST patterns. Compared to the numerical simulations, deep learning model is highly efficient, since it can estimate nonlinear relationships between input data. With the recent development of Graphics Processing Unit (GPU) in computer, large amounts of data can be calculated repeatedly and rapidly. In this study, Short-term SST will be predicted through Convolutional Neural Network (CNN)-based U-Net that can handle spatiotemporal data concurrently and overcome the drawbacks of previously existing deep learning-based models. The SST prediction performance depends on the seasonal and interannual SST variabilities around the southern coast of Korea. The predicted SST has a wide range of variance during spring and summer, while it has small range of variance during fall and winter. A wide range of variance also has a significant correlation with the change of the Pacific Decadal Oscillation (PDO) index. These results are found to be affected by the intensity of the seasonal and PDO-related interannual SST fronts and their intensity variations along the southern Korean seas. This study implies that the SST prediction performance using the developed deep learning model can be significantly varied by seasonal and interannual variabilities in SST.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.128-133
• /
• 2021

Currently, autonomous vehicle markets are commercializing a third-level autonomous vehicle, but there is a possibility that an accident may occur even during fully autonomous driving due to stability issues. In fact, autonomous vehicles have recorded 81 accidents. This is because, unlike level 3, autonomous vehicles after level 4 have to judge and respond to emergency situations by themselves. Therefore, this paper proposes a vehicle crisis detection system(VCDS) that collects and stores information outside the vehicle through CNN, and uses the stored information and vehicle sensor data to output the crisis situation of the vehicle as a number between 0 and 1. The VCDS consists of two modules. The vehicle external situation collection module collects surrounding vehicle and pedestrian data using a CNN-based neural network model. The vehicle crisis situation determination module detects a crisis situation in the vehicle by using the output of the vehicle external situation collection module and the vehicle internal sensor data. As a result of the experiment, the average operation time of VESCM was 55ms, R-CNN was 74ms, and CNN was 101ms. In particular, R-CNN shows similar computation time to VESCM when the number of pedestrians is small, but it takes more computation time than VESCM as the number of pedestrians increases. On average, VESCM had 25.68% faster computation time than R-CNN and 45.54% faster than CNN, and the accuracy of all three models did not decrease below 80% and showed high accuracy.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.11
• /
• pp.381-394
• /
• 2022

Recently, due to the personalization and customization of data, Internet-based services have increased requirements for real-time processing, such as real-time AI inference and data analysis, which must be handled immediately according to the user's situation or requirement. Real-time tasks have a set deadline from the start of each task to the return of the results, and the guarantee of the deadline is directly linked to the quality of the services. However, traditional container systems are limited in operating real-time tasks because they do not provide the ability to allocate and manage deadlines for tasks executed in containers. In addition, tasks such as AI inference and data analysis basically utilize graphical processing units (GPU), which typically have performance impacts on each other because performance isolation is not provided between containers. And the resource usage of the node alone cannot determine the deadline guarantee rate of each container or whether to deploy a new real-time container. In this paper, we propose a monitoring technique for tracking and managing the execution status of deadlines and real-time GPU tasks in containers to support real-time processing of GPU tasks running on containers, and a node list management technique for container placement on appropriate nodes to ensure deadlines. Furthermore, we demonstrate from experiments that the proposed technique has a very small impact on the system.

• Therapeutic Science for Rehabilitation
• /
• v.12 no.2
• /
• pp.69-83
• /
• 2023

Objective : This study, as a preliminary study, applied an Information & Communication Technology (ICT) home-based program to elderly people aged 65 years or older to confirm the effect of the cognitive enhancement program and to find the possibility of remote rehabilitation. Methods : This study from August to October 2022, three subjects were selected and the intervention was conducted for about 2 months. This intervention was conducted using Korean version of Mini-Mental State Examination, Korean version of Montreal Cognitive Assessment (MoCA-K), Computer Cognitive Senior Assessment System, and the Center for Epidemiologic Studies Depression scale to evaluate cognitive improvement before and after the program. The therapist remotely set the level of cognitive training according to the subject's level through weekly feedback. Results : After the intervention, all subjects showed improved scores in most items of the MoCA-K conducted before and after the intervention. In addition, among the items of Cotras-pro, upper cognition, language ability, attention, visual perception, and memory were improved. Conclusion : Cognitive rehabilitation training using an ICT home-based program not only prevented dementia but also made it habitual. Through this study, it was confirmed that remote rehabilitation for the elderly could be possible.

• Journal of The Korean Association For Science Education
• /
• v.43 no.2
• /
• pp.87-98
• /
• 2023

In this study, we investigated the change in science core competency perception of high school students and the reason for change when science inquiry classes were conducted using eight 'skills' of the 2015 revised science curriculum. Fifteen first-year high school students in Jeollanam-do participated in the science inquiry class of this study, and the class was conducted for 20 hours (5 hours a day for four days). The inquiry activities used in the class consisted of four activity stages (research problems, research methods, research results, and conclusions) and each stage was constructed to include at least one 'skill (Problem Recognition, Model Development and Use, Inquiry Design and Performance, Data Collection, Analysis and Interpretation, Mathematical Thinking and Computer Application, Conclusion and Evaluation, Evidence-based Discussion and Demonstration, and Communication)'. As a result of the study, students' perception of the five science core competencies increased statistically significantly at the significance level of 0.01 through inquiry classes and more than 93% of students recognized that their science core competencies improved through the classes. However, since the class of this study was conducted for a small number of students, it is difficult to generalize the effect of the class, and so it is necessary to conduct a quantitative study for many students.

• The Journal of the Korea Contents Association
• /
• v.22 no.8
• /
• pp.377-391
• /
• 2022

The objective of this study is to understand the operational status of the support projects for childcare in daycare centers operated by the Support Centers for Childcare(SCC) during the COVID-19 pandemic and find ways to improve and develop the project operation. To this end, data were collected and analyzed through in-depth interviews from the 1st week to the 4th week of February 2022 with six childcare agents in charge of the support projects for childcare in daycare centers in the SCC located in Seoul and Gyeonggi Province. As a result of the study, it was found that the demand for diversification of project operation methods, expansion of non-face-to-face education, individual consulting, and small-scale education increased while operating the support projects for childcare in daycare centers in the SCC during the COVID-19 pandemic. Operational difficulties were found to be a lack of ability to use media, the burden of coping with unpredictable situations, and insufficient communication between daycare centers and childcare policy institutions. As for the support needs, it was found that it is necessary to employ computer specialists, establish an environment for activating online education, and provide an efficient work delivery system in emergencies.

• Journal of Practical Engineering Education
• /
• v.15 no.2
• /
• pp.381-388
• /
• 2023

Through artificial neural network education using spreadsheets, non-major undergraduate students can understand the operation principle of artificial neural networks and develop their own artificial neural network software. Here, training of the operation principle of artificial neural networks starts with the generation of training data and the assignment of correct answer labels. Then, the output value calculated from the firing and activation function of the artificial neuron, the parameters of the input layer, hidden layer, and output layer is learned. Finally, learning the process of calculating the error between the correct label of each initially defined training data and the output value calculated by the artificial neural network, and learning the process of calculating the parameters of the input layer, hidden layer, and output layer that minimize the total sum of squared errors. Training on the operation principles of artificial neural networks using a spreadsheet was conducted for undergraduate non-major students. And image training data and basic artificial neural network development results were collected. In this paper, we analyzed the results of collecting two types of training data and the corresponding artificial neural network SW with small 12-pixel images, and presented methods and execution results of using the collected training data for Orange machine learning model learning and analysis tools.