• Smart Media Journal
• /
• v.12 no.3
• /
• pp.30-37
• /
• 2023

Alzheimer's disease (AD) symptoms are being treated by early diagnosis, where we can only slow the symptoms and research is still undergoing. In consideration, using T1-weighted images several classification models are proposed in Machine learning to identify AD. In this paper, we consider the improvised feature selection, to reduce the complexity by using wrapping techniques and Restricted Boltzmann Machine (RBM). This present work used the subcortical and cortical features of 278 subjects from the ADNI dataset to identify AD and sMRI. Multi-class classification is used for the experiment i.e., AD, EMCI, LMCI, HC. The proposed feature selection consists of Forward feature selection, Backward feature selection, and Combined PCA & RBM. Forward and backward feature selection methods use an iterative method starting being no features in the forward feature selection and backward feature selection with all features included in the technique. PCA is used to reduce the dimensions and RBM is used to select the best feature without interpreting the features. We have compared the three models with PCA to analysis. The following experiment shows that combined PCA &RBM, and backward feature selection give the best accuracy with respective classification model RF i.e., 88.65, 88.56% respectively.

• Fourth Industrial Review
• /
• v.3 no.2
• /
• pp.11-17
• /
• 2023

Purpose - Recently, in the field of language education, interest in edutech has increased due to difficulties in classroom teaching due to COVID-19. Accordingly, we would like to analyze research topics related to e-learning before and after COVID-19 and examine the implications for the future Korean language education field. Research design, data, and methodology - This study organized a list of papers to be analyzed by searching for e-learning terms applicable to Korean language education in RISS. The collected data was electronically documented, keywords were extracted using text mining techniques, and word frequencies were checked, and then viewed through cloud visualization. Result - It was confirmed that research on e-learning in the field of Korean language education has increased rapidly in 2021 and 2022. In particular, extensive research on online learning methods has been actively conducted due to the difficulties of face-to-face learning in the COVID-19 era. There have been many studies on teaching and learning methods, such as flipped learning, hybrid learning, blended learning, mobile learning, and smart learning. Conclusion - Since the research so far has mainly focused on online class management methods. Therefore, future research suggests that efforts should be made to develop educational contents and teaching methods using specific ICT technologies. These efforts will contribute to advancing smart education that future education aims for.

• Smart Media Journal
• /
• v.12 no.5
• /
• pp.88-101
• /
• 2023

As the definition and role of design changes over time with the times and society, design education needs to update teaching methods to match it. The course design in this study began with an optimisation of the learning model based on previous research and analysis, followed by in-depth interviews, the application of the interview results to the final curriculum design, and finally a questionnaire to verify the positive effects of this teaching model. This teaching model has been applied to teach a pilot class in a university of applied sciences in China. The main characteristics of the course design are Project-Based Learning (PJBL) oriented, team cooperation centric, and an educational model developed based on peer assessment. In every stage of the UI design course, realistic project simulations are adopted, enhancing students' abilities through practical experience, teamwork, and peer assessment. The innovation lies in validating the effectiveness and advantages of this model at every stage of the UI design course, innovating existing teaching methods, optimizing learning models, and combining practice with evaluation. This research found that a project-oriented team course design based on PJBL has a high degree of effectiveness and relevance in each stage of the UI design course, significantly improving students' overall competence. It is expected that the results of this study can be applied in various ways to the course design of the courses that similar to design majors.

• Journal of Advanced Navigation Technology
• /
• v.15 no.6
• /
• pp.1126-1131
• /
• 2011

As the recent paradigm of education changes to become learner-centered, there is an increasing interest in project based class as one of new teaching models. Universities are accepting this change and aiming at fostering human resources of next generations, who are able to create creative changes, and studies are being actively conducted to that end. This study suggested a learner-centered teaching model which minimizes intervention of teachers in conducting projects of main text contents in designed subjects. This study suggested support system for the suggested model project-based class, team organization method, various interaction methods of learners, and team work monitoring method of teachers. And the suggestions were designed and realized through project management applications using smart phones which are being used by a rapidly growing number of people recently.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.12
• /
• pp.5087-5102
• /
• 2015

Rapid popularization of smart cell phone equipped with camera has led to a number of new legal and criminal problems related to multimedia such as digital image, which makes cell phone source identification an important branch of digital image forensics. This paper proposes a classifier combination based source identification strategy for cell phone images. To identify the outlier cell phone models of the training sets in multi-class classifier, a one-class classifier is orderly used in the framework. Feature vectors including color filter array (CFA) interpolation coefficients estimation and multi-feature fusion is employed to verify the effectiveness of the classifier combination strategy. Experimental results demonstrate that for different feature sets, our method presents high accuracy of source identification both for the cell phone in the training sets and the outliers.

• Journal of Korean Clinical Health Science
• /
• v.7 no.2
• /
• pp.1289-1297
• /
• 2019

Purpose: The purpose of this study was to investigate occupational therapy at M college in Changwon and the impact of smart phone use on the school life of college students and to help them find ways to further develop in the future. Methods; Data collection was conducted using questionnaires, and the questionnaires consisted of 152 total questions with 15 interpersonal questions, 23 problem solving skills, 43 self-efficacy, 16 class participation scale, and 55 self-directed learning scale. It was conducted to first and second graders of M college and conducted a survey through the corresponding academic year from March 26, 2019 to March 29, 2019 to retrieve 120 questionnaires and use them for analysis. The collected data were analyzed using SPSS. Statistic 20.0. Results: Studies show that "school life satisfaction" is usually the highest at 53 percent. The "smartphone user motivation" was the highest with 50.8 percent, while the "most frequently used feature on smartphones" was the highest with 57.5 percent on SNS. Satisfaction after using a smartphone was the highest with 49.2 percent, while 41.7 percent said it would be easier to acquire and utilize information in the areas of satisfaction. Conclusion: Smartphone addiction, interpersonal relationships, problem-solving skills, self-efficacy, participation in classes, and self-control learning items are not only affected by one part, but also by the other.

• Journal of Korean Elementary Science Education
• /
• v.39 no.1
• /
• pp.84-99
• /
• 2020

The purpose of this study is to develop a STEAM program using technological pedagogical and content knowledge (TPACK) model to effectively utilize technology to solve the difficulties in the teaching of 'structure and function of our body' unit in the primary science curriculum and to confirm the effect on the academic achievement, creative problem solving ability and scientific interests of elementary students. The program was developed as the STEAM program of the 8th class by utilizing the construction knowledge of the TPACK model. The developed program was applied to 29 experimental group students in 5th grade. And the textbook-oriented circulatory system learning program was applied to 29 5th graders in the same school. As a result of the application of the program, the experimental group showed significant improvement over the comparison group in its creative problem solving ability and scientific interests, and the satisfaction of the class was also high. This caused a positive effect on students because the process of self-directing information about the circulatory system using smart devices, making outputs creatively using 3D printers, and presenting them through role play using produced outputs.

• Smart Structures and Systems
• /
• v.30 no.4
• /
• pp.385-395
• /
• 2022

Detecting cracks on a concrete structure is crucial for structural maintenance, a crack being an indicator of possible damage. Conventional crack detection methods which include visual inspection and non-destructive equipment, are typically limited to a small region and require time-consuming processes. Recently, to reduce the human intervention in the inspections, various researchers have sought computer vision-based crack analyses: One class is filter-based methods, which effectively transforms the image to detect crack edges. The other class is using deep-learning algorithms. For example, convolutional neural networks have shown high precision in identifying cracks in an image. However, when the objective is to classify not only the existence of crack but also the types of cracks, only a few studies have been reported, limiting their practical use. Thus, the presented study develops an image processing procedure that detects cracks and classifies crack types; whether the image contains a crazing-type, single crack, or multiple cracks. The properties and steps in the algorithm have been developed using field-obtained images. Subsequently, the algorithm is validated from additional 227 images obtained from an open database. For test datasets, the proposed algorithm showed accuracy of 92.8% in average. In summary, the developed algorithm can precisely classify crazing-type images, while some single crack images may misclassify into multiple cracks, yielding conservative results. As a result, the successful results of the presented study show potentials of using vision-based technologies for providing crack information with reduced human intervention.

• Smart Structures and Systems
• /
• v.33 no.4
• /
• pp.253-262
• /
• 2024

Current-based mechanical fault diagnosis is more convenient and low cost since additional sensors are not required. However, it is still challenging to achieve this goal due to the weak fault information in current signals. In this paper, a dual-loss convolutional neural network (DLCNN) is proposed to implement the intelligent bearing fault diagnosis via current signals. First, a novel similarity loss (SimL) function is developed, which is expected to maximize the intra-class similarity and minimize the inter-class similarity in the model optimization operation. In the loss function, a weight parameter is further introduced to achieve a balance and leverage the performance of SimL function. Second, the DLCNN model is constructed using the presented SimL and the cross-entropy loss. Finally, the two-phase current signals are fused and then fed into the DLCNN to provide more fault information. The proposed DLCNN is tested by experiment data, and the results confirm that the DLCNN achieves higher accuracy compared to the conventional CNN. Meanwhile, the feature visualization presents that the samples of different classes are separated well.

• Spatial Information Research
• /
• v.23 no.1
• /
• pp.19-31
• /
• 2015

Due to the global warming and unstable abnormal climate changes, water resources differences between regions and water shortage are occurring. Therefore, the water resources management is becoming more important for the stable securement of future water supply and demand. Researches on Smart Water Grid (SWG), which is considered as a new method, that can stably secure and maintain the water resources, are actively being conducted but it is still in infancy. Thus, this study aimed to design SWG simulator based on GIS in order to provide integrated water information in web environment. The user's requirements were analyzed for system development and important functions such as SWG current situation checking, future prediction, filtration plant situation checking functions were designed and data expression techniques using GIS and HTML5 were applied to enhance the understanding of the users. Also, when the emergency situations occurred, the solving process of the situations are reproduced to check the solution process using scenario reproduction functions. Use-case, class, sequence diagram, which are a design for real system development and defines the system usage contents of users, were written, and the story board was written to check the final development contents. This study designed a SWG simulator in order to support the water maintenance reacting to climate changes. The development of system is expected to help securing information to deal with emergency situations such as water shortage and help the decision maker to make decision through reproduction of scenario. The major functions were designed for the convenience of water resource manager and producer but new contents for consumers must be developed to enable duplex information transmission.