• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.264-272
• /
• 2019

In this paper, we propose a 3D human body reconstruction and refinement method from the frames extracted from a video to obtain natural and smooth motion in temporal domain. Individual frames extracted from the video are fed into convolutional neural network to estimate the location of the joint and the silhouette of the human body. This is done by projecting the parameter-based 3D deformable model to 2D image and by estimating the value of the optimal parameters. If the reconstruction process for each frame is performed independently, temporal consistency of human pose and shape cannot be guaranteed, yielding an inaccurate result. To alleviate this problem, the proposed method analyzes and interpolates the principal component parameters of the 3D morphable model reconstructed from each individual frame. Experimental result shows that the erroneous frames are corrected and refined by utilizing the relation between the previous and the next frames to obtain the improved 3D human reconstruction result.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.15 no.3
• /
• pp.31-42
• /
• 2005

We consider a network storage model whose administrator can not be fully trusted. In this model, we assume that all data stored are encrypted for data confidentiality and one owner distributes the decryption key for each time period to users. In this paper, we propose three privilege management schemes. In the first scheme, called Temporal Privilege Management (TPM), we use a symmetric encryption based on one-way function chains for key encapsulation. In the second scheme, called Asymmetric Temporal Privilege Management (ATPM), anyone can encrypt the data using the public key of owner, but only privileged users can decrypt the encrypted data. Finally, we present a scheme to restrict writers' privilege using ID-based signatures in ATPM. In our schemes, the privilege managements are based on the time and the addition of users is efficient. Specially, applying TPM and ATPM, we can solve the back-issue problem.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.3
• /
• pp.193-199
• /
• 2017

Instead of using only spatial features from a single frame for person re-identification, a combination of spatial and temporal factors boosts the performance of the system. A recurrent neural network (RNN) shows its effectiveness in generating highly discriminative sequence-level human representations. In this work, we implement RNN, three Long Short Term Memory (LSTM) network variants, and Gated Recurrent Unit (GRU) on Caffe deep learning framework, and we then conduct experiments to compare performance in terms of size and accuracy for person re-identification. We propose using GRU for the optimized choice as the experimental results show that the GRU achieves the highest accuracy despite having fewer parameters than the others.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2001.10a
• /
• pp.59-64
• /
• 2001

The objectives of the thesis are to propose a pattern classification method for remote sensing data using artificial neural network. First, we apply the error back propagation algorithm to classify the remote sensing data. In this case, the classification performance depends on a training data set. Using the training data set and the error back propagation algorithm, a layered neural network is trained such that the training pattern are classified with a specified accuracy. After training the neural network, some pixels are deleted from the original training data set if they are incorrectly classified and a new training data set is built up. Once training is complete, a testing data set is classified by using the trained neural network. The classification results of Landsat TM data show that this approach produces excellent results which are more realistic and noiseless compared with a conventional Bayesian method.

• Proceedings of the KOSOMBE Conference
• /
• v.1990 no.05
• /
• pp.51-55
• /
• 1990

In this study, a peripheral auditory model used as a frequency feature extractor and a recurrent network which has recurrent links on input nodes is constructed in order to show the reliability of the recurrent network as a recognizer by executing recognition tests for 4 Korean placenames and syllables. As a result of this study, a refined weight compensation method is proposed and, using this method, it is possible to improve the system operation. The recurrent network in this study reflects well time information of temporal speech signal.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.95-102
• /
• 2005

A Parallel Processing model by considering a spatiotemporal parallelism is presented for the training procedure of the MLP neural network. We tried to design the flexible Parallel Processing model by simultaneously applying both of the training-set decomposition for a temporal parallelism and the network decomposition for a spatial parallelism. The analytical Performance evaluation model shows that when the problem size is extremely large, the speedup of each implementation depends, in the extreme, on whether the problem size is pattern-size intensive or pattern-quantify intensive.

• Journal of Industrial Technology
• /
• v.26 no.B
• /
• pp.183-189
• /
• 2006

Ad hoc network does not need any preexisting network infrastructure, and it has been developed as temporal networks in the various fields. Infostation is an efficient system to transfer informations which are not sensitive to delay. In this paper, we propose a disaster emergency management system using sensors attached to animals, that is combined with infostation system. We also analyze the performance of the proposed system by simulation. From the performance analysis results, we expect that the proposed system will be very useful to early detect big forest fires which occur frequently in Korea mountain areas.

• Smart Structures and Systems
• /
• v.19 no.4
• /
• pp.383-391
• /
• 2017

In this paper, we investigate the impacts of network topology on the performance of a distributed estimation algorithm, namely combine-then-adaptive (CTA) diffusion LMS, based on the data with or without the assumptions of temporal and spatial independence with noisy links. The study covers different network models, including the regular, small-world, random and scale-free whose the performance is analyzed according to the mean stability, mean-square errors, communication cost (link density) and robustness. Simulation results show that the noisy links do not cause divergence in the networks. Also, among the networks, the scale free network (heterogeneous) has the best performance in the steady state of the mean square deviation (MSD) while the regular is the worst case. The robustness of the networks against the issues like node failure and noisier node conditions is discussed as well as providing some guidelines on the design of a network in real condition such that the qualities of estimations are optimized.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.9-17
• /
• 2020

Hippocampus is a complex brain structure embedded deep into the temporal lobe. Studies have shown that this structure gets affected by neurological and psychiatric disorders and it is a significant landmark for diagnosing neurodegenerative diseases. Hippocampus features play very significant roles in region-of-interest based analysis for disease diagnosis and prognosis. In this study, we have attempted to learn the embeddings of this important biomarker. As conventional metric learning methods for feature embedding is known to lacking in capturing semantic similarity among the data under study, we have trained deep Siamese convolutional neural network for learning metric of the hippocampus. We have exploited Gwangju Alzheimer's and Related Dementia cohort data set in our study. The input to the network was pairs of three-view patches (TVPs) of size 32 × 32 × 3. The positive samples were taken from the vicinity of a specified landmark for the hippocampus and negative samples were taken from random locations of the brain excluding hippocampi regions. We have achieved 98.72% accuracy in verifying hippocampus TVPs.

• Journal of Biomedical Engineering Research
• /
• v.11 no.1
• /
• pp.157-162
• /
• 1990

In this study, a peripheral auditory model is used as a frequency feature extractor and a recurrent network which has recurrent links on input nodes is constructed in order to show the reliability of the recurrent network as a recognizer by executing recognition tests for 4 Korean place names and syllables. In the case of using the general learning rule, it is found that the weights are diverged for a long sequence because of the characteristics of the node function in the hidden and output layers. So, a refined weight compensation method is proposed and, using this method, it is possible to improve the system operation and to use long data. The recognition results are considerably good, even if time worping and endpoint detection are omitted and learning patterns and test patterns are made of average length of data. The recurrent network used in this study reflects well time information of temporal speech signal.