• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.453-461
• /
• 2021

Many deep learning approaches have been studied for image classification in computer vision. However, there are not enough data to generate accurate models in medical fields, and many datasets are not annotated. This study presents a new method that can use both unlabeled and labeled data. The proposed method is applied to classify cervix images into normal versus cancerous, and we demonstrate the results. First, we use a patch self-supervised learning for training the global context of the image using an unlabeled image dataset. Second, we generate a classifier model by using the transferred knowledge from self-supervised learning. We also apply attention learning to capture the local features of the image. The combined method provides better performance than state-of-the-art approaches in accuracy and sensitivity.

• Journal of the Korea Convergence Society
• /
• v.11 no.9
• /
• pp.375-383
• /
• 2020

The study was to examine the mediating effect of self-efficacy in learning in the relationship between the learning satisfaction and motivation to transfer of nursing students who received the psychiatric nursing convergence simulation practicum using standardized patients. Participants were 144 third grade nursing students. Data were analyzed descriptive statistics, t-test, one-way ANOVA, Pearson's correlation coefficient analysis, and multiple regression following the Baron and Kenny's method and Sobel test for mediation. There were significant correlations between learning satisfaction and self-efficacy in learning(r=.686, p<.001), learning satisfaction and motivation to transfer(r=.633, p<.001) and self-efficacy in learning and motivation to transfer(r=.804, p<.001). Self-efficacy in learning showed partial mediating effects in the relationship between learning satisfaction and motivation to transfer(Z=7.63, p<.001). To increase the motivation to transfer, strategies to enhance the self-efficacy of nursing students are required.

• 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 the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.1-11
• /
• 2023

Breast cancer is the disease that affects women the most worldwide. Due to the development of computer technology, the efficiency of machine learning has increased, and thus plays an important role in cancer detection and diagnosis. Deep learning is a field of machine learning technology based on an artificial neural network, and its performance has been rapidly improved in recent years, and its application range is expanding. In this paper, we propose a DNN-SVM hybrid model that combines the structure of a deep neural network (DNN) based on transfer learning and a support vector machine (SVM) for breast cancer classification. The transfer learning-based proposed model is effective for small training data, has a fast learning speed, and can improve model performance by combining all the advantages of a single model, that is, DNN and SVM. To evaluate the performance of the proposed DNN-SVM Hybrid model, the performance test results with WOBC and WDBC breast cancer data provided by the UCI machine learning repository showed that the proposed model is superior to single models such as logistic regression, DNN, and SVM, and ensemble models such as random forest in various performance measures.

• Journal of Industrial Convergence
• /
• v.20 no.5
• /
• pp.29-38
• /
• 2022

Because of the need of actual performance of education, this study aims to understand how the factors of educational content and organizational characteristics affect organizational commitment and work performance, which are organizational effects, through learning transfer. As a result, task value, job relevance, and organizational compensation had a significant effect on learning transfer, learning transfer had a significant effect on organizational commitment and work performance, and organizational commitment had a significant effect on work performance. In order to increase the learning transfer of education, when specifying the connection with the actual job and strengthening the compensation system of the members, the learning transfer can be increased and eventually connected to performance. Since limited variables are considered, a more representative sample or professional group should be extracted through future research. In future studies, it will be possible to closely grasp the relationship between learning transfer and organizational effectiveness by setting representative samples and specifying variables.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.465-470
• /
• 2024

The advancement of AI-based image generation technology has resulted in the creation of various images, emphasizing the need for technology capable of accurately discerning them. The amount of generated image data is limited, and to achieve high performance with a limited dataset, this study proposes a model for discriminating generated images using transfer learning. Applying pre-trained models from the ImageNet dataset directly to the CIFAKE input dataset, we reduce training time cost followed by adding three hidden layers and one output layer to fine-tune the model. The modeling results revealed an improvement in the performance of the model when adjusting the final layer. Using transfer learning and then adjusting layers close to the output layer, small image data-related accuracy issues can be reduced and generated images can be classified.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.3
• /
• pp.55-65
• /
• 2019

Although crack on concrete exists from its early formation, crack requires attention as it affects stiffness of structure and can lead demolition of structure as it grows. Detecting cracks on concrete is needed to take action prior to performance degradation of structure, and deep learning can be utilized for it. In this study, transfer learning, one of the deep learning techniques, was used to detect the crack, as the amount of crack's image data was limited. Pre-trained Inception-v3 was applied as a base model for the transfer learning. Web scrapping was utilized to fetch images of concrete wall with or without crack from web. In the recognition of crack, image post-process including changing size or removing color were applied. In the visualization of crack, source images divided into 30px, 50px or 100px size were used as input data, and different numbers of input data per category were applied for each case. With the results of visualized crack image, false positive and false negative errors were examined. Highest accuracy for the recognizing crack was achieved when the source images were adjusted into 224px size under gray-scale. In visualization, the result using 50 data per category under 100px interval size showed the smallest error. With regard to the false positive error, the best result was obtained using 400 data per category, and regarding to the false negative error, the case using 50 data per category showed the best result.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.5
• /
• pp.674-677
• /
• 2020

The cultural background of users utilizing image search engines has a significant impact on the satisfaction of the search results. Therefore, it is important to analyze and understand the cultural context of images for more accurate image search. In this paper, we investigate how the cultural context of images can affect the performance of image classification. To this end, we first collected various types of images (e.g,. food, temple, etc.) with various cultural contexts (e.g., Korea, Japan, etc.) from web search engines. Afterwards, a deep transfer learning approach using VGG19 and MobileNetV2 pre-trained with ImageNet was adopted to learn the cultural features of the collected images. Through various experiments we show the performance of image classification can be differently affected according to the cultural context of images.

• Educational Technology International
• /
• v.22 no.2
• /
• pp.311-339
• /
• 2021

This study examined the effects of scaffolding types (Toulmin's Argument Pattern: TAP or Argumentation Vee Diagram: AVD) and individual metacognition levels (low or high) on students' learning achievement in online collaborative argumentation. A total of 191 Chinese undergraduates took part in this study. They were randomly assigned to either the TAP scaffolding, AVD scaffolding, or no scaffolding condition. They were teamed up in small groups of two or three students to argue with their peers using SNS as the online collaborative argumentation environment. The results revealed that students in the TAP and AVD scaffolding conditions did not gain significantly higher retention or transfer scores than students without scaffolding. However, students in the TAP scaffolding condition significantly outperformed those in the AVD scaffolding condition on transfer scores. Individual metacognition did not significantly affect learning achievement in online collaborative argumentation. Additionally, there was no significant interaction effect between scaffolding types and individual metacognition levels on retention or on transfer. The findings have implications for scaffolding design for online collaborative argumentation and also suggest that more attention should be paid to social metacognition rather than to individual metacognition when students work collaboratively.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2026-2033
• /
• 2023

Due to Thailand's nuclear energy public acceptance problem, the understanding of nuclear energy public perception was the key factor affecting to re-consideration of the nuclear energy program. Thailand Institute of Nuclear Technology and its alliances together developed the classification model for the nuclear energy public perception from the big data comments on social media using Facebook using deep transfer learning. The objective was to insight into the Thailand nuclear energy public perception on Facebook social media platform using sentiment analysis. The supervised learning was used to generate up-to-date classification model with more than 80% accuracy to classify the public perception on nuclear power plant news on Facebook from 2009 to 2022. The majority of neutral sentiments (80%) represented the opportunity for Thailand to convince people to receive a better nuclear perception. Negative sentiments (14%) showed support for other alternative energies due to nuclear accident concerns while positive sentiments (6%) expressed support for innovative nuclear technologies.