• International Journal of Control, Automation, and Systems
• /
• v.1 no.2
• /
• pp.194-202
• /
• 2003

In this paper, we introduce a category of Multi-FNN (Fuzzy-Neural Networks) models, analyze the underlying architectures and propose a comprehensive identification framework. The proposed Multi-FNNs dwell on a concept of fuzzy rule-based FNNs based on HCM clustering and evolutionary fuzzy granulation, and exploit linear inference being treated as a generic inference mechanism. By this nature, this FNN model is geared toward capturing relationships between information granules known as fuzzy sets. The form of the information granules themselves (in particular their distribution and a type of membership function) becomes an important design feature of the FNN model contributing to its structural as well as parametric optimization. The identification environment uses clustering techniques (Hard C - Means, HCM) and exploits genetic optimization as a vehicle of global optimization. The global optimization is augmented by more refined gradient-based learning mechanisms such as standard back-propagation. The HCM algorithm, whose role is to carry out preprocessing of the process data for system modeling, is utilized to determine the structure of Multi-FNNs. The detailed parameters of the Multi-FNN (such as apexes of membership functions, learning rates and momentum coefficients) are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. To evaluate the performance of the proposed model, two numeric data sets are experimented with. One is the numerical data coming from a description of a certain nonlinear function and the other is NOx emission process data from a gas turbine power plant.

• Journal of Digital Contents Society
• /
• v.14 no.3
• /
• pp.333-341
• /
• 2013

Robot education has the favorable influence on creativity and problem-solving ability of students. Therefore, it is commonly known to elementary school students, their parents and teacher through robot education for after school and contests. However, it has not been actively taught at university of education students because of the lack of systematic education program. In this paper, we have developed robot education program using problem-based learning and educational robot for pre-service elementary teachers. We have examined their recognition on robot education and education program after applying the developed program. Interviews for improving robot education program were also conducted. We find out robot education program has the favorable influence on the recognition, satisfaction and effectiveness for robot education. In particular, we know that education will related to robot was augmented by this education program.

• Smart Media Journal
• /
• v.7 no.1
• /
• pp.31-36
• /
• 2018

In this paper, we propose automatic screen on / off method of OST-HMD screen using gaze depth estimation technique. The proposed method uses MLP (Multi-layer Perceptron) to learn the user's gaze information and the corresponding distance of the object, and inputs the gaze information to estimate the distance. In the learning phase, eye-related features obtained using a wearable eye-tracker. These features are then entered into the Multi-layer Perceptron (MLP) for learning and model generation. In the inference step, eye - related features obtained from the eye tracker in real time input to the MLP to obtain the estimated depth value. Finally, we use the results of this calculation to determine whether to turn the display of the HMD on or off. A prototype was implemented and experiments were conducted to evaluate the feasibility of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.837-852
• /
• 2021

Recurrent neural network (RNN) architectures have been used for language modeling (LM) tasks that require learning long-range word or character sequences. However, the RNN architecture is still suffered from unstable gradients on long-range sequences. To address the issue of long-range sequences, an attention mechanism has been used, showing state-of-the-art (SOTA) performance in all LM tasks. A differentiable neural computer (DNC) is a deep learning architecture using an attention mechanism. The DNC architecture is a neural network augmented with a content-addressable external memory. However, in the write operation, some information unrelated to the input word remains in memory. Moreover, DNCs have been found to perform poorly with low numbers of weight parameters. Therefore, we propose a robust memory deallocation method using a limited retention vector. The limited retention vector determines whether the network increases or decreases its usage of information in external memory according to a threshold. We experimentally evaluate the robustness of a DNC implementing the proposed approach according to the size of the controller and external memory on the enwik8 LM task. When we decreased the number of weight parameters by 32.47%, the proposed DNC showed a low bits-per-character (BPC) degradation of 4.30%, demonstrating the effectiveness of our approach in language modeling tasks.

• Phonetics and Speech Sciences
• /
• v.12 no.4
• /
• pp.63-71
• /
• 2020

Speech recognition is one of the areas actively commercialized using deep learning and machine learning techniques. However, the majority of speech recognition systems on the market are developed on data with limited diversity of speakers and tend to perform well on typical adult speakers only. This is because most of the speech recognition models are generally learned using a speech database obtained from adult males and females. This tends to cause problems in recognizing the speech of the elderly, children and people with dialects well. To solve these problems, it may be necessary to retain big database or to collect a data for applying a speaker adaptation. However, this paper proposes that a new end-to-end speech recognition method consists of an acoustic augmented recurrent encoder and a transformer decoder with linguistic prediction. The proposed method can bring about the reliable performance of acoustic and language models in limited data conditions. The proposed method was evaluated to recognize Korean elderly and children speech with limited amount of training data and showed the better performance compared of a conventional method.

• Journal of The Korean Association of Information Education
• /
• v.26 no.3
• /
• pp.219-227
• /
• 2022

Students are always preparing for remote classes while taking face-to-face classes due to COVID-19. However, it is true that the class satisfaction with distance learning is not high for students and teachers. The idea that even if remote classes are conducted at home, it would be nice to have classes together like real ones, the need for a virtual world education program that utilizes augmented reality and virtual reality based on the metaverse has emerged. However, there are very few studies that teachers try to apply them to their classes. In this study, a metaverse application curriculum was presented for elementary science and 'space' domains. To implement the metaverse, ZEPETO and COSPACIS EDU were used. In the analysis of content creation with students and evaluation with schoolmates, this study showed that the concentration of learning was increased and creativity improved in the 'real', 'individual', and 'society' domains.

• Imaging Science in Dentistry
• /
• v.52 no.4
• /
• pp.383-391
• /
• 2022

Purpose: Periodontitis, the most prevalent chronic inflammatory condition affecting teeth-supporting tissues, is diagnosed and classified through clinical and radiographic examinations. The staging of periodontitis using panoramic radiographs provides information for designing computer-assisted diagnostic systems. Performing image segmentation in periodontitis is required for image processing in diagnostic applications. This study evaluated image segmentation for periodontitis staging based on deep learning approaches. Materials and Methods: Multi-Label U-Net and Mask R-CNN models were compared for image segmentation to detect periodontitis using 100 digital panoramic radiographs. Normal conditions and 4 stages of periodontitis were annotated on these panoramic radiographs. A total of 1100 original and augmented images were then randomly divided into a training (75%) dataset to produce segmentation models and a testing (25%) dataset to determine the evaluation metrics of the segmentation models. Results: The performance of the segmentation models against the radiographic diagnosis of periodontitis conducted by a dentist was described by evaluation metrics(i.e., dice coefficient and intersection-over-union [IoU] score). MultiLabel U-Net achieved a dice coefficient of 0.96 and an IoU score of 0.97. Meanwhile, Mask R-CNN attained a dice coefficient of 0.87 and an IoU score of 0.74. U-Net showed the characteristic of semantic segmentation, and Mask R-CNN performed instance segmentation with accuracy, precision, recall, and F1-score values of 95%, 85.6%, 88.2%, and 86.6%, respectively. Conclusion: Multi-Label U-Net produced superior image segmentation to that of Mask R-CNN. The authors recommend integrating it with other techniques to develop hybrid models for automatic periodontitis detection.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.6 no.11
• /
• pp.519-528
• /
• 2016

Most cultural contents currently we face are not suitable for associating with state of arts and high technology as simply providing one-sided learning. Pictures and movies of cultural contents also sees to utilize for efficacy of cultural education. There are still some limitations to draw interest from users when providing one-sided learning for cultural study, which aims to only deliver knowledge itself. In this paper, we propose interactive HMD VR cultural contents that can support more experience to get rid of aforementioned limitations. To this end, we first select quite interesting and wellknown cultural contents from world wide to draw more attention and effect. To increase immersion, presence and interactivity we have used HMD VR and Leapmotion, which intentionally draws more attention to increase interest. The cultural contents also facilitate augmented information as well as puzzle gaming components. To verify, we have carried out a user study as well.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.494-497
• /
• 2012

Black marker cause unnatural problems between the existing various contents and marker. To solve this problem, we tested the various colors and color placement according to frequency of 3D objects. Based on this, infant's learning content system based NyARToolkit for the mobile-based augmented reality was implemented. We are solved the unnatural problems by insert to color marker in the Implemented system. and infant can study seamlessly because concentration increases by the familiar character on the markers.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.764-765
• /
• 2016

다양한 체험 중 인체의 신비에 관심이 있는 아이들을 위한 교육 목적의 중강현실을 마이크로소프트 키넥트 장비를 활용해서 구현하였다. 기존에 책의 이미지와 마네킹을 통해 인체 장기의 구조를 학습하는 방법에서 한 단계 발전시켜 아이들의 상체에 증강현실로 인체 장기 구조 이미지를 보여줌으로써 색다른 체험을 제공하는 흥미로운 학습 방법을 제시하고 있다. 추가적인 기능으로, 아이들의 성장 발달에 도움을 주는 게임 및 추억을 간직할 수 있는 촬영 기능도 제공하고 있다. 이 기법은 건강 교육 체험에 활용하여 흡연자의 폐와 과음한 사람의 간 등을 당사자의 상체에 중강현실로 보여주어 건강하지 못한 인체 장기 구조를 체험해 기존 방식보다 더욱 현실감이 있는 체험적인 건강 교육으로 활용될 것으로 기대한다.