• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1540-1551
• /
• 2020

Aiming at the problem that the existing human behavior recognition algorithm cannot fully utilize the multi-level spatio-temporal information of the network, a human behavior recognition algorithm based on a dense three-dimensional residual network is proposed. First, the proposed algorithm uses a dense block of three-dimensional residuals as the basic module of the network. The module extracts the hierarchical features of human behavior through densely connected convolutional layers; Secondly, the local feature aggregation adaptive method is used to learn the local dense features of human behavior; Then, the residual connection module is applied to promote the flow of feature information and reduced the difficulty of training; Finally, the multi-layer local feature extraction of the network is realized by cascading multiple three-dimensional residual dense blocks, and use the global feature aggregation adaptive method to learn the features of all network layers to realize human behavior recognition. A large number of experimental results on benchmark datasets KTH show that the recognition rate (top-l accuracy) of the proposed algorithm reaches 93.52%. Compared with the three-dimensional convolutional neural network (C3D) algorithm, it has improved by 3.93 percentage points. The proposed algorithm framework has good robustness and transfer learning ability, and can effectively handle a variety of video behavior recognition tasks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.962-975
• /
• 2020

The accurate segmentation of infant brain MR image into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is very important for early studying of brain growing patterns and morphological changes in neurodevelopmental disorders. Because of inherent myelination and maturation process, the WM and GM of babies (between 6 and 9 months of age) exhibit similar intensity levels in both T1-weighted (T1w) and T2-weighted (T2w) MR images in the isointense phase, which makes brain tissue segmentation very difficult. We propose a deep network architecture based on U-Net, called Triple Residual Multiscale Fully Convolutional Network (TRMFCN), whose structure exists three gates of input and inserts two blocks: residual multiscale block and concatenate block. We solved some difficulties and completed the segmentation task with the model. Our model outperforms the U-Net and some cutting-edge deep networks based on U-Net in evaluation of WM, GM and CSF. The data set we used for training and testing comes from iSeg-2017 challenge (http://iseg2017.web.unc.edu).

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.68 no.1
• /
• pp.102-107
• /
• 2019

This paper proposes a method to improve the mass spectral detection performance of the residual gas analyzer. By improving the mode estimation method for setting the threshold value and improving the additive noise elimination method, it is possible to detect mass spectrums having low peak values of the threshold level difficult to distinguish from noise. Ion signal blocks for each mass index with noise removed by the improved method are effective for eliminating invalid ion signals based on the linear and quadratic fittings. The mass spectrum can be obtained from the quadratic fitted curves for the reconstructed ion signal block using only the valid ion signals. In addition, the resolution of the mass spectrum can be improved by correcting the error caused by the shift of the spectral peak position. To verify the performance of the proposed method, computer simulations were performed using real ion signals obtained from the residual gas analysis system under development. The simulation results show that the proposed method is valid.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.142-146
• /
• 2023

We present a method for generating 3D structures and rendering objects by combining VAE (Variational Autoencoder) and GAN (Generative Adversarial Network). This approach focuses on generating and rendering 3D models with improved quality using residual learning as the learning method for the encoder. We deep stack the encoder layers to accurately reflect the features of the image and apply residual blocks to solve the problems of deep layers to improve the encoder performance. This solves the problems of gradient vanishing and exploding, which are problems when constructing a deep neural network, and creates a 3D model of improved quality. To accurately extract image features, we construct deep layers of the encoder model and apply the residual function to learning to model with more detailed information. The generated model has more detailed voxels for more accurate representation, is rendered by adding materials and lighting, and is finally converted into a mesh model. 3D models have excellent visual quality and accuracy, making them useful in various fields such as virtual reality, game development, and metaverse.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.1-15
• /
• 2022

The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.75-76
• /
• 2008

A low complexity encoding scheme for coarse grain scalability is proposed. The proposed method exploits the statistics of residuals between current and reference blocks using the macroblock mode predicted from the previous quality layer. To test how the mode is optimal in the current layer, the statistical hypothesis testing for the variances of the residual sub-blocks is performed. The proposed method reduces the total encoding time up to 51% when three CGS scalability layers are encoded. However, the quality degradation and bit-rate increment of the each layer are negligible.

• Journal of the Korean Statistical Society
• /
• v.24 no.2
• /
• pp.495-506
• /
• 1995

We present formula for detecting influential observations on the smoothing parameter in smoothing spline. Further, we express them as functions of basic building blocks such as residuals and leverage, and compare it with the local influence approach by Thomas (1991). An example based on a real data set is given.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.966-970
• /
• 2011

The thermo-mechanical interaction between brake block and wheel tread during braking has been found to cause thermal crack on the wheel tread. Due to thermal expansion of the rim material, the thermal cracks will protrude from the wheel tread and be more exposed to wear during the wheel/block contact than the rest of the tread surface. The wheel rim is in residual compression stress when is new. After service running, the region in the tread has reversed to tension. This condition can lead to the formation and growth of thermal cracks in the rim which can ultimately lead to premature failure of wheel. In the present paper, the thermal cracks of railway wheel, one of severe damages on the wheel tread, were evaluated to understand the safety of railway wheel in running condition. The residual stresses for damaged wheel which are applied to tread brake are investigated. Mainly X-ray diffusion method is used. Under the condition of concurrent loading of continuous rolling contact with rails and cyclic frictional heat from brake blocks, the reduction of residual stress is found to correlate well with the thermal crack initiation.

• Journal of the Society of Naval Architects of Korea
• /
• v.44 no.5
• /
• pp.496-503
• /
• 2007

Although weld-induced deformation is inevitable in shipbuilding, it is important to reduce it as low as possible during fabrication for a more efficient production of ships' blocks. The weld-induced deformation is more serious in thin plates than in thick plates because heat affect zone of thin plates is wider than that of thick plates, and in addition internal and external constraints much more influence upon weld-induced deformation of thin plates. This paper deals with the application of the mechanical tensioning method to butt weld of thin plates to reduce the transverse and longitudinal deformation. in order to investigate the quantitative effect of tensioning method upon the reduction of angular deformation and shrinkage in longitudinal and transverse direction of weld line, butt welding test have been carried out for several thin plate specimens with varying plate thickness and magnitude of tensile load. Numerical simulation has been also carried out to compare the weld-induced deformation and residual stress. From the present study, it has been found that the tensioning method is very effective on reduction of weld-induced residual stress as well as weld-induced deformation.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.5
• /
• pp.537-542
• /
• 2011

The thermo-mechanical interaction between brake block and wheel tread during braking has been found to cause thermal crack on the wheel tread. Due to thermal expansion of the rim material, the thermal cracks will protrude from the wheel tread and be more exposed to wear during the wheel/block contact than the rest of the tread surface. The wheel rim is in residual compression stress when is new. After service running, the region in the tread has reversed to tension. This condition can lead to the formation and growth of thermal cracks in the rim which can ultimately lead to premature failure of wheel. In the present paper, the thermal cracks of railway wheel, one of severe damages on the wheel tread, were evaluated to understand the safety of railway wheel in running condition. The residual stresses for damaged wheel which are applied to tread brake are investigated. Mainly X-ray diffusion method is used. Under the condition of concurrent loading of continuous rolling contact with rails and cyclic frictional heat from brake blocks, the reduction of residual stress is found to correlate well with the thermal crack initiation.