• ETRI Journal
• /
• v.29 no.1
• /
• pp.18-26
• /
• 2007

This paper presents an improved redundant picture coding method that efficiently enhances the error resiliency of H.264. The proposed method applies polyphase downsampling to residual blocks obtained from inter prediction and selectively encodes the rearranged residual blocks in the redundant picture coding process. Moreover, a spatial-temporal sample construction method is developed for the redundant coded picture, which further improves the reconstructed picture quality in error prone environments. Simulations based on JM11.0 were run to verify the proposed method on different test sequences in various error prone environments with average packet loss rates of 3%, 5%, 10%, and 20%. Results of the simulations show that the presented method significantly improves the robustness of H.264 to packet loss by 1.6 dB PSNR on average over the conventional redundant picture coding method.

• ETRI Journal
• /
• v.43 no.3
• /
• pp.538-548
• /
• 2021

This paper proposes an approach to improve the performance of no-reference video quality assessment for sports videos with dynamic motion scenes using an efficient spatiotemporal model. In the proposed method, we divide the video sequences into video blocks and apply a 3D shearlet transform that can efficiently extract primary spatiotemporal features to capture dynamic natural motion scene statistics from the incoming video blocks. The concatenation of a deep residual bidirectional gated recurrent neural network and logistic regression is used to learn the spatiotemporal correlation more robustly and predict the perceptual quality score. In addition, conditional video block-wise constraints are incorporated into the objective function to improve quality estimation performance for the entire video. The experimental results show that the proposed method extracts spatiotemporal motion information more effectively and predicts the video quality with higher accuracy than the conventional no-reference video quality assessment methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.568-570
• /
• 2023

The problem of classifying of age, gender, and race images still poses challenges. Despite deep and machine learning strides, convolutional neural networks (CNNs) remain pivotal in addressing these issues. This paper introduces a novel CNN-based approach for accurate and efficient age, gender, and race classification. Leveraging CNNs with residual blocks, our method enhances learning while minimizing computational complexity. The model effectively captures low-level and high-level features, yielding improved classification accuracy. Evaluation of the diverse 'fair face' dataset shows our model achieving 56.3%, 94.6%, and 58.4% accuracy for age, gender, and race, respectively.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.19 no.4
• /
• pp.398-403
• /
• 2006

This paper describes the evaluation of the long duration current impulse withstand characteristics of ZnO blocks for high voltage surge arresters. Four ZnO varistors were manufactured with the general ceramic production method and the long duration current impulse withstand test, electrical uniformity evaluation test and microstructure observation were performed. All varistors exhibited high density, which was in the range of $5.42{\sim}5.46g/cm^3$. In the electrical properties, the reference voltage of samples was in the range of $5.11{\sim}5.25\;kV$ and the residual voltage was in the range of $8.314{\sim}8.523\;kV$. In the long duration current impulse withstand test, sample No.2 and No.3 failed at the 2nd and 4th shot of series impulse currents, respectively, but the rest survived 18 shots during the test. Before and after this test, the variation ratio of the residual voltage of samples survived was below 0.5 %, which was in the acceptance range of 5 %. According to the results of the test, it is thought that if the soldering method is improved, ZnO varistors would be possible to apply to the high voltage arresters like the station class and transmission line arresters in the near future.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2007.11a
• /
• pp.486-487
• /
• 2007

This paper describes the evaluation of long duration current impulse withstand characteristics of ZnO blocks for high voltage surge arresters. Four ZnO varistors were manufactured with the general ceramic production method and three abroad varistors were also prepared to be compared. All varistors exhibited high density, which was in the range of $5.42{\sim}5.49g/cm^3$. In the electrical properties, the reference voltage of all samples was in the range of 5.11~5.72kV and the residual voltage was in the range of 8.314~9.305kV. In the long duration current impulse withstand test, sample 2 and 3 failed at the 2nd and 4th shot of series impulse currents, respectively, but the rest survived 18 shots during the test. Before and after this test, the variation ratio of the residual voltage of samples survived were below 1.7%, which were in the acceptance range of 5%.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.07b
• /
• pp.1158-1161
• /
• 2004

This paper presents structural characteristics of station class lightning arresters and electrical characteristics of manufactured ZnO varistor blocks which are usable in those arresters. Three types of station class lightning arresters were investigated and those are a ceramic arrester, a FRP tube type polymer arrester, and a FRP rod type polymer arrester. Each arrester has merits and demerits with structural characteristics. In general, polymer arresters were made of silicon rubber for housing materials, FRP tube or rod for mechanical strength, ZnO blocks for electrical characteristics, and metal parts for electrical contact and the silicon rubber, the housing materials, was directly injected to the arrester module which was assembly composed of electrodes, ZnO blocks and FRP tube or rod, and to prevent the nonlinear electric fields distribution on upper parts of arresters, the grade ring was adopted to the upper electrodes. The reference voltage, nonlinear coefficient, residual voltage, and voltage ratio of manufactured ZnO varistors are 4.90kV, 50, 9.54kV, 1.94, respectively. Compared to designed electrical characteristics, the reference voltage was low for 600v and the voltage ratio was slightly high. However, the characteristics of discharge withstand was so excellent that the mechanical destruction does not occur at the impulse current of $8/20{\mu}s$ 10kA for 100 times.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1447-1453
• /
• 2020

In this paper, we propose a method for no-reference quality assessment of sports videos using 3D shearlet transform and deep residual neural networks. In the proposed method, 3D shearlet transform-based spatiotemporal features are extracted from the overlapped video blocks and applied to logistic regression concatenated with a deep residual neural network based on a conditional video block-wise constraint to learn the spatiotemporal correlation and predict the quality score. Our evaluation reveals that the proposed method predicts the video quality with higher accuracy than the conventional no-reference video quality assessment methods.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.28 no.3
• /
• pp.156-165
• /
• 2005

A new heuristic algorithm for the heterogeneous single container loading problem is proposed in this paper, This algorithm fills empty spaces with the homogeneous load-blocks of identically oriented boxes and splits residual space into three sub spaces starting with an empty container. An initial loading pattern is built by applying this approach recursively until all boxes are exhausted or no empty spaces are left. In order to generate alternative loading patterns, the load-blocks of pattern determining spaces are replaced with the alternatives that were generated on determining the load-blocks. An improvement algorithm compares these alternatives with the initial pattern to find improved one. Numerical experiments with 715 test cases show the good performance of this new algorithm, above all for problems with strongly heterogeneous boxes.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.429-440
• /
• 2021

With the recent development of deep convolutional neural network learning, deep learning techniques applied to single image super-resolution are showing good results. One of the existing deep learning-based super-resolution techniques is RDN(Residual Dense Network), in which the initial feature information is transmitted to the last layer using residual dense blocks, and subsequent layers are restored using input information of previous layers. However, if all hierarchical features are connected and learned and a large number of residual dense blocks are stacked, despite good performance, a large number of parameters and huge computational load are needed, so it takes a lot of time to learn a network and a slow processing speed, and it is not applicable to a mobile system. In this paper, we use the residual dense structure, which is a continuous memory structure that reuses previous information, and the residual dense channel attention block using the channel attention method that determines the importance according to the feature map of the image. We propose a method that can increase the depth to obtain a large receptive field and maintain a concise model at the same time. As a result of the experiment, the proposed network obtained PSNR as low as 0.205dB on average at 4× magnification compared to RDN, but about 1.8 times faster processing speed, about 10 times less number of parameters and about 1.74 times less computation.

• Journal of the Korean Society for Heat Treatment
• /
• v.2 no.2
• /
• pp.33-37
• /
• 1989

In order to improve hardness uniformity of standard-hardness blocks. experimental procedure was designed using Taguchi Method. For this purpose the following factors were studied: austenitizing temperature, tempering condition, grinding condition, subzero treatment, lapping time, $15{\mu}m$ polishing time, final polishing time. These factors were processed and then ten hardness values were measured on each specimen. SN (signal to noise) ratio for each condition was calculated with standard variations of these values. Finally, from the calculated value of ANOVA on SN ratios, the lapping time was found to be the main factor Better uniformity with longer lapping time implies that residual stress that was formed after quenching is a dominent parameter that affects on the uniformity of hardness. Therefore, step-quenching method was adapted to minimize the residual stress. By this modification of quenching procedure, the hardness uniformity was improved remarkably and the yield ratio was increased from 55% to 88%.