• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.135-145
• /
• 2020

Recently, deep-learning based methods for low-light image enhancement accomplish great success through supervised learning. However, they still suffer from the lack of sufficient training data due to difficulty of obtaining a large amount of low-/normal-light image pairs in real environments. In this paper, we propose an unsupervised learning approach for single low-light image enhancement using the bright channel prior (BCP), which gives the constraint that the brightest pixel in a small patch is likely to be close to 1. With this prior, pseudo ground-truth is first generated to establish an unsupervised loss function. The proposed enhancement network is then trained using the proposed unsupervised loss function. To the best of our knowledge, this is the first attempt that performs a low-light image enhancement through unsupervised learning. In addition, we introduce a self-attention map for preserving image details and naturalness in the enhanced result. We validate the proposed method on various public datasets, demonstrating that our method achieves competitive performance over state-of-the-arts.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4317-4335
• /
• 2018

Semi-supervised multi-view latent space learning is gaining considerable popularity recently in many machine learning applications due to the high cost and difficulty to obtain the large amount of label information of data. Although some semi-supervised multi-view latent space learning methods have been presented, there is still much space for improvement: 1) How to learn latent discriminant intact feature representations by employing data of multiple views; 2) How to exploit the manifold structure of both labeled and unlabeled point in the learned latent intact space effectively. To address the above issues, we propose an approach called semi-supervised multi-view manifold discriminant intact space learning ($SM^2DIS$) for image classification in this paper. $SM^2DIS$ aims to seek a manifold discriminant intact space for data of different views by making use of both the discriminant information of labeled data and the manifold structure of both labeled and unlabeled data. Experimental results on MNIST, COIL-20, Multi-PIE, and Caltech-101 databases demonstrate the effectiveness and robustness of our proposed approach.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.515-522
• /
• 2021

It is hard to prepare sufficient training data for speech emotion recognition due to the difficulty of emotion labeling. In this paper, we apply transfer learning with large-scale training data for speech recognition on a transformer-based model to improve the performance of speech emotion recognition. In addition, we propose a method to utilize context information without decoding by multi-task learning with speech recognition. According to the speech emotion recognition experiments using the IEMOCAP dataset, our model achieves a weighted accuracy of 70.6 % and an unweighted accuracy of 71.6 %, which shows that the proposed method is effective in improving the performance of speech emotion recognition.

• The KIPS Transactions:PartA
• /
• v.10A no.4
• /
• pp.321-330
• /
• 2003

This paper proposes an agent-based adaptive tutoring system that monitors learning process of learners' and provides learning materials dynamically according to the analyzed learning character. Furthermore, it uses fuzzy concept to evaluate learners' ability and to provide learning materials appropriate to the level of learners'. For this, we design a courseware knowledge structure systematically and then construct a fuzzy level set on the basis of it considering importance of learning targets, difficulty of learning materials and relation degree between learning targets and learning materials. Using agent, monitoring continually the learning process of learners 'inferencing to offer proper hints in case of incorrect answer in learning assesment, composing dynamically learning materials according to the learning feature and the evaluation of assesment, our system implements effectively adaptive instruction system. Moreover, appling the fuzzy concept to the system could naturally consider and ideal with various and uncertain items of learning environment thus could offer more flexible and effective instruction-learning methods.

• Journal of the Korea Convergence Society
• /
• v.9 no.2
• /
• pp.85-90
• /
• 2018

The purpose of this study is to analyze the effect of flipped learning strategy, which is an online offline convergence learning strategy becoming a hot issue, on students' learning styles..Ultimately, the goal is to analyze the academic achievements and learning attitudes by applying the flipped learning strategy considering the preferred learning styles of Korean students. By assuming that Korean students are accustomed to traditional lecture class, it is assumed that the students would have difficulty in applying the flipped learning strategy which involves information gathering and problem solving through discussion. In order to analyze whether the application of flipped learning strategy is effective, it is necessary to identify students' preferred learning style and to develop appropriate teaching strategies accordingly.

• Journal of Korean Physical Therapy Science
• /
• v.28 no.1
• /
• pp.33-45
• /
• 2021

Background: Children with cerebral palsy have difficulty acquiring motor skills through motor learning due to lack of motor planning of the central nervous system and musculoskeletal dysfunction. Motor learning is the acquisition or modification of movements with the aim of developing skilled movements and behaviors. Cerebral palsy improve motor function through motor learning, and effective motor learning mainly depends on practice parameters such as learning feedback. Therefore, we investigate the effect of motor learning in children with cerebral palsy and try to present the possibility of clinical application. Design: A systemic review. Methods: Research papers were published from Jan, 2010 to Dec, 2020 and were searched using PubMed and Medline. The search terms are 'task specific training' OR 'motor learning' OR 'feedback(Mesh term)' OR 'goal activity' AND 'cerebral palsy(Mesh term)'. A total of eight papers were analyzed in this study. The paper presented the quality level based on the research evidence, and also presented PEDro (Physiotherapy Evidence Database) scores to evaluate the quality of design studies in randomized clinical trials. Results: The results showed that motor learning coaching in children with cerebral palsy improved motor function in post and follow up tests. Also, self-control feedback of motor learning is more effective than external control feedback. 100% external control feedback of motor learning is effective in the acquisition phase and 50% external feedback of motor learning is effective in the retain phase. Conclusion: These results suggest that it will be an important data for establishing evidence on the effect of motor learning arbitration methods in children with cerebral palsy to develop clinical applicability and protocols.

• Journal of The Korean Association of Information Education
• /
• v.6 no.2
• /
• pp.212-224
• /
• 2002

The purpose of this study is to design and implement the web-based counselling system in aspects of learning type and method by PBL in Constructivism. Learning problem is classified into learning difficulty, learning disability, emotional disability, memory/cognition, ADHD(attention deficit hyperactivity disorder), classwork, and school circumstance. Counselling for individual, offline visit, parents, electronic mail, and group with professionals who were involved in the design and implementation of learning counselling were used to supplement the clinic process for learning. The result of this study aims to administer the distance counselling system for learning without prominent computer knowledge. Each learner can solve diverse private learning problems which can be widely applied for situated learning. Also these online strategies by PBL indicate that providing learning types and methods are critical for overall understanding in online counselling system for learning.

• Journal of Convergence for Information Technology
• /
• v.10 no.6
• /
• pp.87-95
• /
• 2020

Previously, there were no studies that were not aware of the importance of video, were interested in the educational value of Flipped Learning, and there were many wrong experiments because they did not understand Flipped Learning. Therefore, an accurate understanding of Flipped Learning is needed. This study proposed the caution of video learning of Flipped Learning and presented the papers and grounds to support to examine the educational value of Flipped Learning. A video of the lecture should be produced with a core content of 10 to 15 minutes, and found that the educational value of Flipped Learning lies in self-directed learning, cooperative learning, habruta, overcoming the oblivion curve and metacognition. It is hoped that this study will provide good guidance and direction of education for teachers who have difficulty Flipped Learning.

• Journal of Science Education
• /
• v.41 no.2
• /
• pp.213-225
• /
• 2017

Most students have difficulties and negative perceptions about physics learning. Especially, it is difficult to understand the whole context by learning based on logical-scientific thinking which excludes narrative thinking. This study aims to develop a storytelling teaching-learning method using the narrative thinking in physics lessons for improving the difficulty of students of physics learning, For this purpose, a storytelling teaching-learning method that can improve scientific attitude and understand and change the concepts was developed through literature research. The following results were confirmed its effects to apply high school students and middle school students. First, the teaching-learning method using the storytelling for high school students with low interest in learning had a significant effect in science-related occupation, interest in science and science-related activities, criticism, openness, cooperation, and spontaneity. Second, the middle school students who are active in learning recognized that teaching and learning methods using storytelling helped to understand physics concepts. The storytelling teaching-learning method developed through this study is expected to stimulate students' interest and motivation in physics and to be useful for learning concepts by improving their scientific thinking skills.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.5
• /
• pp.155-162
• /
• 2021

n-step TD learning is a combination of Monte Carlo method and one-step TD learning. If appropriate n is selected, n-step TD learning is known as an algorithm that performs better than Monte Carlo method and 1-step TD learning, but it is difficult to select the best values of n. In order to solve the difficulty of selecting the values of n in n-step TD learning, in this paper, using the characteristic that overestimation of Q can improve the performance of initial learning and that all n-step returns have similar values for Q ≈ Q^*, we propose a new learning target, which is composed of the maximum and the mean of all k-step returns for 1 ≤ k ≤ n. Finally, in OpenAI Gym's Atari game environment, we compare the proposed algorithm with n-step TD learning and proved that the proposed algorithm is superior to n-step TD learning algorithm.