• Journal of the Ergonomics Society of Korea
• /
• v.11 no.2
• /
• pp.47-56
• /
• 1992

In this paper, a mathematical model of learning curve is proposed to study the fi- nger's reaction time. The model is a logarithmic linear type which represents a lear- ning curve appropriately, and parameters are estimated by the linear. The learning coefficient and percentage of a reaction time can easily computed in the mathematical model. This quantitative approach provieds an important information to be used fot the working capqbility qualification of re-employment as well as the adaptability estimation of aged workers.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.355-360
• /
• 2021

COVID-19 has brought major changes to school education. Although it was attempted to guarantee students' right to learn through romote learning, the limitations of remote learning compared to face-to-face classes were clear. Nevertheless, the method of remote learning is undoubtedly a learning method that needs to be continuously developed in terms of being able to consider separated time and space and enabling learners to learn individually and autonomously. Therefore, in this study, real-time romote learning cases were analyzed at the elementary school stage, and problems in real-time remote classes were discovered and improved through teacher interviews. The problems with real-time remote classes in elementary school unit classes examined through examples are: First, that the proportion of teacher activity is high due to the anxiety of the unfamiliar environment of remote classes, and second, even though it is a real-time interactive class, it It was impossible to provide feedback. As a solution to this, it is necessary to consider the basic class steps (introduction-deployment-organization) and the use of class tools to provide appropriate communication and feedback was suggested.

• Journal of Industrial Convergence
• /
• v.20 no.12
• /
• pp.125-133
• /
• 2022

This study attempted to find out whether learning time has a mediating effect according to the gender, region, and grade of middle school students in the relationship between academic engagement and self-esteem. To this end, a survey of 1,045 middle school students in Gyeongsangnam-do was conducted on academic engagement, learning time, and self-esteem. Difference verification was conducted to determine the difference in academic engagement, learning time, and self-esteem according to the general characteristics of the study subjects, correlation analysis was conducted to determine the correlation between major variables, and regression analysis was conducted to verify the mediating effect of learning time. As a result of the analysis, first, there was no difference in the academic engagement of middle school students by group. In the learning time, middle school students in the city area were significantly higher than those in the township area, male students had higher self-esteem than female students, and students in the city area had significantly higher self-esteem as the grade went up. Second, as a result of correlation analysis, learning time, academic engagement, and self-esteem showed a positive correlation. Third, in the entire group not divided by group, both the direct path through which academic engagement reaches self-esteem and the partial mediating model from learning time to self-esteem showed significant effects. In the analysis by gender, only female students excluding male students showed a partial mediating effect, and the analysis results by region showed a partial mediating effect only on students in the city. The analysis results by grade showed a partial mediating effect only for second-year middle school students. In order to improve the self-esteem of middle school students, education and counseling should be conducted in consideration of not only individual differences by gender and grade, but also the region in which they live.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.13 no.5
• /
• pp.422-428
• /
• 1988

An iterative learning control system is a control system which makes system outputs follow desired outputs by iterating its trials over a finite time interval. In a discrete time system, we proposed one method in which present control inputs can be obtained by a linear combination of the input sequence and time-shifted error sequence at previous trial. In contrast with a continous time learning control system which needs differential opreration of an error signal, the time shift operation of the error sequence is simpler in a computer control system and its effectiveness is shown by a simulation.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.9
• /
• pp.125-132
• /
• 2021

At a time when non-face-to-face classes are being held for a long time due to Corona (COVD-19), research on non-face-to-face teaching and learning methods is needed. Existing teaching and learning methods are limited in their application to non-face-to-face classes as they present face-to-face practical and experiential teaching methods. In this study, we present a method of utilizing the extended reality (XR: eXtended Reality) technology for the 5AL (5 Activity Learning) teaching method, which is a teaching and learning method selected by the Institute for University Education Innovation. The 5AL teaching method consists of PBL Learning, Havruta Learning, Flipped Learning, Smart Activity Learning, and Gamification Learning. In this study, a method of combining the released extended reality contents with 5AL was presented. In addition, we developed content that integrates the 5 learning methods of 5AL and confirmed the learning effect through testing.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.6
• /
• pp.287-294
• /
• 2019

With the automation of production lines in the manufacturing industry, the importance of real-time fault diagnosis of facility is increasing. In this paper, we propose a fault diagnosis algorithm of LM (Linear Motion)-guide based on deep learning using vibration signals. Generally, in order to guarantee the performance of the deep learning, it is necessary to have a sufficient amount of data, but in a manufacturing industry, it is often difficult to obtain enough data due to physical and time constraints. To solve this problem, we propose a convolutional neural networks (CNN) model based on transfer learning. In addition, the spectrogram image is input to the CNN to reflect the frequency characteristic of the vibration signals with time. The performance of fault diagnosis according to various load condition and transfer learning method was compared and evaluated by experiments. The results showed that the proposed algorithm exhibited an excellent performance.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.1
• /
• pp.17-24
• /
• 2023

With the continuous growth in the amount of data collected and analyzed, deep learning has become increasingly popular for extracting meaningful insights from various fields. However, hardware limitations pose a challenge for achieving meaningful results with limited data. To address this challenge, this paper proposes an algorithm that leverages the characteristics of convolutional neural networks (CNNs) to reduce the size of image datasets by 20% through smoothing and shrinking the size of images using color elements. The proposed algorithm reduces the learning time and, as a result, the computational load on hardware. The experiments conducted in this study show that the proposed method achieves effective learning with similar or slightly higher accuracy than the original dataset while reducing computational and time costs. This color-centric dataset construction method using image smoothing techniques can lead to more efficient learning on CNNs. This method can be applied in various applications, such as image classification and recognition, and can contribute to more efficient and cost-effective deep learning. This paper presents a promising approach to reducing the computational load and time costs associated with deep learning and provides meaningful results with limited data, enabling them to apply deep learning to a broader range of applications.

• Journal of Forest and Environmental Science
• /
• v.40 no.1
• /
• pp.15-23
• /
• 2024

This research aimed to assess the possibility of detecting forest degradation using time-series satellite imagery and three different deep learning-based change detection techniques. The dataset used for the deep learning models was composed of two sets, one based on surface reflectance (SR) spectral information from satellite imagery, combined with Texture Information (GLCM; Gray-Level Co-occurrence Matrix) and terrain information. The deep learning models employed for land cover change detection included image differencing using the Unet semantic segmentation model, multi-encoder Unet model, and multi-encoder Unet++ model. The study found that there was no significant difference in accuracy between the deep learning models for forest degradation detection. Both training and validation accuracies were approx-imately 89% and 92%, respectively. Among the three deep learning models, the multi-encoder Unet model showed the most efficient analysis time and comparable accuracy. Moreover, models that incorporated both texture and gradient information in addition to spectral information were found to have a higher classification accuracy compared to models that used only spectral information. Overall, the accuracy of forest degradation extraction was outstanding, achieving 98%.

• Journal of Engineering Education Research
• /
• v.12 no.4
• /
• pp.150-158
• /
• 2009

This study deals with the effect of learner's self-regulated learning strategy in the non-real-time online discussion. Based on these research results, it was suggested self-regulated learning strategy should be utilized in order to enhance the cognitive dimension participation and discussion satisfaction quality of non-real-time online discussion.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.13 no.4
• /
• pp.352-359
• /
• 1988

A learning control system which should have memory elements can be designed by utilizing the concept of parameter adaptation for unknown control object system parameters and regard it as a hybrid adaptive control system. A parameter adaptive learning control system applicable to a continuous time system has been already reported. Since there have been rapid developments in digital technology, it is possible to extend a continuous time parameter adaptive learning control system concept to a discrete time case. This problem is treated in this paper. Its justfication is proved and a simulation shows that this algorithms is effective.