• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.8
• /
• pp.21-31
• /
• 1998

In this paper, a new algorithm is proposed which distributes multicast cells in a copy network. The dual copy network is composed of running adder network, distributor, dummy address encoder, and broadcasting network. It is operated lower input address and higher one simultaneously by the distribution algorithm. As a result, for each input has a better equal opportunity of processing, cell delay and hardware complexity are reduced in copy network. Also, for it adopts the broadcasting network from an expansion Banyan network with binary tree and Banyan network, overflow probability is reduced to a half in that network. As a result of computer simulation, the copy network processed by the distribution algorithm is remarkably improved in cell delay of input buffer according to all input loads.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.309-317
• /
• 2022

In this paper, we propose a machine learning-based copy-move forgery detection network with dual branches. Because the rotation or scaling operation is frequently involved in copy-move forger, the conventional convolutional neural network is not effectively applied in detecting copy-move tampering. Therefore, we divide the input into rotation-invariant and scaling-invariant features based on the wavelet coefficients. Each of the features is input to different branches having the same structure, and is fused in the combination module. Each branch comprises feature extraction, correlation, and mask decoder modules. In the proposed network, VGG16 is used for the feature extraction module. To check similarity of features generated by the feature extraction module, the conventional correlation module used. Finally, the mask decoder model is applied to develop a pixel-level localization map. We perform experiments on test dataset and compare the proposed method with state-of-the-art tampering localization methods. The results demonstrate that the proposed scheme outperforms the existing approaches.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.4B
• /
• pp.397-402
• /
• 2004

In this paper, we have designed and simulated a new file transmission method. This method restricts memory copy and context switching happened in traditional file transmission. This method shows an improved performance than traditional method in network environment. When the UNIX/LINUX system that uses the existing file transfer technique transmits a packet to the remote system, a memory copy between the user and kernel space occurs over twice at least. Memory copy between the user and kernel space increase a file transmission time and the number of context switching. As a result, the existing file transfer technique has a problem of deteriorating the performance of file transmission. We propose a new algorithm for solving these problems. It doesn't perform memory copy between the user and kernel space. Hence, the number of memory copy and context switching is limited to the minimum. We have modified the network related source code of LINUX kernel 2.6.0 to analyzing the performance of proposed algorithm and implement new network system calls.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.5
• /
• pp.1-7
• /
• 2012

In this paper, we design and implement the simulator for WAN storage replication model performance evaluation in cloud computing environment. Each cloud of simulator is composed of virtual machine emulator and storage emulator. The virtual machine emulator is composed of read/write ratio module, the read/write sequence combination module, and the read/write request module. The storage emulator is composed of storage management module, data transfer module, read/write operations module, and overhead processing module. Using the simulator, we evaluate performance of migration scheme, pre-copy and the post-copy, considering about read/write ratio, network delay, and network bandwidth. Through simulation, we have confirmed that the average migration time of pre-copy was decreased proportional to the read operation. However, average migration time of post-copy was on the increase. Also, the average migration time of post-copy was increased proportional to the network delay. However, average migration time of pre-copy was shown uniformly. Therefore, we show that pre-copy model more effective to reduce the average migration time than the post-copy model. The average migration time of pre-copy and post-copy were not affected by the change of network bandwidth. Therefore, these results show that selects the storage replication model to be, the network bandwidth know not being the important element.

• Journal of KIISE:Information Networking
• /
• v.29 no.6
• /
• pp.696-705
• /
• 2002

This paper presents a new copy network for multicast ATM switches. Many studies have been carried out up to date since the proposition of Lee's copy network. However, the overflows and cell conflicts within the switch have still been raised a problem in argument. In order to reduce those problems, we proposed a 3-dimensional multicast switching architecture which has shared buffers in this paper. The proposed architecture can reduce the overflows and cell conflicts through multiple paths and output ports even in the high load environments. Also, we proposed a cell splitting algorithm which handles the cell in the case of large fan-out, and a copy network to increase throughput by expanding the Lee's Broadcast Banyan Network(BBN). Cell copy uses the Boolean interval splitting algorithm and the multicast pattern of the cells according to the self-routing characteristics of the network. In the proposed copy network, we improve the problems such as overflow, cell splitting of large fanout, cell conflicts, etc., which were still existed in the Lee's network. The results of performance evaluation by computer simulation show that the proposed scheme has better throughput, cell loss rate and cell delay than the conventional method.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.10
• /
• pp.52-63
• /
• 1998

In this paper, several improvements to a copy network proposed previously for multicast packet switching are described. The improvements provide a solution to some problems inherent in multicasting. The input fairness problem caused by overf low is solved by a dynamic starting point decider(DSD), which can calculate running sums of copy requests starting from any input port. The starting point is changed adaptively in every time slot based on both the fill level of the input buffers in current time slot and the overflow situations of the previous time slot. Using the fill level of the conventional network. The DSD also provides the function of regulating overall copy requests according to the amount of input traffics. This is an essential function in improving overall throughputs of the copy networks. The throughput of a multicast switch can be improved substantially if partial service of copy request is implemented when overflow occurs. Call-splitting can also be implemented by the DSD in a straightforward manner. The hardware for the DSD is derived with the objective of simple architectures for the high speed operation. Simulation study of the copy network under various traffic conditions is presented to evaluate its performance.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.32A no.12
• /
• pp.1-8
• /
• 1995

In this paper, we propose an extendible copy network in a large-scale ATM switch consisting of small switch modules implementable on a single VLSI chip or a single PCB. Considering multicasting switches consist of a copy network and a routing network, there exist broadcast and group translators (BGT) which assign the destination addresses into copied cells. The BGT table can be reduced by vertical partitioning method; copied cells are translated in adjacent BGTs and each BGT table has a single destination address per connection. In addition, the distribution network routes and copies incomming cells into several groups statically which are translated into consecutive BGTs. This guarantees the integrity of cell sequences. Connection-setup time as well as the BGT table size can be reduced significantly.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1133-1144
• /
• 2021

Zero-copy is a technology that is also called no-memory copy, and through its use, context switching between the user space and the kernel space can be reduced to minimize the load on the CPU. However, this technology is only used to transmit small random files, and has not yet been widely used for large file transfers. This paper intends to discuss the practical application of zero-copy in processing large files via a network. To this end, we first developed a small test bed and program that can transmit and store data based on zero-copy. Afterwards, we intend to verify the usefulness of the applied technology in detail through detailed performance evaluation

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.8C
• /
• pp.703-710
• /
• 2012

The new article, related to temporary copy on exploitation of copyrighted works, has been introduced in the copyright law as partly revised on December 2, 2011. While number of researches on in-network caching including Content-Centric Networking are conducted quite actively in recent years, the need for legal and institutional considerations has arisen since temporal storage (i.e. temporal copy) may be made not only at user devices but also in routers such as network equipments. This paper examines issues on temporary copy of copyrighted works mainly focusing on the articles and the related articles of the recently revised copyright law as well as the Free Trade Agreement between the Republic of Korea and the United States of America and further studies necessary institutions required to actualize in-network caching.

• Journal of Communications and Networks
• /
• v.14 no.6
• /
• pp.653-661
• /
• 2012

High-availability seamless redundancy (HSR) is a redundancy protocol for Ethernet networks that provides two frame copies for each frame sent. Each copy will pass through separate physical paths, pursuing zero fault recovery time. This means that even in the case of a node or a link failure, there is no stoppage of network operations whatsoever. HSR is a potential candidate for the communications of a smart grid, but its main drawback is the unnecessary traffic created due to the duplicated copies of each sent frame, which are generated and circulated inside the network. This downside will degrade network performance and might cause network congestion or even stoppage. In this paper, we present two approaches to solve the above-mentioned problem. The first approach is called quick removing (QR), and is suited to ring or connected ring topologies. The idea is to remove the duplicated frame copies from the network when all the nodes have received one copy of the sent frame and begin to receive the second copy. Therefore, the forwarding of those frame copies until they reach the source node, as occurs in standard HSR, is not needed in QR. Our example shows a traffic reduction of 37.5%compared to the standard HSR protocol. The second approach is called the virtual ring (VRing), which divides any closed-loop HSR network into several VRings. Each VRing will circulate the traffic of a corresponding group of nodes within it. Therefore, the traffic in that group will not affect any of the other network links or nodes, which results in an enhancement of traffic performance. For our sample network, the VRing approach shows a network traffic reduction in the range of 67.7 to 48.4%in a healthy network case and 89.7 to 44.8%in a faulty network case, compared to standard HSR.