• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.8
• /
• pp.989-996
• /
• 2010

Statistical regression and/or interpolation models have been used for data analysis and response prediction using the results of the physical experiments and/or computer simulations in structural engineering fields. These models have been employed during the last decade to develop a variety of design methodologies. However, these models only handled responses with respect to space variables such as size and shape of structures and cannot handle time-variant dynamic responses, i.e. response varying with time. In this research, statistical space-time metamodels based on multiple response approach that can handle responses with respect to both space variables and a time variable are proposed. Regression and interpolation models such as the response surface model (RSM) and kriging model were developed for handling time-variant dynamic responses of structural engineering. We evaluate the accuracies of the responses predicted by the two statistical space-time metamodels by comparing them with the responses obtained by the physical experiments and/or computer simulations.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.2E
• /
• pp.100-106
• /
• 2010

Multiple-model speech recognizer has been shown to be quite successful in noisy speech recognition. However, its performance has usually been tested using the general speech front-ends which do not incorporate any noise adaptive algorithms. For the accurate evaluation of the effectiveness of the multiple-model frame in noisy speech recognition, we used the state-of-the-art front-ends and compared its performance with the well-known multi-style training method. In addition, we improved the multiple-model speech recognizer by employing N-best reference HMMs for interpolation and using multiple SNR levels for training each of the reference HMM.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.6
• /
• pp.473-480
• /
• 2004

In this paper we propose an effective feature compensation scheme based on the speech model in order to achieve robust speech recognition. The proposed feature compensation method is based on parallel combined mixture model (PCMM). The previous PCMM works require a highly sophisticated procedure for estimation of the combined mixture model in order to reflect the time-varying noisy conditions at every utterance. The proposed schemes can cope with the time-varying background noise by employing the interpolation method of the multiple mixture models. We apply the‘data-driven’method to PCMM tot move reliable model combination and introduce a frame-synched version for estimation of environments posteriori. In order to reduce the computational complexity due to multiple models, we propose a technique for mixture sharing. The statistically similar Gaussian components are selected and the smoothed versions are generated for sharing. The performance is examined over Aurora 2.0 and speech corpus recorded while car-driving. The experimental results indicate that the proposed schemes are effective in realizing robust speech recognition and reducing the computational complexities under both simulated environments and real-life conditions.

• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.101-110
• /
• 2021

In computer vision, single-image super resolution has been an area of research for a significant period. Traditional techniques involve interpolation-based methods such as Nearest-neighbor, Bilinear, and Bicubic for image restoration. Although implementations of convolutional neural networks have provided outstanding results in recent years, efficiency and single model multi-scalability have been its challenges. Furthermore, previous works haven't placed enough emphasis on real-number scalability. Interpolation-based techniques, however, have no limit in terms of scalability as they are able to upscale images to any desired size. In this paper, we propose a convolutional neural network possessing the advantages of the interpolation-based techniques, which is also efficient, deeming it suitable in practical implementations. It consists of convolutional layers applied on the low-resolution space, post-up-sampling along the end hidden layers, and additional layers on high-resolution space. Up-sampling is applied on a multiple channeled feature map via bicubic interpolation using a single model. Experiments on architectural structure, layer reduction, and real-number scale training are executed with results proving efficient amongst multi-scale learning (including scale multi-path-learning) based models.

• Structural Engineering and Mechanics
• /
• v.45 no.6
• /
• pp.759-777
• /
• 2013

In this paper, a topology optimization method based on the element independent nodal density (EIND) is developed for continuum solids with multiple load cases and multiple constraints. The optimization problem is formulated ad minimizing the volume subject to displacement constraints. Nodal densities of the finite element mesh are used a the design variable. The nodal densities are interpolated into any point in the design domain by the Shepard interpolation scheme and the Heaviside function. Without using additional constraints (such ad the filtering technique), mesh-independent, checkerboard-free, distinct optimal topology can be obtained. Adopting the rational approximation for material properties (RAMP), the topology optimization procedure is implemented using a solid isotropic material with penalization (SIMP) method and a dual programming optimization algorithm. The computational efficiency is greatly improved by multithread parallel computing with OpenMP to run parallel programs for the shared-memory model of parallel computation. Finally, several examples are presented to demonstrate the effectiveness of the developed techniques.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.26 no.1
• /
• pp.51-64
• /
• 2008

In this paper, an experiment was done where the input(scanner, digital still camera) and monitor(CRT, LCD) device used the linear multiple regression and the GOG (Gain-Offset-Gamma) characterization model to perform a color transformation. Also to color conversion method of the digital printer it used the LUT(Look Up Table), 3dimension linear interpolation and a tetrahedron interpolation method. The results are as follows. From color reappearance of digital printing case of monitor, the XYZ which it converts in linear multiple regression of input device it multiplied the inverse matrix, and then it applies the inverse GOG model and after color converting the patch of the result most which showed color difference below 5 at monitor RGB value. Also, The XYZ which is transmitted from the case input device which is a printer it makes at LAB value to convert an extreme, when the LAB value which is converted calculating the CMY with the LUT and tetrahedral interpolations the color conversion which considers the black quantity was more accurate.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.814-817
• /
• 2002

High-dimensional data with two or more attributes are considered. A typical example of such data is face images of various individuals and expressions. In these cases, collecting a complete data set is often difficult since the number of combinations can be large. In the present study, we propose a method to interpolate data of missing combinations from other data. If this becomes possible, robust recognition of multiple attributes is expectable. The key of this subject is appropriate extraction of the similarity that the face images of same individual or same expression have. Bilinear model ［1］has been proposed as a solution of this subjcet. However, experiments on application of bilinear model to classification of face images resulted in low performance ［2］. In order to overcome the limit of bilinear model, in this research, a nonlinear model on a neural network is adopted and usefulness of this model is experimentally confirmed.

• Journal of Broadcast Engineering
• /
• v.12 no.2
• /
• pp.128-136
• /
• 2007

Since the multi-view video is a set of video sequences captured by multiple array cameras for the same three-dimensional scene, it can provide multiple viewpoint images using geometrical manipulation and intermediate view generation. Although multi-view video allows us to experience more realistic feeling with a wide range of images, the amount of data to be processed increases in proportion to the number of cameras. Therefore, we need to develop efficient coding methods. One of the possible approaches to multi-view video coding is to generate an intermediate image using view interpolation method and to use the interpolated image as an additional reference frame. The previous view interpolation method for multi-view video coding employs fixed size block matching over the pre-determined disparity search range. However, if the disparity search range is not proper, disparity error may occur. In this paper, we propose an efficient view interpolation method using initial disparity estimation, variable block-based estimation, and pixel-level estimation using adjusted search ranges. In addition, we propose a multi-view video coding method based on H.264/AVC to exploit the intermediate image. Intermediate images have been improved about $1{\sim}4dB$ using the proposed method compared to the previous view interpolation method, and the coding efficiency have been improved about 0.5 dB compared to the reference model.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.237-240
• /
• 2020

The fine-tuned neural network (NN) model for a whole temporal portion in a video does not always yield the best quality (e.g., PSNR) performance over all regions of each frame in the temporal period. For certain regions (usually homogeneous regions) in a frame for super-resolution (SR), even a simple bicubic interpolation method may yield better PSNR performance than the fine-tuned NN model. When there are multiple NN models available at the receivers where each NN model is trained for a group of images having a specific category of image characteristics, the performance of Quality enhancement can be improved by selectively applying an appropriate NN model for each image region according to its image characteristic category to which the NN model was dedicatedly trained. In this case, it is necessary to signal which NN model is applied for each region. This is very advantageous for image restoration and quality enhancement (IRQE) applications at user terminals with limited computing capabilities.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.6 no.1
• /
• pp.1-11
• /
• 2003

In this study, TOPMODEL(TOPography based hydrologic MODEL) was tested linked with Muskingum river routing technique for $581.7km^2$ Anseong-cheon watershed. Linear trend surface interpolation was used to give flow direction for flat areas located in downstream watershed. MDF (multiple flow direction) algorithm was adopted to derive the distribution of ln(a/$tan{\beta}$) values of the model. Because the coarser DEM resolution, the greater information loss, the watershed was divided into subwaterhseds to keep DEM resolution, and the simulation result of the upstream watershed was transferred to downstream watershed by Muskingum techniques. Relative error of the simulated result by 500 m DEM resolution showed 27.2 %. On the other hand, the relative error of the simulated result of 300 m DEM resolution by linked 2 subwatersheds with Muskingum method showed 15.8 %.