Search results for: Shigetaka Nakamura

Authors: Shinji Ukita, Naohiro Nakamura, Yuji Miyazu

Abstract:

In considering the dynamic characteristics of structure, natural frequency and damping ratio are useful indicator. When performing dynamic design, it's necessary to select an appropriate initial damping model and hysteretic model. In the linear region, the setting of initial damping model influences the response, and in the nonlinear region, the combination of initial damping model and hysteretic model influences the response. However, the dynamic characteristics of structure in the nonlinear region remain unclear. In this paper, we studied the effect of setting of initial damping model and hysteretic model on the dynamic characteristics of structure. On initial damping model setting, Initial stiffness proportional, Tangent stiffness proportional, and Rayleigh-type were used. On hysteretic model setting, TAKEDA model and Normal-trilinear model were used. As a study method, dynamic analysis was performed using a lumped mass model of base-fixed. During analysis, the maximum acceleration of input earthquake motion was gradually increased from 1 to 600 gal. The dynamic characteristics were calculated using the ARX model. Then, the characteristics of 1st and 2nd natural frequency and 1st damping ratio were evaluated. Input earthquake motion was simulated wave that the Building Center of Japan has published. On the building model, an RC building with 30×30m planes on each floor was assumed. The story height was 3m and the maximum height was 18m. Unit weight for each floor was 1.0t/m2. The building natural period was set to 0.36sec, and the initial stiffness of each floor was calculated by assuming the 1st mode to be an inverted triangle. First, we investigated the difference of the dynamic characteristics depending on the difference of initial damping model setting. With the increase in the maximum acceleration of the input earthquake motions, the 1st and 2nd natural frequency decreased, and the 1st damping ratio increased. Then, in the natural frequency, the difference due to initial damping model setting was small, but in the damping ratio, a significant difference was observed (Initial stiffness proportional≒Rayleigh type>Tangent stiffness proportional). The acceleration and the displacement of the earthquake response were largest in the tangent stiffness proportional. In the range where the acceleration response increased, the damping ratio was constant. In the range where the acceleration response was constant, the damping ratio increased. Next, we investigated the difference of the dynamic characteristics depending on the difference of hysteretic model setting. With the increase in the maximum acceleration of the input earthquake motions, the natural frequency decreased in TAKEDA model, but in Normal-trilinear model, the natural frequency didn’t change. The damping ratio in TAKEDA model was higher than that in Normal-trilinear model, although, both in TAKEDA model and Normal-trilinear model, the damping ratio increased. In conclusion, in initial damping model setting, the tangent stiffness proportional was evaluated the most. In the hysteretic model setting, TAKEDA model was more appreciated than the Normal-trilinear model in the nonlinear region. Our results would provide useful indicator on dynamic design.

Keywords: initial damping model, damping ratio, dynamic analysis, hysteretic model, natural frequency

Procedia PDF Downloads 154

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 260

Authors: Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Kensuke Nakamura, Dongeun Choi, Byung-Woo Hong

Abstract:

Artefacts are commonly encountered in the imaging process of clinical computed tomography (CT) where the artefact refers to any systematic discrepancy between the reconstructed observation and the true attenuation coefficient of the object. It is known that CT images are inherently more prone to artefacts due to its image formation process where a large number of independent detectors are involved, and they are assumed to yield consistent measurements. There are a number of different artefact types including noise, beam hardening, scatter, pseudo-enhancement, motion, helical, ring, and metal artefacts, which cause serious difficulties in reading images. Thus, it is desired to remove nuisance factors from the degraded image leaving the fundamental intrinsic information that can provide better interpretation of the anatomical and pathological characteristics. However, it is considered as a difficult task due to the high dimensionality and variability of data to be recovered, which naturally motivates the use of machine learning techniques. We propose an image restoration algorithm based on the deep neural network framework where the denoising auto-encoders are stacked building multiple layers. The denoising auto-encoder is a variant of a classical auto-encoder that takes an input data and maps it to a hidden representation through a deterministic mapping using a non-linear activation function. The latent representation is then mapped back into a reconstruction the size of which is the same as the size of the input data. The reconstruction error can be measured by the traditional squared error assuming the residual follows a normal distribution. In addition to the designed loss function, an effective regularization scheme using residual-driven dropout determined based on the gradient at each layer. The optimal weights are computed by the classical stochastic gradient descent algorithm combined with the back-propagation algorithm. In our algorithm, we initially decompose an input image into its intrinsic representation and the nuisance factors including artefacts based on the classical Total Variation problem that can be efficiently optimized by the convex optimization algorithm such as primal-dual method. The intrinsic forms of the input images are provided to the deep denosing auto-encoders with their original forms in the training phase. In the testing phase, a given image is first decomposed into the intrinsic form and then provided to the trained network to obtain its reconstruction. We apply our algorithm to the restoration of the corrupted CT images by the artefacts. It is shown that our algorithm improves the readability and enhances the anatomical and pathological properties of the object. The quantitative evaluation is performed in terms of the PSNR, and the qualitative evaluation provides significant improvement in reading images despite degrading artefacts. The experimental results indicate the potential of our algorithm as a prior solution to the image interpretation tasks in a variety of medical imaging applications. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: auto-encoder neural network, CT image artefact, deep learning, intrinsic image representation, noise reduction, total variation

Procedia PDF Downloads 165