• Journal of Drive and Control
• /
• v.19 no.2
• /
• pp.17-26
• /
• 2022

Recently, automatic transmissions caused a good improvement in the shift quality of a forklift. An advanced shift control algorithm, which was based on TCU firmware, was applied with embedded control technology and microcontrollers. In the clutch-to-clutch shifting, one friction element is released and the other friction element is activated. During this process, if the release and application timings are not synchronized, an overrun or tie-up occurs and ultimately leads to a shift shock. The TCU, which measures only the speed of the forklift, inevitably applies the open-loop shift control. In this situation, the speed ratio does not change during the clutch fill. The torque phase occurs until the clutch is disengaged. In this study, an offline shift logic of the learning control was proposed. It induced a synchronous shift when the learning control progressed. During this process, the reference current trajectory of the release clutch was corrected and applied to the next upshift. We considered the results of the overrun/tie-up characteristics of the upshift performed immediately before. The vehicle test proved that the deviation in shift quality, which was caused by the difference in the mechanical characteristics of the clutch, could be improved by the learning control.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.183-183
• /
• 2021

Deep learning methods and their application have become an essential part of prediction and modeling in water-related research areas, including hydrological processes, climate change, etc. It is known that application of deep learning leads to high availability of data sources in hydrology, which shows its usefulness in analysis of precipitation, runoff, groundwater level, evapotranspiration, and so on. However, there is still a limitation on microclimate analysis and prediction with deep learning methods because of deficiency of gauge-based data and shortcomings of existing technologies. In this study, a real-time rainfall prediction model was developed from a sky image data set with convolutional neural networks (CNNs). These daily image data were collected at Chung-Ang University and Korea University. For high accuracy of the proposed model, it considers data classification, image processing, ratio adjustment of no-rain data. Rainfall prediction data were compared with minutely rainfall data at rain gauge stations close to image sensors. It indicates that the proposed model could offer an interpolation of current rainfall observation system and have large potential to fill an observation gap. Information from small-scaled areas leads to advance in accurate weather forecasting and hydrological modeling at a micro scale.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.213-219
• /
• 2023

In recent years, popularity of deep learning (DL) is increased due to its ability to extract features from Hyperspectral images. A lack of discrimination power in the features produced by traditional machine learning algorithms has resulted in poor classification results. It's also a study topic to find out how to get excellent classification results with limited samples without getting overfitting issues in hyperspectral images (HSIs). These issues can be addressed by utilising a new learning network structure developed in this study.EfficientNet-B4-Based Convolutional network (EN-B4), which is why it is critical to maintain a constant ratio between the dimensions of network resolution, width, and depth in order to achieve a balance. The weight of the proposed model is optimized by Search and Rescue Operations (SRO), which is inspired by the explorations carried out by humans during search and rescue processes. Tests were conducted on two datasets to verify the efficacy of EN-B4, with Indian Pines (IP) and the University of Pavia (UP) dataset. Experiments show that EN-B4 outperforms other state-of-the-art approaches in terms of classification accuracy.

• Communications of Mathematical Education
• /
• v.28 no.2
• /
• pp.281-302
• /
• 2014

The purpose of this paper is to offer a history of golden ratio, the criterion raised by Markowsky, and misconceptions about golden ratio. Markowsky(1992) insists that the golden ratio does not appear in the great pyramid of Khufu. On the contrary, we claim that there exists the golden ration on it. Elementary and middle school text books, and domestic history books deal with the great pyramid of Khuff and the Parthenon by examples of the golden ratio. Text books make many incorrect statements about golden ratio; so in teaching and learning the golden ratio, we recommend the design-composition of dynamic symmetry, for example, industrial design, aerodynamic, architecture design, and screen design. Finally we discuss the axial age how to affect the school mathematics with respect to the subject of Thales and the golden ratio.

• Korean Journal of Radiology
• /
• v.24 no.4
• /
• pp.294-304
• /
• 2023

Objective: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. Materials and Methods: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. Results: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). Conclusion: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.2
• /
• pp.199-206
• /
• 2023

This study attempted to examine the relationship between college students' participation in the learning community according to the characteristics of learners. To this end, the learning community divided the subject-linked learning community into a foundation learning community and an advanced learning community. Learner characteristics were classified by gender, grade, and major. A cross-analysis was conducted to examine the difference between participation in the foundation learning community and the advanced learning community according to the learner characteristics. The results are as follows. First, the participation of female students in the foundation learning community and the advanced learning community was higher than that of male students, but it was not statistically significant. Second, it was found that there was a significant difference in participation in the learning community according to the grade. In the case of the foundation learning community, the participation rate of the first and second year students was relatively high, and in the case of the advanced learning community, the ratio of the third and fourth year students was relatively high. Third, as a result of examining the differences by major, it was found that the participation rate of health and welfare universities was high in both the foundation learning community and the advanced learning community. Based on these results, discussions and suggestions are presented.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.6
• /
• pp.59-68
• /
• 2004

Cooperative web-based learning is an teaching strategy in which small teams, each of students with different levels of ability, use a variety of learning activities to improve their understanding of a subject via the web. The objective of this paper is to propose new assessment items for evaluating students fairly in cooperative web-based learning. As a result, improved academic achievement, improved behavior and attendance, and increased self-confidence can be made in cooperative web-based learning due to the fair assessment, In this paper, the environment and instructional strategies for successful learning are firstly examined. In addition, the existing evaluation items in traditional classroom are also analyzed in order to develop new evaluation criteria in the web. Based on these analyzed items, we propose new evaluation items for cooperative web-based learning. In addition, the proposed items related to participant ratio, cooperability, and accountability are analyzed according to team organization styles and instructional models.

• Journal of the Korean School Mathematics Society
• /
• v.10 no.1
• /
• pp.129-148
• /
• 2007

Recent reform movement in mathematics education has focused not only on the curriculum development but also on teachers' learning or professional development. Whereas various theoretical paradigms call for different programs of professional development for teachers, one of the common emphases is on the pedagogical content knowledge [PCK] which encompasses contents and methods to teach. Against this background, this study developed comprehensive instructional materials for the purpose of fostering PCK in mathematics for elementary school teachers with 17 essential learning themes such as fraction, plane geometry, and area. Each loaming theme was first summarized on the basis of literature reviews and surveys in terms of knowledge in mathematics contents, knowledge in teaching methods, and knowledge in students' mathematical understanding and learning. Each theme was then analyzed in detail on how it was represented in the national curriculum and its concomitant textbooks along with workbooks. Finally, this report included a reconstruction of one unit in textbooks per each learning theme, followed by teaching notes and suggestions from classroom implementation. This was intended for teachers to apply what they might loam from this material to their actual mathematics instruction. Given the page limit, this paper dealt only with the learning theme of ratio.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.32-38
• /
• 2021

Image classification through deep learning on the image from photographs has been a very active research field for the past several years. In this paper, we propose a method of automatically discriminating stone images from domestic source through deep learning, which is to use Python's hash library to scan 300×300 pixel photo images of granites such as Hwangdeungseok, Goheungseok, and Pocheonseok, performing data preprocessing to create learning images by examining duplicate images for each stone, removing duplicate images with the same hash value as a result of the inspection, and deep learning by stone. In addition, to utilize VGGNet, the size of the images for each stone is resized to 224×224 pixels, learned in VGG16 where the ratio of training and verification data for learning is 80% versus 20%. After training of deep learning, the loss function graph and the accuracy graph were generated, and the prediction results of the deep learning model were output for the three kinds of stone images.

• Human Ecology Research
• /
• v.61 no.4
• /
• pp.543-563
• /
• 2023

The purpose of this study is to design and develop a Metaverse ZEP platform-based teaching and learning process plan by selecting learning topics that are commonly dealt with among the core concepts of the "family" area of practical (technical and home) subjects. To this end, a teaching and learning process plan was developed through planning, Metaverse platform design, expert review, and revision stages. The Metaverse ZEP "Open Class Day" platform, a virtual learning space, was created and developed to further utilize EduTech programs, such as Padlet, Mentimeter, Jamboard, Miricanvas, and Spatial. The teaching and learning process plan developed in this study consists of a total of seven sessions, including approaching EduTech, Changing Families, Exploring Our Family, and Counseling Centers 1, 2, and 3. Among them, Geumji Counseling Center 1, 2, and 3 was designed as a class in which parents and children participate together in open classes using the ZEP platform. This platform can be used as part of parent classes as well as to encourage online participation in the open classes held periodically at each individual school. In terms of the content validity ratio (CVR) of the developed teaching and learning process verified through five experts, 12 out of 15 questions had a CVR of 1, while the remaining three questions had a CVR of 0.6. The three questions with lower validity were revised and supplemented.