• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.345-349
• /
• 2023

In this paper, we propose a study on the development of deep learning structure for defective pixel detection of next-generation smart LED display board using imaging device. In this research, a technique utilizing imaging devices and deep learning is introduced to automatically detect defects in outdoor LED billboards. Through this approach, the effective management of LED billboards and the resolution of various errors and issues are aimed. The research process consists of three stages. Firstly, the planarized image data of the billboard is processed through calibration to completely remove the background and undergo necessary preprocessing to generate a training dataset. Secondly, the generated dataset is employed to train an object recognition network. This network is composed of a Backbone and a Head. The Backbone employs CSP-Darknet to extract feature maps, while the Head utilizes extracted feature maps as the basis for object detection. Throughout this process, the network is adjusted to align the Confidence score and Intersection over Union (IoU) error, sustaining continuous learning. In the third stage, the created model is employed to automatically detect defective pixels on actual outdoor LED billboards. The proposed method, applied in this paper, yielded results from accredited measurement experiments that achieved 100% detection of defective pixels on real LED billboards. This confirms the improved efficiency in managing and maintaining LED billboards. Such research findings are anticipated to bring about a revolutionary advancement in the management of LED billboards.

• Journal of Korean Elementary Science Education
• /
• v.41 no.4
• /
• pp.701-724
• /
• 2022

In this study, the Nature of Science (NOS) instrument for elementary school students in the form of open questionnaires was developed specifically to reveal elementary school students' perceptions of the NOS, and its validity and effectiveness were investigated. To develop a NOS instrument for elementary school students, problems that may occur when applying the existing NOS instruments to elementary school students were analyzed and based on this, the development direction of the NOS instrument was established. In addition, after selecting seven NOS types suitable for the level of elementary school students, the preliminary instrument was produced by modifying and supplementing the items in the existing instruments for each type or by developing new items. Finally, the NOS instrument consisting of eight questions was developed by adding one question asking for a comprehensive understanding of science to seven questions related to each type of NOS after a content validity test of the science education expert group. To verify the practical effect of the developed instrument, pre- and post-tests were conducted on 50 students in two classes of sixth grade at two elementary schools in Seoul: 'existing instrument → development instrument' in one class, and 'development instrument → existing instrument' in the other class. The collected data were then compared and evaluated through summary content analysis and analyzed by executing the Wilcoxon signed-rank test. As a result of comparing and analyzing students' responses to the existing NOS instrument and the developed NOS instrument, students' perspectives on the NOS were more diverse when using the developed instrument, and the level of error in the response caused by misinterpreting the intention of the question was reduced. In addition, when using the developed instrument, the responses of the majority of students at a statistically significant level changed more specifically. In this study, the implications for the development of NOS instruments suitable for elementary school students were discussed based on these results.