• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.960-966
• /
• 2009

A manifold is used to represent a relationship between high-dimensional data samples in low-dimensional space. In human pose estimation, it is created in low-dimensional space for processing image and 3D body configuration data. Manifold learning is to build a manifold. But it is vulnerable to silhouette variations. Such silhouette variations are occurred due to view-change, person-change, distance-change, and noises. Representing silhouette variations in a single manifold is impossible. In this paper, we focus a silhouette variation problem occurred by view-change. In previous view invariant pose estimation methods based on manifold learning, there were two ways. One is modeling manifolds for all view points. The other is to extract view factors from mapping functions. But these methods do not support one by one mapping for silhouettes and corresponding body configurations because of unsupervised learning. Modeling manifold and extracting view factors are very complex. So we propose a method based on triple manifolds. These are view manifold, pose manifold, and body configuration manifold. In order to build manifolds, we employ biased manifold learning. After building manifolds, we learn mapping functions among spaces (2D image space, pose manifold space, view manifold space, body configuration manifold space, 3D body configuration space). In our experiments, we could estimate various body poses from 24 view points.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.2093-2108
• /
• 2017

In this paper, we describe a novel method for recognizing human actions from different views via view knowledge transfer. Our approach is characterized by two aspects: 1) We propose a unsupervised topic transfer model (TTM) to model two view-dependent vocabularies, where the original bag of visual words (BoVW) representation can be transferred into a bag of topics (BoT) representation. The higher-level BoT features, which can be shared across views, can connect action models for different views. 2) Our features make it possible to obtain a discriminative model of action under one view and categorize actions in another view. We tested our approach on the IXMAS data set, and the results are promising, given such a simple approach. In addition, we also demonstrate a supervised topic transfer model (STTM), which can combine transfer feature learning and discriminative classifier learning into one framework.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.174-184
• /
• 2022

3D human pose estimation models can be classified into a multi-view model and a single-view model. In general, the multi-view model shows superior pose estimation performance compared to the single-view model. In the case of the single-view model, the improvement of the 3D pose estimation performance requires a large amount of training data. However, it is not easy to obtain annotations for training 3D pose estimation models. To address this problem, we propose a method to generate pseudo ground-truths of multi-view human pose data from a multi-view model and exploit the resultant pseudo ground-truths to train a single-view model. In addition, we propose a multi-view consistency loss function that considers the consistency of poses estimated from multi-view images, showing that the proposed loss helps the effective training of single-view models. Experiments using Human3.6M and MPI-INF-3DHP datasets show that the proposed method is effective for training single-view 3D human pose estimation models.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.11 no.3
• /
• pp.39-45
• /
• 2002

The computer technology and internet have the potential to provide a highly interactive and powerful learning environment for engineering disciplines. Many academic courses that teach engineering subjects have already begun incorporating virtual instruments as teaching and learning tools. This paper introduces the concept of the virtual instrument and reports some of the LabVIEW software applications in several universities. Finally the paper contemplates the future trends on the remote laboratory via the internet for engineering education.

• Journal of the Korean Data and Information Science Society
• /
• v.12 no.2
• /
• pp.83-93
• /
• 2001

We investigate a kernel approach to discriminant analysis for binary classification as a machine learning point of view. Our view of the kernel approach follows support vector method which is one of the most promising techniques in the area of machine learning. As usual discriminant analysis, the kernel method can discriminate an object most likely belongs to. Moreover, it has some advantage over discriminant analysis such as data compression and computing time.

• Journal of The Korean Association For Science Education
• /
• v.5 no.2
• /
• pp.81-88
• /
• 1985

The purpose of the study was to establish a new view of textbook which may contribute to the abolishment of the instruction mainly based on the only textbook and to the promotion of creativities of students. We first reviewed science textbooks and related teaching-learning materials of foreign countries with emphasis on the relationship among textbook and teaching-learning materials and practical use of them. In western countries the roles of traditional textbook has been changed. That is, various kinds of materials such as reading book, work-book, worksheet, experimental guidebook, filmstrips are used to raise effect of instruction besides of traditional type of textbook. Secondary, we identified the problems related to the science textbook-view of textbook, textbook contents, practical use of textbook-through opinion survey administered to principals akd teachers of elementary schools. The results of the survey are as follows; Concerning the view of textbook, most teachers did not recognize textbook as an absolute materials. They thought that textbook contents could be taught reorganized according to their judgements. On the contrary, teachers responded to the question of whether or not they follow contents of textbook as they are presented in it were approximately 30%. Further, more than 75% of them have seldom used instructional materials except textbooks. In order to revise the problems of our present textbook as stated above, a new view of textbook should be established. We, above all, established 4 basic premises for searching a new view of textbook. 1) Textbook should not be considered as the only material but as being at the center of various teaching -learning materials. 2) The importance of textbook should be illustrated Among Curriculum, textbook and related teaching-learning materials, instruction and evaluation. 3. Textbook contents should not be regarded as definitely fixed or absolute ones. 4. Human being can understand environment more fully by commanding his swnsory organ multilaterally. Under these premises we disscussed about curriculum and textbook, textbook, and instruction, akd evaluation method.

• Journal of the Korean Society of Radiology
• /
• v.16 no.3
• /
• pp.295-302
• /
• 2022

Sparse-view computed tomography (CT) imaging technique is able to reduce radiation dose, ensure the uniformity of image characteristics among projections and suppress noise. However, the reconstructed images obtained by the sparse-view CT imaging technique suffer from severe artifacts, resulting in the distortion of image quality and internal structures. In this study, we proposed a convolutional neural network (CNN) with wavelet transformation and residual learning for reducing artifacts in sparse-view CT image, and the performance of the trained model was quantitatively analyzed. The CNN consisted of wavelet transformation, convolutional and inverse wavelet transformation layers, and input and output images were configured as sparse-view CT images and residual images, respectively. For training the CNN, the loss function was calculated by using mean squared error (MSE), and the Adam function was used as an optimizer. Result images were obtained by subtracting the residual images, which were predicted by the trained model, from sparse-view CT images. The quantitative accuracy of the result images were measured in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The results showed that the trained model is able to improve the spatial resolution of the result images as well as reduce artifacts in sparse-view CT images effectively. Also, the trained model increased the PSNR and SSIM by 8.18% and 19.71% in comparison to the imaging model trained without wavelet transformation and residual learning, respectively. Therefore, the imaging model proposed in this study can restore the image quality of sparse-view CT image by reducing artifacts, improving spatial resolution and quantitative accuracy.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2000.11a
• /
• pp.59-60
• /
• 2000

The past few years have seen a dramatic increase in gene expression data on the basis of DNA microarrays or DNA chips. Going beyond a generic view on the genome, microarray data are able to distinguish between gene populations in different tissues of the same organism and in different states of cells belonging to the same tissue. This affords a cell-wide view of the metabolic and regulatory processes under different conditions, building an effective basis for new diagnoses and therapies of diseases. In this talk we present machine learning techniques for effective mining of DNA microarray data. A brief introduction to the research field of machine learning from the computer science and artificial intelligence point of view is followed by a review of recently-developed learning algorithms applied to the analysis of DNA chip gene expression data. Emphasis is put on graphical models, such as Bayesian networks, latent variable models, and generative topographic mapping. Finally, we report on our own results of applying these learning methods to two important problems: the identification of cell cycle-regulated genes and the discovery of cancer classes by gene expression monitoring. The data sets are provided by the competition CAMDA-2000, the Critical Assessment of Techniques for Microarray Data Mining.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.2 no.2
• /
• pp.91-98
• /
• 2010

In this paper, we looked around an effective teaching plan base on the LabVIEW by utilizing the USB type DAQ device. Moreover, we have been learning the concept of control and instrumentation engineering through theory and practice classwork in the various field of engineering, come to automation engineering as well as electricity, electronic, telecommunication and computer science. In case of the best learning to understand the concept and operate the practice, we'd like to propose the application technique to make use of the PC based on LabVIEW software with USB type DAQ devices, better than to depend upon the expensive equipment as before. As a result, we hope that this technique to be considered easily accessible to understand anyone and expect distinguished applications.

• Journal of the Korean Geographical Society
• /
• v.32 no.4
• /
• pp.511-520
• /
• 1997

As the spatial analysis paradigm was established in the discipline during the 1960s, the regional geography became regrded as a nonscientific enterprise. However, school geography has remained an old fashioned regional paradigm. Since then, regional framework which characterized geography curricula in education has been attacked and replaced by more scientific and systematic content. But recently, globalization and localization has rapidly transformed the everyday life of ordinary people. This social change requires regional awareness in school. The purpose of this study is to find relevant learning theories for geography in deucation and to suggest principles of constructing content for regional geography. We must transform the logic of regional concepts into educational content with reference to the learning process. We must examine various propositions for the leaming process. According to the Atomic view of knowledge, the learning process is cumulative, but this can't be applied to sophisticated knowledge. In the Organic view, the learning process is regarded as gradual differentiation. But the learning process is reciprocal, and socially constructed. Applied to geography in education, this view regard "meaningful learning" as social interaction between student's private geographies and content based on public (or academic) geographies.