• Clean Technology
• /
• v.28 no.2
• /
• pp.138-146
• /
• 2022

Electricity has become a factor that dramatically affects the market economy. The day-ahead system marginal price determines electricity prices, and system marginal price forecasting is critical in maintaining energy management systems. There have been several studies using mathematics and machine learning models to forecast the system marginal price, but few studies have been conducted to develop, compare, and analyze various machine learning and deep learning models based on a data-driven framework. Therefore, in this study, different machine learning algorithms (i.e., autoregressive-based models such as the autoregressive integrated moving average model) and deep learning networks (i.e., recurrent neural network-based models such as the long short-term memory and gated recurrent unit model) are considered and integrated evaluation metrics including a forecasting test and information criteria are proposed to discern the optimal forecasting model. A case study of South Korea using long-term time-series system marginal price data from 2016 to 2021 was applied to the developed framework. The results of the study indicate that the autoregressive integrated moving average model (R-squared score: 0.97) and the gated recurrent unit model (R-squared score: 0.94) are appropriate for system marginal price forecasting. This study is expected to contribute significantly to energy management systems and the suggested framework can be explicitly applied for renewable energy networks.

• Geomechanics and Engineering
• /
• v.37 no.1
• /
• pp.49-64
• /
• 2024

Rocks undergoing repeated loading and unloading over an extended period, such as due to earthquakes, human excavation, and blasting, may result in the gradual accumulation of stress and deformation within the rock mass, eventually reaching an unstable state. In this study, a CNN-CCM is proposed to address the mechanical behavior. The structure and hyperparameters of CNN-CCM include Conv2D layers × 5; Max pooling2D layers × 4; Dense layers × 4; learning rate=0.001; Epoch=50; Batch size=64; Dropout=0.5. Training and validation data for deep learning include 71 rock samples and 122,152 data points. The AI Rock Constitutive Model learned by CNN-CCM can predict strain values(ε₁) using Mass (M), Axial stress (σ₁), Density (ρ), Cyclic number (N), Confining pressure (σ₃), and Young's modulus (E). Five evaluation indicators R², MAPE, RMSE, MSE, and MAE yield respective values of 0.929, 16.44%, 0.954, 0.913, and 0.542, illustrating good predictive performance and generalization ability of model. Finally, interpreting the AI Rock Constitutive Model using the SHAP explaining method reveals that feature importance follows the order N > M > σ₁ > E > ρ > σ₃.Positive SHAP values indicate positive effects on predicting strain ε₁ for N, M, σ₁, and σ₃, while negative SHAP values have negative effects. For E, a positive value has a negative effect on predicting strain ε₁, consistent with the influence patterns of conventional physical rock constitutive equations. The present study offers a novel approach to the investigation of the mechanical constitutive model of rocks under cyclic loading and unloading conditions.

• International Journal of Computer Science & Network Security
• /
• v.21 no.2
• /
• pp.54-65
• /
• 2021

The movement control order and shutting down educational institution in Saudi Arabia has jeopardized the teaching and learning process. Education was shifted to distance learning in order to avoid any academic loss. In the middle of the Covid-19 crisis, there is a need to assess the full image of e-learning in Saudi Arabia. To investigate student and teachers' perception and acceptance, parents' attitudes and believes about distance education are the main goals of the study. The mix-method research design was employed to collect data. Three surveys were distributed to 100 students and 50 teachers and 50 parents from different educational institutions in Saudi Arabia, while semi-structured interviews were conducted with 10 parents. Random stratified and convenient sampling methods were adopted. Both descriptive and content analysis was conducted using SPSS25.0 and NVIVO software for quantitative and qualitative data accordingly. The findings showed that students are comfortable with remote education and are receiving enough support from schools and instructors but they think online education can't replace conventional face-to-face learning. Moreover, the results showed that teachers are having challenges in preparing online classes because of the development of conducting online classes and the lack of training. However, parents showed negative attitudes regarding the benefits and values of remote education and preferred conventional learning styles in elementary schools. Parents tended to reject and resist distance learning for several reasons: professional knowledge and lack of time to support their young kids in online classes, the shortcomings of e-learning, young children's inadequate self-regulation. Saudi parents are neither trained nor ready to use e-learning. The study provided suggestion and implications for teacher education and policymakers.

• Journal of The Korean Association of Information Education
• /
• v.16 no.4
• /
• pp.439-450
• /
• 2012

This paper explores effectiveness of integrating Problem-Based Learning with Web 2.0 technologies in Computer subject matter education for improving quality of lessons and adapting of social needs for pre-service teachers. Students have studied about computer subject matter for 4 times. The process of leaning have recorded by Web 2.0 tools that is one of the cloud services. Also the students have written reflection journals about experiences of PBL process and results. The PBL process and reflection journals have been analyzed by qualitative data analysis. Conclusions are drawn as to potential for the use of Web 2.0 tools for PBL in computer subject matter. The results of the analyses showed the following: 1) Increasing the understanding of the computer subject matter education, 2) enhancing students' competence in using ICT potentially, 3) cultivating teaching and learning strategies on Web 2.0 environment and 4) enhancing competence of future teaching activities through experiencing e-portfolio as a performance-assessment tool.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.11 no.1
• /
• pp.6-12
• /
• 2004

Purpose: The purpose of this study was to evaluate self-study learning achievement in undergraduate nursing students who used a web-based wound care e-book. Method: The web-based wound care e-book was applied to 80 nursing students at Y university. The students studied the wound care e-book for four weeks and practiced wound dressing by themselves in open laboratory. Learning achievement was evaluated according to achievement of unit objectives and performance of an actual wound dressing. Result: 1. The total mean score for achievement of unit objectives was 3.06 (${\pm}0.41$) and the total mean score on the performance of the wound dressing was 89.40 (${\pm}5.47$). 2. There was no difference between the scores in the performance test (F=1.012, p=.366) for students who used self-study and those who were given a lecture. 3. A positive correlation was found between achievement of unit objectives and performance of the wound dressing (r=0.306, p<0.05). Conclusion: The web-based wound care e-book was effective in facilitating self-study for nursing students, and there is a need to continuously develop and up-date web-based nursing education e-books to facilitate self-study.

• Educational Technology International
• /
• v.23 no.2
• /
• pp.207-237
• /
• 2022

As technological changes continue to accelerate every day, meeting the needs of a shifting educational landscape requires leaving an exclusively "in-person" education behind. Gamified learning environments should be carefully designed in light of conflicting studies to suit students' needs. The purpose of this meta-analysis is to draw conclusive results regarding the application of the most commonly used game elements in education, i.e., badges and leaderboards, through a comprehensive analysis of their impact on academic performance in online learning. Review Manager (RevMan 5.4) was used to analyze eligible studies selected from Emerald, SAGE, ERIC, EBSCO, and ProQuest between January 2011 and January 2022. Analyzing 37 studies found that using leaderboards and badges in online education enhanced academic performance when compared to traditional learning without gamification (SMD = 0.39). The badge-only intervention showed a larger effect size (SMD = 0.33) than the leaderboard-only intervention (SMD = 0.27). Badges and leaderboards together exhibited a larger effect size (SMD = 0.48) than individual game elements (SMD = 0.40). The impact of the game elements on academic performance was greater in the humanities (SMD = 0.51) than in STEM fields (SMD = 0.32) and was greater for K-12 students (SMD = 0.63) than for college students (SMD = 0.31). This study contributes to a timely discussion of the use of badges and leaderboards in COVID-19 online learning trends and provides relevant data for designing integrations of online education and gamification models.

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.73-88
• /
• 2023

Brain tumors can also be an abnormal collection or accumulation of cells in the brain that can be life-threatening due to their ability to invade and metastasize to nearby tissues. Accurate diagnosis is critical to the success of treatment planning, and resonant imaging is the primary diagnostic imaging method used to diagnose brain tumors and their extent. Deep learning methods for computer vision applications have shown significant improvements in recent years, primarily due to the undeniable fact that there is a large amount of data on the market to teach models. Therefore, improvements within the model architecture perform better approximations in the monitored configuration. Tumor classification using these deep learning techniques has made great strides by providing reliable, annotated open data sets. Reduce computational effort and learn specific spatial and temporal relationships. This white paper describes transfer models such as the MobileNet model, VGG19 model, InceptionResNetV2 model, Inception model, and DenseNet201 model. The model uses three different optimizers, Adam, SGD, and RMSprop. Finally, the pre-trained MobileNet with RMSprop optimizer is the best model in this paper, with 0.995 accuracies, 0.99 sensitivity, and 1.00 specificity, while at the same time having the lowest computational cost.

• Journal of Korea Multimedia Society
• /
• v.12 no.5
• /
• pp.757-766
• /
• 2009

This study presents an adaptive hypermedia learning system which can provide individual learning environment using a learner behavioral model. This system proposes a LBML which can manage learners' learning behavioral information by tracking down such information real-time. The system consists of a collecting system of learning behavioral information and an adaptive learning support system. The collecting system of learning behavioral information uses Web 2.0 technologies and collects learners' learning behavioral information real-time based on a SCORM CMI data model. The collected information is stored as LBML instances of individual learners based on a LBML schema. With the adaptive learning support system, a rule-based learning supporting module and an interactive learning supporting module are developed by analysing LBML instances.

• Korean Journal of Mathematics
• /
• v.32 no.1
• /
• pp.43-57
• /
• 2024

Given a domain X and a collection H of functions h : X → {0, 1}, the Vapnik-Chervonenkis (VC) dimension of H measures its complexity in an appropriate sense. In particular, the fundamental theorem of statistical learning says that a hypothesis class with finite VC-dimension is PAC learnable. Recent work by Fitzpatrick, Wyman, the fourth and seventh named authors studied the VC-dimension of a natural family of functions ℋ'²_t(E) : 𝔽²_q → {0, 1}, corresponding to indicator functions of circles centered at points in a subset E ⊆ 𝔽²_q. They showed that when |E| is large enough, the VC-dimension of ℋ'²_t(E) is the same as in the case that E = 𝔽²_q. We study a related hypothesis class, ℋ^d_t(E), corresponding to intersections of spheres in 𝔽^d_q, and ask how large E ⊆ 𝔽^d_q needs to be to ensure the maximum possible VC-dimension. We resolve this problem in all dimensions, proving that whenever |E| ≥ C_dq^d-1/(d-1) for d ≥ 3, the VC-dimension of ℋ^d_t(E) is as large as possible. We get a slightly stronger result if d = 3: this result holds as long as |E| ≥ C_3q^7/3. Furthermore, when d = 2 the result holds when |E| ≥ C_2q^7/4.

• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.490-501
• /
• 2018

This study was conducted to develop and test effects of E-book based Flipped Learning education for nursing students. This study was one-group pretest-posttest design. The data were collected from 54 second-year nursing students in the located Y city and August 28 2017 to October 16 2017. The data were analyzed by descriptive statistics, paired t-test, Pearson's correlation coefficient, and stepwise multiple regression with SPSS 20.0 program. The results showed that the program was effective in increasing the critical thinking disposition (t=-8.62, p<.001), academic self-efficacy (t=-9.62, p<.001) and major satisfaction (t=-8.11, p<.001). The result of the stepwise multiple regression indicates the critical thinking disposition predict 13.4% (F=9.22, p<.001) of major satisfaction. The result of the stepwise multiple regression indicates the critical thinking disposition predict 13.4% (F=9.22, p<.001) of major satisfaction. Therefore, strategies for enhancing critical thinking disposition is needed by applying various teaching and learning strategies for nursing students.