• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1375-1385
• /
• 2022

In this paper, we propose a semi-supervised domain adaptation solution to deal with practical face recognition (FR) scenarios where a single face image for each target identity (to be recognized) is only available in the training phase. Main goal of the proposed method is to reduce the discrepancy between the target and the source domain face images, which ultimately improves FR performances. The proposed method is based on the Domain Adatation network (DAN) using an MMD loss function to reduce the discrepancy between domains. In order to train more effectively, we develop a novel loss function learning strategy in which MMD loss and cross-entropy loss functions are adopted by using different weights according to the progress of each epoch during the learning. The proposed weight adoptation focuses on the training of the source domain in the initial learning phase to learn facial feature information such as eyes, nose, and mouth. After the initial learning is completed, the resulting feature information is used to training a deep network using the target domain images. To evaluate the effectiveness of the proposed method, FR performances were evaluated with pretrained model trained only with CASIA-webface (source images) and fine-tuned model trained only with FERET's gallery (target images) under the same FR scenarios. The experimental results showed that the proposed semi-supervised domain adaptation can be improved by 24.78% compared to the pre-trained model and 28.42% compared to the fine-tuned model. In addition, the proposed method outperformed other state-of-the-arts domain adaptation approaches by 9.41%.

• Journal of Engineering Education Research
• /
• v.25 no.6
• /
• pp.14-22
• /
• 2022

This paper is a basic study of college of engineering freshmen's adaptation to college life, and the relationship between sub-variables of academic self-efficacy, learning immersion, and academic curiosity is analyzed. And based on the results, a plan to support new students of the College of engineering is suggested.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1048-1063
• /
• 2020

In this study, we propose a reinforcement learning agent to control the data transmission rates of nodes in carrier sensing multiple access with collision avoidance (CSMA/CA)-based wireless networks. We design a reinforcement learning (RL) agent, based on Q-learning. The agent learns the environment using the timeout events of packets, which are locally available in data sending nodes. The agent selects actions to control the data transmission rates of nodes that adjust the modulation and coding scheme (MCS) levels of the data packets to utilize the available bandwidth in dynamically changing channel conditions effectively. We use the ns3-gym framework to simulate RL and investigate the effects of the parameters of Q-learning on the performance of the RL agent. The simulation results indicate that the proposed RL agent adequately adjusts the MCS levels according to the changes in the network, and achieves a high throughput comparable to those of the existing data transmission rate adaptation schemes such as Minstrel.

• Journal of Information Science Theory and Practice
• /
• v.1 no.1
• /
• pp.10-26
• /
• 2013

Domain transfer is a widely recognized problem for machine learning algorithms because models built upon one data domain generally do not perform well in another data domain. This is especially a challenge for tasks such as opinion classification, which often has to deal with insufficient quantities of labeled data. This study investigates the feasibility of self-training in dealing with the domain transfer problem in opinion classification via leveraging labeled data in non-target data domain(s) and unlabeled data in the target-domain. Specifically, self-training is evaluated for effectiveness in sparse data situations and feasibility for domain adaptation in opinion classification. Three types of Web content are tested: edited news articles, semi-structured movie reviews, and the informal and unstructured content of the blogosphere. Findings of this study suggest that, when there are limited labeled data, self-training is a promising approach for opinion classification, although the contributions vary across data domains. Significant improvement was demonstrated for the most challenging data domain-the blogosphere-when a domain transfer-based self-training strategy was implemented.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.2 no.1
• /
• pp.1-7
• /
• 2010

Recently, interest in u-learning to pursue effective learning by using ubiquitous environment in teaching and learning activities. In u-learning environment, learners should be able to push necessary information at the right time and the right place. Also calm technology oriented to, and this means that it can recognize learners' terminal information and to provide adaptive interface. In u-learning environment, main learning terminals would be mobile terminals which support mobility. However, learning in the existing PC environment should not be excluded. Thus, by providing adaptive interface according to various learners' terminal in LMS for u-learning, learners are able to learn through consistent and natural learning interface with any computer or any network at any place and at any time. The purpose of this study is to propose the interface adaptation based on terminal information focusing on the layout transformation process in the development environment.

• Journal of Korean Elementary Science Education
• /
• v.23 no.2
• /
• pp.101-109
• /
• 2004

The purpose of this research is to provide useful data in forming sound scientific concepts by investigating elementary students' non-scientific concepts related to their concepts of biological adaptation, and by analyzing the general inclinations and causes of some misconceptions. Twenty-four objective questions were designed to be given to 5th and 6th grade elementary students in order to investigate their concepts of biological adaptation. According to the test results, they formed scientific concepts in most questions. But they appeared to have many misconceptions in some parts which should be guided by the teacher's additional explanations rather than by the education curricula's focus. There are some cases where the 6th grade students had more misconceptions than the 5th grade students who were not systemically taught the concepts of biological adaptation, for the reasons of strengthening or maintaining the misconceptions by confusing the contents of learning. Male and female students have different scientific concepts of different questions according to their interest and attention. Therefore, it is necessary to develop various teaching-learning data which can help the teachers' additional explanations about the concepts of biological adaptation and invoke students' interest and attention, and to seek appropriate measures to form sound scientific concepts among teachers as well as students.

• The Korean Journal of Emergency Medical Services
• /
• v.25 no.2
• /
• pp.157-167
• /
• 2021

Purpose: The study was a qualitative study to examine the synchronous and asynchronous distanced learning experience of online paramedic students during the COVID-19 pandemic. Methods: The subjects included 10 students enrolled in the department of emergency medical service at J City C University. Written consent was provided by the subjects prior to the study, and focus group interviews were then conducted with sufficient explanation. The interviews were recorded and were directly transcribed immediately after the interview. Research results were then derived through content analysis. Results: A total of 4 domains and 9 categories were derived from the experiences of paramedic students on distanced learning. The 4 domains included "distanced lectures type," "student's adaptation and non-adaptation," "change of evaluation," and "learning anxiety." Conclusion: Contents of each domain derived from this study are expected to be used as basic data for the design of the distanced learning in the future.

• ETRI Journal
• /
• v.36 no.3
• /
• pp.429-438
• /
• 2014

Semantic role labeling (SRL) is a task in natural-language processing with the aim of detecting predicates in the text, choosing their correct senses, identifying their associated arguments, and predicting the semantic roles of the arguments. Developing a high-performance SRL system for a domain requires manually annotated training data of large size in the same domain. However, such SRL training data of sufficient size is available only for a few domains. Constructing SRL training data for a new domain is very expensive. Therefore, domain adaptation in SRL can be regarded as an important problem. In this paper, we show that domain adaptation for SRL systems can achieve state-of-the-art performance when based on structural learning and exploiting a prior model approach. We provide experimental results with three different target domains showing that our method is effective even if training data of small size is available for the target domains. According to experimentations, our proposed method outperforms those of other research works by about 2% to 5% in F-score.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.2
• /
• pp.73-81
• /
• 2024

Recently, mobile manipulators have been utilized in agriculture industry for weed removal and harvest automation. This paper proposes a domain adaptive fruit detection method for harvest automation, by utilizing OWL-ViT model which is an open-vocabulary object detection model. The vision-language model can detect objects based on text prompt, and therefore, it can be extended to detect objects of undefined categories. In the development of deep learning models for real-world problems, constructing a large-scale labeled dataset is a time-consuming task and heavily relies on human effort. To reduce the labor-intensive workload, we utilized a large-scale public dataset as a source domain data and employed a domain adaptation method. Adversarial learning was conducted between a domain discriminator and feature extractor to reduce the gap between the distribution of feature vectors from the source domain and our target domain data. We collected a target domain dataset in a real-like environment and conducted experiments to demonstrate the effectiveness of the proposed method. In experiments, the domain adaptation method improved the AP50 metric from 38.88% to 78.59% for detecting objects within the range of 2m, and we achieved 81.7% of manipulation success rate.

• Korean Journal of Remote Sensing
• /
• v.38 no.2
• /
• pp.199-213
• /
• 2022

The unsupervised domain adaptation can solve the impractical issue of repeatedly collecting high-quality training data every year for annual crop classification. This study evaluates the applicability of deep learning-based unsupervised domain adaptation models for crop classification. Three unsupervised domain adaptation models including a deep adaptation network (DAN), a deep reconstruction-classification network, and a domain adversarial neural network (DANN) are quantitatively compared via a crop classification experiment using unmanned aerial vehicle images in Hapcheon-gun and Changnyeong-gun, the major garlic and onion cultivation areas in Korea. As source baseline and target baseline models, convolutional neural networks (CNNs) are additionally applied to evaluate the classification performance of the unsupervised domain adaptation models. The three unsupervised domain adaptation models outperformed the source baseline CNN, but the different classification performances were observed depending on the degree of inconsistency between data distributions in source and target images. The classification accuracy of DAN was higher than that of the other two models when the inconsistency between source and target images was low, whereas DANN has the best classification performance when the inconsistency between source and target images was high. Therefore, the extent to which data distributions of the source and target images match should be considered to select the best unsupervised domain adaptation model to generate reliable classification results.