• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권10호
• /
• pp.5049-5062
• /
• 2016

This paper analyzes the secrecy performance of an amplify-and-forward (AF) relay network, where a multi-antenna eavesdropper attempts to overhear the transmitted message from a multi-antenna source to a multi-antenna destination with a single antenna relay. Firstly, we derive the approximate analytical expressions for the secrecy outage probability (SOP) and average secrecy rate (ASR) of the relay network. Then, asymptotic expressions of SOP and ASR at high main-to-eavesdropper ratio (MER) are also provided to reveal the diversity gain of the secure communication. Finally, numerical results are given to verify the theoretical analysis and show the effect of the number of antennas in the considered relay network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권5호
• /
• pp.2253-2272
• /
• 2018

We propose a deep learning method for multi-focus image fusion. Unlike most existing pixel-level fusion methods, either in spatial domain or in transform domain, our method directly learns an end-to-end fully convolutional two-stream network. The framework maps a pair of different focus images to a clean version, with a chain of convolutional layers, fusion layer and deconvolutional layers. Our deep fusion model has advantages of efficiency and robustness, yet demonstrates state-of-art fusion quality. We explore different parameter settings to achieve trade-offs between performance and speed. Moreover, the experiment results on our training dataset show that our network can achieve good performance with subjective visual perception and objective assessment metrics.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2003년도 추계 학술발표회논문집
• /
• pp.66-73
• /
• 2003

The technique for the seismic reliability evaluation of the electric power network is presented. In the previous study, the state of the substations was represented by the bi-state which is classified as failure or survival. However, the hi-state model can result in oversimplified analysis, because substations are worked by the parallel operating system. In this paper, Considering the characteristics of the parallel operating system, the damage of the substation is expressed by the multi-state for the more realistic seismic reliability evaluation. Using Monte-Carlo simulation method, the seismic reliability for Korean 345㎸ electric power network is evaluated. Analysis results show that reliability levels of the network by the multi-state analysis is higher than that by the hi-state analysis and the electric power network in southeastern area of the Korean Peninsular may be vulnerable to earthquakes.

• International Journal of Computer Science & Network Security
• /
• 제21권7호
• /
• pp.56-62
• /
• 2021

The surge in generic attacks execution against cipher text on the computer network has led to the continuous advancement of the mechanisms to protect information integrity and confidentiality. The implementation of explicit decision tree machine learning algorithm is reported to accurately classifier generic attacks better than some multi-classification algorithms as the multi-classification method suffers from detection oversight. However, there is a need to improve the accuracy and reduce the false alarm rate. Therefore, this study aims to improve generic attack classification by implementing two hybridized decision tree algorithms namely Naïve Bayes Decision tree (NBTree) and Logistic Model tree (LMT). The proposed hybridized methods were developed using the 10-fold cross-validation technique to avoid overfitting. The generic attack detector produced a 99.8% accuracy, an FPR score of 0.002 and an MCC score of 0.995. The performances of the proposed methods were better than the existing decision tree method. Similarly, the proposed method outperformed multi-classification methods for detecting generic attacks. Hence, it is recommended to implement hybridized decision tree method for detecting generic attacks on a computer network.

• Journal of Information Processing Systems
• /
• 제18권3호
• /
• pp.311-318
• /
• 2022

Tobacco sales enterprises often need to summarize and verify the daily sales bills, which may consume substantial manpower, and manual verification is prone to occasional errors. The use of artificial intelligence technology to realize the automatic identification and verification of such bills offers important practical significance. This study presents a novel multi-branch residual network for tobacco sales bills to improve the efficiency and accuracy of tobacco sales. First, geometric correction and edge alignment were performed on the input sales bill image. Second, the multi-branch residual network recognition model is established and trained using the preprocessed data. The comparative experimental results demonstrated that the correct recognition rate of the proposed method reached 98.84% on the China Tobacco Bill Image dataset, which is superior to that of most existing recognition methods.

• International journal of advanced smart convergence
• /
• 제13권2호
• /
• pp.16-24
• /
• 2024

With an increase in the relevance of next-generation integrated networking environments, the need to effectively utilize advanced networking techniques also increases. Specifically, integrating Software-Defined Networking (SDN) with Multi-access Edge Computing (MEC) is critical for enhancing network flexibility and addressing challenges such as security vulnerabilities and complex network management. SDN enhances operational flexibility by separating the control and data planes, introducing management complexities. This paper proposes a reinforcement learning-based network path optimization strategy within SDN environments to maximize performance, minimize latency, and optimize resource usage in MEC settings. The proposed Enhanced Proximal Policy Optimization (PPO)-based scheme effectively selects optimal routing paths in dynamic conditions, reducing average delay times to about 60 ms and lowering energy consumption. As the proposed method outperforms conventional schemes, it poses significant practical applications.

• ETRI Journal
• /
• 제31권5호
• /
• pp.534-544
• /
• 2009

Finding link-disjoint or node-disjoint paths under multiple constraints is an effective way to improve network QoS ability, reliability, and so on. However, existing algorithms for such scheme cannot ensure a feasible solution for arbitrary networks. We propose design principles of an algorithm to fill this gap, which we arrive at by analyzing the properties of optimal solutions for the multi-constrained link-disjoint path pair problem. Based on this, we propose the link-disjoint optimal multi-constrained paths algorithm (LIDOMPA), to find the shortest link-disjoint path pair for any network. Three concepts, namely, the candidate optimal solution, the contractive constraint vector, and structure-aware non-dominance, are introduced to reduce its search space without loss of exactness. Extensive simulations show that LIDOMPA outperforms existing schemes and achieves acceptable complexity. Moreover, LIDOMPA is extended to the node-disjoint optimal multi-constrained paths algorithm (NODOMPA) for the multi-constrained node-disjoint path pair problem.

• 한국멀티미디어학회논문지
• /
• 제19권12호
• /
• pp.1909-1918
• /
• 2016

This paper presents a unified framework for joint Convolutional Neural Network (CNN) based vehicle detection by leveraging multi-spectral image pairs. With the observation that under challenging environments such as night vision and limited light source, vehicle detection in a single color image can be more tractable by using additional far-infrared (FIR) image, we design joint CNN architecture for both RGB and FIR image pairs. We assume that a score map from joint CNN applied to overall image can be considered as confidence of vehicle existence. To deal with various scale ratios of vehicle candidates, multi-scale images are first generated scaling an image according to possible scale ratio of vehicles. The vehicle candidates are then detected on local maximal on each score maps. The generation of overlapped candidates is prevented with non-maximal suppression on multi-scale score maps. The experimental results show that our framework have superior performance than conventional methods with a joint framework of multi-spectral image pairs reducing false positive generated by conventional vehicle detection framework using only single color image.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 추계종합학술대회
• /
• pp.677-681
• /
• 2002

기존의 고정 단말기(PC)에서만 주로 행해지던 각종 다중 사용자 접속 온라인 응용이 최근 모바일 단말기의 급속한 확산으로 기존 PC와 PDA, 휴대폰 등이 공동 작업을 수행하는 멀티 플랫폼 기반 온라인 응용으로 전환되고 있다. 이 논문에서는 멀티 플랫폼 기반 네트워크 응용을 위한 기반 구조를 제안하였다. 그리고 다양한 클라이언트의 프로세서 처리 능력과 통신 속도의 비대칭이라는 멀티 플랫폼 응용의 특징을 고려한 중복 일관성 제어 기법, 다양한 클라이언트간의 변경 전파 프로토콜을 제안하였다. 그리고 멀티 플랫폼 기반 채팅 프로그램을 제작하여 제안한 구조 및 기법들이 적절히 동작함을 보였다.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2005년도 학술대회 논문집
• /
• pp.81-87
• /
• 2005

이 논문은 자동차에서 제어 네트워크로 이미 신뢰성이 확인된 CAN(Controller Area Network) 필드버스를 산업계 복수전동기 제어에 적용하기 위하여 지능형 제어모듈로 CAN 이 내장된 DSP2812 프로세서를 이용하여 제어 및 모니터링기술을 개발하였다. 산업계에 광범위하게 사용되고 있는 유도전동기를 대상으로 여러 대의 유도전동기를 제어하기 위한 제어 알고리즘과 CAN기반제어네트워크 구축방법을 개발하였다. 이 시스템 성능을 평가하기 위하여 2대의 유도전동기 인버터 구동시스템에 적용하여 CAN 기반 네트워크 제어 실험을 수행하였다. 그 결과 광범위한 속도와 정역회전에서 실시간 네트워크 기반 제어성능을 확인하였다.