• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.141-149
• /
• 2024

This paper proposes a configuration automation technique to minimize service interruption time in the event of a corporate network access layer switch failure. The automation is achieved without the need for a separate external system, as the network setting information is stored in a container inside the switch, enabling rapid recovery without requiring separate storage. This approach ensures the continuity of network services and demonstrates the efficiency of configuration automation. The proposed technique improves corporate network stability by providing a quick response in the event of a failure.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.5B
• /
• pp.477-483
• /
• 2011

In this paper, we propose the design and implementation of the storage-based data sharing system in the separate network environment to improve efficiency of data transmission. The previous system generates files per received packet and transmit files to another network through storage. This system causes inefficiency by reading unnecessary blocks, when it transmits a number of files through storage. Our proposed system deals with this inefficiency by adopting concept of snapshot. Consequently, we create one file with snapshot so that the number of files can be reduced and the file size can be optimized according to the block size. The proposed system improves the response time significantly with the minimized reading of unnecessary blocks, compared to the previous system.

• Journal of applied mathematics & informatics
• /
• v.37 no.3_4
• /
• pp.271-279
• /
• 2019

We investigate how a feedforward neural network works to separate a geometric region from its complement. Our investigations are restricted to regions in ${\mathbb{R}}$ or ${\mathbb{R}}^2$ including an interval, a triangular region, a disk and the union of two disjoint disks. We also examine what happens at each layer of the network.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2006.05a
• /
• pp.209-212
• /
• 2006

In this study, Support Vector Machine(SVM) and Artificial Neural Network(ANN) are used for developing the defect diagnostic algorithm of the aircraft turbo-shaft engine. Effect of altitude variation on the Defect Diagnostics algorithm has been included and evaluated. Separate learning Algorithm(SLA) suggested with ANN to loam the performance data selectively after classifying the position of defects by SVM improves the classification speed and accuracy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.2
• /
• pp.447-460
• /
• 1996

Network optimization and design procedures often separate quality of service (QOS) performance measures from reliability issues. This paper considers channel allocation and flow assignment (routing) in a network subject to link failures. Fault-tolerant channel allocation and flow assingments are determined which minimize network cost while maintaining QOS performance requirements. this approach is shown to yield significant network cost reductions compared to previous heuristic methods used in the design of packet switched network with unreliable links.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.2
• /
• pp.449-456
• /
• 2018

Many organizations divide the network to manage the network in order to prevent the leakage of internal data between separate organizations / departments by sending and receiving unnecessary traffic. The most fundamental network separation method is based on physically separate equipment. However, there is a case where a network is divided and operated logically by utilizing a virtual LAN (VLAN) network access control function that can be constructed at a lower cost. In this study, we first examined the possibility of bypassing the logical network separation through VLAN ID scanning and double encapsulation VLAN hopping attack. Then, we showed and implemented a data leak scenario by utilizing the acquired VLAN ID. Furthermore, we proposed a simple and effective technique to detect and prevent the double encapsulation VLAN hopping attack, which is also implemented for validation. We hope that this study improves security of organizations that use the VLAN-based logical network separation by preventing internal data leakage or external cyber attack exploiting double encapsulation VLAN vulnerability.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.476-488
• /
• 2021

Objective: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. Materials and Methods: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. Results: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). Conclusion: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.

• 한국정보통신설비학회:학술대회논문집
• /
• 2007.08a
• /
• pp.121-124
• /
• 2007

This article describes a function and structure of access network equipment under BcN environment. Access network until now have constructed separately to offer voice, data service. However, simplifies network structure, function that can do traffic concentration, subscriber certification, individual charging, QoS according to service and routing is required in BcN. In this paper, compare method offering by separate system with existing access network and method that offer integrating function inside system for structure of suitable access network to BcN and search structure of access network equipment for desirable access network of hereafter. Composition of this paper is as following. In Chapter 2, establishment history and structure of access network until present. In Chaprte 3, define suitable requirement and functions to BcN. And compare structure for access net work that is new with present. Last Chapter 4, suggests direction of structure of BcN access network and concludes conclusion.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.11 no.1
• /
• pp.43-50
• /
• 2007

In this study, Hybrid Separate Learning Algorithm(SLA) consisting of Support Vector Machine(SVM) and Artificial Neural Network(ANN) has been used for developing the defect diagnostic algorithm of the aircraft turbo-shaft engine in the off-design range considering altitude variation. Although the number of teaming data and test data highly increases more than 6 times compared with those required for the design condition, the proposed defect diagnostics of gas turbine engine using SLA was verified to give the high defect classification accuracy in the off-design range considering altitude variation.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.10
• /
• pp.871-880
• /
• 2000

A twin-servo mechanism is used to increase the payload capacity and assembling speed of high precision motion control systems such as semiconductor chip mounters. In this paper, we focus on the modeling of the twin-servo system and propose its network representation. And also, we propose a robust synchronizing motion control algorithm to cancel out the skew motion of the twin-servo system caused by different dynamic characteristics of two driving systems and the vibration generated by high accelerating and decelerating motions. The proposed control algorithm consists of separate feedback motion control algorithms for each driving system and a skew motion compensation algorithm. A robust tracking controller based on internal-loop compensation is proposed as a separate motion controller and its disturbance attenuation property is shown. The skew motion compensation algorithm is also designed to maintain the synchronizing motion during high speed operation, and the stability of the whole closed loop system is proved based on passivity theory. Finally, experimental results are shown to illustrate control performance.