• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.123-131
• /
• 2019

In this study, we modified CT images of femoral head in consideration of anatomically meaningful structure, proposing the method to augment the training data of convolution Neural network for segmentation of femur mesh model. First, the femur mesh model is obtained from the CT image. Then divide the mesh model into meaningful parts by using cluster analysis on geometric characteristic of mesh surface. Finally, transform the segments by using an appropriate mesh deformation algorithm, then create new CT images by warping CT images accordingly. Deep learning models using the data enhancement methods of this study show better image division performance compared to data augmentation methods which have been commonly used, such as geometric conversion or color conversion.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.2
• /
• pp.401-415
• /
• 2019

Recently, there has been a lot of studies and efforts to strengthen the stability of critical infrastructures against increasing cyber attacks to critical infrastructures. In this thesis, I defined what cyber threats are, after showing you various definitions about what cyber threats are and what the types are. After studying about significant cyber threats from China, I showed you the realities of cyber threats with the analysis about starting points, types of cyber threats, ratios of attacks and so on. At last, I defined guidelines about unnecessary oversea IP range blocking. Also, I proposed unnecessary oversea IP range blocking methodologies with per information system and per network system. Furthermore, I proposed blocking characteristics per security equipment and security operation improvement and blocking effects and service process to normal oversea users.

• Convergence Security Journal
• /
• v.19 no.1
• /
• pp.61-66
• /
• 2019

Cyber space is a place where free activities are guaranteed. However, it is also true that not all individuals and countries strive for peaceful cyberspace, and that there is a growing tendency to gain unfair advantage through this space. Therefore, the state should reform laws and institutions to keep cyberspace safe. By establishing the "Basic Law on Cyberspace" which includes the law of the state law on cyberspace, it is necessary to be able to recognize and respond to the direction of the national legal discipline on cyberspace. The development of digital forensics is an urgent task due to the rapid development of IT. However, if the law is delayed for various reasons, some of the existing laws should be amended to improve the stability of the law in accordance with the circumstances. To this end, it is necessary to revise the "Information and Communication Infrastructure Protection Act", "Information and Communication Network Enhancement and Information Protection Act", "Integrated Defense Law", "Establishment of Defense Information Infrastructure Infrastructure and Defense Information Resource Management Act".

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.401-410
• /
• 2019

In this paper, we propose a reference picture generation method for Inter-layer prediction based deep learning to improve the SHVC coding performance. A description will be given of a structure for performing filtering using a VDSR network on a DCT-IF based upsampled picture to generate a new reference picture and a training method for generating a reference picture between SHVC Inter-layer. The proposed method is implemented based on SHM 12.0. In order to evaluate the performance, we compare the method of generating Inter-layer predictor by applying dictionary learning. As a result, the coding performance of the enhancement layer showed a bitrate reduction of up to 13.14% compared to the method using dictionary learning, a bitrate reduction of up to 15.39% compared to SHM, and a bitrate reduction of 6.46% on average.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.3
• /
• pp.265-276
• /
• 2019

In our previous study, the LeNet3 model successfully classified images from the transverse surfaces of five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch). However, a practical limitation exists in our system stemming from the nature of the training images obtained from the transverse plane of the wood species. In real-world applications, it is necessary to utilize images from the longitudinal surfaces of lumber. Thus, we improved our model by training it with images from the longitudinal and transverse surfaces of lumber. Because the longitudinal surface has complex but less distinguishable features than the transverse surface, the classification performance of the LeNet3 model decreases when we include images from the longitudinal surfaces of the five Korean softwood species. To remedy this situation, we adopt ensemble methods that can enhance the classification performance. Herein, we investigated the use of ensemble models from the LeNet and MiniVGGNet models to automatically classify the transverse and longitudinal surfaces of the five Korean softwoods. Experimentally, the best classification performance was achieved via an ensemble model comprising the LeNet2, LeNet3, and MiniVGGNet4 models trained using input images of $128{\times}128{\times}3pixels$ via the averaging method. The ensemble model showed an F1 score greater than 0.98. The classification performance for the longitudinal surfaces of Korean pine and Korean red pine was significantly improved by the ensemble model compared to individual convolutional neural network models such as LeNet3.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.14 no.5
• /
• pp.49-56
• /
• 2004

An Internet draft, named RR(Return Routability) protocol, proposed to IETF mobileip WG, in order to establish an optimal path to MN(Mobile Node) by securely sending the BU(Binding Update) message to CN(Correspondent Node). However, it has some problems with initiating the protocol by the MN: it causes to increases in communication load in the home network, to increases communication delay between MN and CN, and increases in communication load due to unnecessary message exchanges. To resolve the problems, this paper proposes an alternative scheme for the RR protocol in MIPv6. The proposed scheme is devised to start the protocol by HA on receiving the first packet from CN. It decreases the route optimization overhead by reducing the number of BU messages as well as the communication time. Beside these advantages, this scheme provides the same security grade as the original RR protocol.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.15 no.5
• /
• pp.3-11
• /
• 2005

This paper presents a performance analysis model based on an M/M/1 queue and Poisson distribution of input data traffic. The simulation on a pipelined AES system with processing rate of 10 rounds per clock shows $4.0\%$ higher performance than a non-pipelined version consuming 10 clocks per transaction. Physical implementation of pipelined AES with FPGA takes 3.5 times bigger gate counts than the non-pipelined version whereas the pipelined version yields only $3.5\%$ performance enhancement. The proposed analysis model can be used to optimize cost-performance of AES hardware designs.

• Journal of Advanced Navigation Technology
• /
• v.24 no.6
• /
• pp.451-457
• /
• 2020

Diverse sensors are equipped on P-3C Maritime Patrol Aircraft for RoKN to detect and monitor tactical targets. Tactical targets are maintained/shared by tactical computer stations which consist of a clustering network in the aircraft and displayed in various ways on TSDs(Tactical Situation Displays) for mission operators to perform their specified missions. Korea peninsula is widely covered with the sea areas and neighboured with several countries; which makes huge number of ships and aircraft deployment around the place. Due to an increase in number of sensors and enhancement of their sensitivities; we were aware of the necessity of TSD improvements to provide huge number of tactical targets and to display them efficiently. In this paper, we propose a solution for the improvements by using previous backup data and re-usage of the data, then we verify the proposal through implementation and evaluation results.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.1-11
• /
• 2021

Slow sync is a photography technique where a user takes an image with long exposure and a camera flash to enlighten the foreground and background. Unlike short exposure with flash and long exposure without flash, slow sync guarantees the bright foreground and background in the dim environment. However, taking a slow sync image with a smartphone is difficult because the smartphone camera has continuous and weak flash and can not turn on flash if the exposure time is long. This paper proposes a deep learning method that input is a short exposure flash image and output is a slow sync image. We present a deep learning network with a weight map for spatially varying enlightenment. We also propose a dataset that consists of smartphone short exposure flash images and slow sync images for supervised learning. We utilize the linearity of a RAW image to synthesize a slow sync image from short exposure flash and long exposure no-flash images. Experimental results show that our method trained with our dataset synthesizes slow sync images effectively.

• Journal of the Korea Society for Simulation
• /
• v.19 no.3
• /
• pp.91-98
• /
• 2010

This paper is on the research result for analyzing the performance of GLORY(GLobal Resource management sYstem) used for Web Server Cluster system, which was developed at ETRI(Electronic and Telecommunication Research Institute). The paper includes the definition of Web Server Cluster System, the characteristics of the system, user oriented system performance, current performance enhancement methods, computer simulation model for GLORY and its experimental results for the performance of GLORY. GLORY is composed of 2048~1,000,000 units of PCs, and is used for Internet servers. From the results of the simulation experiments, we notice that GLORY has enough capacity to fully serve the appropriate level of Internet services. Also, the results show that Web server service time is longer than that for network transmission time but requires more DNS than expected, and that 100Mbps LAN is good enough for directly connecting Internet to the Web servers while not affecting the total system performance.