• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1685-1695
• /
• 2021

To generate a deep learning model with high performance, a large training dataset should be required. However, it requires a lot of time and cost to generate a large training dataset in remote sensing. Therefore, the importance of transfer learning of deep learning model using a small dataset have been increased. In this paper, we performed transfer learning of trained model based on open datasets by using orthoimages and digital maps to detect changes of building objects in multitemporal orthoimages. For this, an initial training was performed on open dataset for change detection through the HRNet-v2 model, and transfer learning was performed on dataset by orthoimages and digital maps. To analyze the effect of transfer learning, change detection results of various deep learning models including deep learning model by transfer learning were evaluated at two test sites. In the experiments, results by transfer learning represented best accuracy, compared to those by other deep learning models. Therefore, it was confirmed that the problem of insufficient training dataset could be solved by using transfer learning, and the change detection algorithm could be effectively applied to various remote sensed imagery.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.2
• /
• pp.351-358
• /
• 2018

Reinforcement learning is a machine learning method which aims to determine a policy to get optimal actions in dynamic and stochastic environments. But reinforcement learning has high computational complexity and needs a lot of time to get solution, so it is not easily applicable to uncertain and continuous environments. To tackle the complexity problem, AC (actor-critic) method is used and it separates an action-value function into a value function and an action decision policy. Also, in transfer learning method, the knowledge constructed in one environment is adapted to another environment, so it reduces the time to learn in a reinforcement learning method. In this paper, we present AC method and transfer learning method to solve the problem of a reinforcement learning method. Finally, we analyze the case study which a transfer learning method is used to solve BS(base station) switching problem in wireless access networks.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.30-37
• /
• 2022

Disease threatens plant growth and recognizing the type of disease is essential to making a remedy. In recent years, deep learning has witnessed a significant improvement for this task, however, a large volume of labeled images is one of the requirements to get decent performance. But annotated images are difficult and expensive to obtain in the agricultural field. Therefore, designing an efficient and effective strategy is one of the challenges in this area with few labeled data. Transfer learning, assuming taking knowledge from a source domain to a target domain, is borrowed to address this issue and observed comparable results. However, current transfer learning strategies can be regarded as a supervised method as it hypothesizes that there are many labeled images in a source domain. In contrast, unsupervised transfer learning, using only images in a source domain, gives more convenience as collecting images is much easier than annotating. In this paper, we leverage unsupervised transfer learning to perform plant disease recognition, by which we achieve a better performance than supervised transfer learning in many cases. Besides, a vision transformer with a bigger model capacity than convolution is utilized to have a better-pretrained feature space. With the vision transformer-based unsupervised transfer learning, we achieve better results than current works in two datasets. Especially, we obtain 97.3% accuracy with only 30 training images for each class in the Plant Village dataset. We hope that our work can encourage the community to pay attention to vision transformer-based unsupervised transfer learning in the agricultural field when with few labeled images.

• East Asian Journal of Business Economics (EAJBE)
• /
• v.5 no.4
• /
• pp.20-38
• /
• 2017

Purpose - this study analyzes the impact of restaurant startup education on transfer effects in learning and entrepreneurial intentions based on previous research. Also, problems and ways to provide effective business startup education for a restaurant founder will be proposed based on the result. Research design, data, methodolog - this study collected surveys by conducting direct investigation. From July 20th of 2016 to September 20th of 2016 (approximately 60 days), the survey was collected. Out of 540 surveys, 520 were collected. And excepting 9 surveys which were untrustworthily conducted, total 511 surveys were used for the analysis. Results - First, as a result of the impact of which factor of a restaurant founder's startup education has a positive impact on transfer effect in learning (the satisfaction of startup education and learning transfer), law education, entrepreneurship education and business district analysis education and practical education have turned out be positively related variables. Secondly, as a result of the impact of a restaurant founder's startup education satisfaction on transfer in learning, it has been identified that startup education has a positive impact. Lastly, by conducting an analysis to find out which factor from a restaurant founder's transfer effect in learning has an impact on entrepreneurial intention, all variables, including startup education satisfaction and transfer effect in learning, are positively influencing factors. Conclusions - as startup education satisfaction of a restaurant founder is increasing, there is a higher level of transfer effect in learning. Moreover, as transfer effect of startup business is getting higher, it has an impact on entrepreneurial intention.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.4
• /
• pp.474-484
• /
• 2024

Reinforcement learning, which are also studied in the field of defense, face the problem of sample efficiency, which requires a large amount of data to train. Transfer learning has been introduced to address this problem, but its effectiveness is sometimes marginal because the model does not effectively leverage prior knowledge. In this study, we propose a stochastic initial state randomization(SISR) method to enable robust knowledge transfer that promote generalized and sufficient knowledge transfer. We developed a simulation environment involving a cooperative robot transportation task. Experimental results show that successful tasks are achieved when SISR is applied, while tasks fail when SISR is not applied. We also analyzed how the amount of state information collected by the agents changes with the application of SISR.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.10
• /
• pp.332-340
• /
• 2019

This descriptive research study was undertaken to identify the degree of learning motivation, transfer climate, learning self-efficacy, and transfer motivation, and to correlate the variables, in nursing students receiving simulation-based education. The subjects of this study were 4th grade nursing students who completed a simulation course at a nursing university; data collected using the self-report questionnaire were analyzed using the SPSS 21.0 program. Our results indicate high values of learning motivation, transfer climate (including the lower variables supervisor's support, peer's support, and transfer opportunity), learning self-efficacy, and transfer motivation. Learning motivation, learning self-efficacy, and transfer motivation significantly differed with respect to social motivation for entering school (Z=6.04, p=0.049; Z=6.92, p=0.031; Z=9.16, p=0.010, respectively) and major satisfaction (Z=8.55, p=0.036; Z=12.55, p=0.006; Z=13.47, p=0.004, respectively). All these variables were positively correlated, especially transfer motivation with learning motivation, supervisor's support, peer's support, transfer opportunity, and learning self-efficacy. Taken together, the results of this study indicate a need to develop an effective simulation-based education program to encourage transfer motivation, as well as follow-up studies that verify the causal relationship between transfer motivation and related variables.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.845-850
• /
• 2023

In this paper, we propose a method for diagnosing ball bearing vibration using transfer learning. STFT, which can analyze vibration signals in time-frequency, was used as input to CNN to diagnose failures. In order to rapidly learn CNN-based deep artificial neural networks and improve diagnostic performance, we proposed a transfer learning-based deep learning learning technique. For transfer learning, the feature extractor and classifier were selectively learned using a VGG-based image classification model, the data set for learning was publicly available ball bearing vibration data provided by Case Western Reserve University, and performance was evaluated by comparing the proposed method with the existing CNN model. Experimental results not only prove that transfer learning is useful for condition diagnosis in ball bearing vibration data, but also allow other industries to use transfer learning to improve condition diagnosis.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.1
• /
• pp.10-22
• /
• 2021

Purpose: To overcome the difficulty in building a large data set with a high-quality in medical imaging, a concept of 'blended-transfer learning' (BTL) using a combination of both source data and target data is proposed for the target task. Materials and Methods: Source and target tasks were defined as training of the source and target networks to reconstruct cardiac CINE images from undersampled data, respectively. In transfer learning (TL), the entire neural network (NN) or some parts of the NN after conducting a source task using an open data set was adopted in the target network as the initial network to improve the learning speed and the performance of the target task. Using BTL, an NN effectively learned the target data while preserving knowledge from the source data to the maximum extent possible. The ratio of the source data to the target data was reduced stepwise from 1 in the initial stage to 0 in the final stage. Results: NN that performed BTL showed an improved performance compared to those that performed TL or standalone learning (SL). Generalization of NN was also better achieved. The learning curve was evaluated using normalized mean square error (NMSE) of reconstructed images for both target data and source data. BTL reduced the learning time by 1.25 to 100 times and provided better image quality. Its NMSE was 3% to 8% lower than with SL. Conclusion: The NN that performed the proposed BTL showed the best performance in terms of learning speed and learning curve. It also showed the highest reconstructed-image quality with the lowest NMSE for the test data set. Thus, BTL is an effective way of learning for NNs in the medical-imaging domain where both quality and quantity of data are always limited.

• Journal of Engineering Education Research
• /
• v.12 no.3
• /
• pp.3-12
• /
• 2009

The recent development of engineering design education has brought enormous influence in many engineering educations. But, most studies in this area have focused only on the system or curriculum development rather than on the effect of the program to the real situation, the transfer. The purpose of this study is to identify the effects of learning and learning transfer in engineering design program at the university level. Transfer is defined as the use of trained knowledge and skill back on the job. The results of the study are as follows. First, learner characteristics and curriculum design had a significant influence on learning effectiveness. Second, learner characteristics had a significant influence an learning transfer. Also, the learning had a significant influence an learning transfer.

• Educational Technology International
• /
• v.16 no.2
• /
• pp.183-200
• /
• 2015

This study investigated the effect of learning achievements and cognitive load according to different types of presenting learning materials and epistemological beliefs (EB). Learning achievements in this study were composed by retention and transfer of ill-structured problem. A total of 80 college students participated in the study. Prior to the learning, students were guided to fill out a questionnaire regarding epistemological beliefs and a prior knowledge test. The students of each group studied with a different type of reading material: full text (FT), full text including key questions (KeyFT) and full text including a concept map (CmFT). After a session of study was finished, they were asked to complete the posttest: retention and transfer. The results showed that there was a significant difference in transfer achievements. CmFT outperformed higher scores than the other types. There was no significant difference in retention among the groups. It is strongly believed that the types of presenting learning materials may have affected the understanding of ill-structured problem solving skills. Students with sophisticated EB showed higher achievements on retention and transfer than naive-EB and mixed-EB. Even though the data showed decrease of the cognitive load on the type of materials and EB, there were no significant differences on the cognitive load. We should consider a positive effect of types of presenting learning materials and EB enhancing capabilities of solving ill-structured problems in real life.