• 융합보안논문지
• /
• 제1권1호
• /
• pp.37-45
• /
• 2001

In this paper, separated and optimized pattern database model is proposed. In order to improve efficiency of Network-based IDS, pattern database is classified by proper basis. Classification basis is decided by the specific Intrusions validity on specific target. Using this model, IDS searches only valid patterns in pattern database on each captured packets. In result, IDS can reduce system resources for searching pattern database. So, IDS can analyze more packets on the network. In this paper, proper classification basis is proposed and pattern database classified by that basis is formed. And its performance is verified by experimental results.

• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2003년도 하계학술대회 논문집
• /
• pp.145-148
• /
• 2003

In this paper an nonlinear neuro PID controller is constructed by the control system of general PID controller using a Self-Recurrent Neural Network. And the games of the PID controller in the proposed control system are automatically adjusted by back-propagation algorithm of the neural network. Applying to the position control system, it's performance is verified through the results of computer simulation.

• 융합보안논문지
• /
• 제12권3호
• /
• pp.67-73
• /
• 2012

본 논문에서는 지그비를 이용한 무선 기반 센서 네트워크 단점을 극복하기 위하여 유무선 네트워크 연동 기술을 이용한 하이브리드 센서 네트워크 구현 방안을 제시하였다. 제안된 유무선 연동 센서 네트워크는 CATV망에서의 저손실 전송 특성을 바탕으로 실내 무선 환경의 열악한 전송 특성을 보완할 수 있으며, 마찬가지로 동일 주파수 대역의 무선랜과 블루투스의 간섭에서도 자유로울 수 있다. 또한 이미 충분한 인프라가 구축되어 있는 CATV망을 변경없이 사용하고, 기존 무선망의 전송 부정확성에 대한 안정성과 예측 가능한 전송 링크를 제공함으로써 네트워크 설계가 보다 효율적이었으며, 센서 네트워크의 안정성과 높은 신뢰성을 보장하였다.

• 한국정보과학회논문지:정보통신
• /
• 제34권5호
• /
• pp.305-315
• /
• 2007

광대역통합망(Broadband Convergence Network, BcN)은 전화, 인터넷, 방송 네트워크 등 개별적으로 운용되어오던 네트워크들을 하나의 통합망으로 구축, 구동, 관리하는 차세대 네트워크이다. 개별적으로 운용되어오던 네트워크들이 하나로 통합되면서 서비스 별로 산재해 있던 네트워크의 위협요소는 하나의 통합망에서 더욱더 위력적인 요소로 다가올 것이다. 본 논문에서는 BcN 서비스들이 악성 공격에 대해 지속적인 서비스 운영을 보장하기 위한 네트워크 디자인 방법을 제안한다. 본 연구는 서비스 시간과 공간 중요도를 바탕으로 BcN 필수 서비스 구성요소를 도출하고, 구성요소의 형태에 따라 서버 형태, 게이트웨이 형태, 복합 형태의 세 가지 타입으로 구분한다. BcN 환경에서 발생 가능한 공격 시나리오들을 통해 BcN 필수 서비스의 침입감내 기술 적용 방안을 모색한다. 이를 통하여 하드웨어 중복성과 Policy 서버의 보안 정책 설정을 통한 BcN 침입감내 네트워크 디자인을 제안한다. 본 논문에서는 제안한 프로토타입 네트워크를 BcN에 적용하기 전과 적용한 후 BcN에서 공격이 발생되었을 때의 시나리오를 통하여 BcN의 침입감내를 가능케 함을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권9호
• /
• pp.4334-4356
• /
• 2017

In orthogonal frequency-division multiplexing (OFDM) systems, phase noise introduced by the local oscillators can cause bit error rate (BER) performance degradation. To solve the phase noise problem, a novel orthogonal-polarization-based phase noise self-cancellation (OP-PNSC) scheme is proposed. First, the efficiency of canceling the phase noise of the OP-PNSC scheme in the AWGN channel is investigated. Then, the OP-PNSC scheme in the polarization-dependent loss (PDL) channel is investigated due to power imbalance caused by PDL, and a PDL pre-compensated OP-PNSC (PPC -OP-PNSC) scheme is proposed to mitigate the power imbalance caused by PDL. In addition, the performance of the PPC-OP-PNSC scheme is investigated, where the signal-to-interference-plus-noise ratio (SINR) and spectral efficiency (SE) performances are analyzed. Finally, a comparison between the OP-PNSC and polarization diversity scheme is discussed. The numerical results show that the BER and SINR performances of the OP-PNSC scheme outperform the case with the phase noise compensation and phase noise self-cancellation scheme.

• 한국멀티미디어학회논문지
• /
• 제23권10호
• /
• pp.1236-1249
• /
• 2020

In a most recent object tracking research work, applying Convolutional Neural Network and Recurrent Neural Network-based strategies become relevant for resolving the noticeable challenges in it, like, occlusion, motion, object, and camera viewpoint variations, changing several targets, lighting variations. In this paper, the LSTM Network-based Tracking association method has proposed where the technique capable of real-time multi-object tracking by creating one of the useful LSTM networks that associated with tracking, which supports the long term tracking along with solving challenges. The LSTM network is a different neural network defined in Keras as a sequence of layers, where the Sequential classes would be a container for these layers. This purposing network structure builds with the integration of tracking association on Keras neural-network library. The tracking process has been associated with the LSTM Network feature learning output and obtained outstanding real-time detection and tracking performance. In this work, the main focus was learning trackable objects locations, appearance, and motion details, then predicting the feature location of objects on boxes according to their initial position. The performance of the joint object tracking system has shown that the LSTM network is more powerful and capable of working on a real-time multi-object tracking process.

• 디지털융복합연구
• /
• 제12권12호
• /
• pp.323-328
• /
• 2014

융합망에 사용되는 D-MAC 프로토콜은 사물간 무선링크를 연결하기 위해 설계된 프로토콜이다. 이 프로토콜은 이웃 노드 가운데 로컬 데이터 교환과 수집을 위해 제공되고, 싱크로부터 센서 노드로 제어패킷과 관심 패킷이 분배된다. 본 논문에서는 융합망의 D-MAC 보안 인증 적용 여부에 따른 전력소모 효율성에 대해 분석하였다. 인증기법이 MAC 통신에 적용될 경우, 인증처리 유무에 따라 프리앰블의 에너지 소비 여부가 연관이 된다. 인증이 적용될 경우 서비스 공격에 대응하여 에너지 소비가 감소된다. 향후 보안 인증기법에 관련한 연구를 수행할 계획이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권6호
• /
• pp.1979-1995
• /
• 2015

Network convergence is regarded as the development tendency of the future wireless networks, for which self-organization paradigms provide a promising solution to alleviate the upgrading capital expenditures (CAPEX) and operating expenditures (OPEX). Self-optimization, as a critical functionality of self-organization, employs a decentralized paradigm to dynamically adapt the varying environmental circumstances while without relying on centralized control or human intervention. In this paper, we present comprehensive surveys of heterogeneous networks (HetNets) and investigate the enhanced self-optimization models. Self-optimization approaches such as dynamic mobile access network selection, spectrum resource allocation and power control for HetNets, etc., are surveyed and compared, with possible methodologies to achieve self-optimization summarized. We hope this survey paper can provide the insight and the roadmap for future research efforts in the self-optimization of convergence networks.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.142-146
• /
• 2023

We present a method for generating 3D structures and rendering objects by combining VAE (Variational Autoencoder) and GAN (Generative Adversarial Network). This approach focuses on generating and rendering 3D models with improved quality using residual learning as the learning method for the encoder. We deep stack the encoder layers to accurately reflect the features of the image and apply residual blocks to solve the problems of deep layers to improve the encoder performance. This solves the problems of gradient vanishing and exploding, which are problems when constructing a deep neural network, and creates a 3D model of improved quality. To accurately extract image features, we construct deep layers of the encoder model and apply the residual function to learning to model with more detailed information. The generated model has more detailed voxels for more accurate representation, is rendered by adding materials and lighting, and is finally converted into a mesh model. 3D models have excellent visual quality and accuracy, making them useful in various fields such as virtual reality, game development, and metaverse.

• 한국통신학회논문지
• /
• 제22권1호
• /
• pp.64-71
• /
• 1997

Digital communication channels are imparied by linear effects such as dispersion, ISI(intersymbol Interference), fading phenomenon etc. But, the practical channel equalization system is required to design for compensating the nonlinear distortion caused by harmonic distortion etc. This paper is a study on the performance of nonlinear channel equalization using RBF(Radial Basis Funclion) network, which has the equivalent structure to the optimal Basian filter. Expecially, the variance of RBF network is modifiedby nonlinear polynomial filters to compare the convergence characteristic of nonlinear channel equalization. Experimental results show that the modified RBF network achieves the faster convergence property than conventional RBF network. Moreover, the RBF network ofhigher order variance modified represents the better performance than that of lower order variance in the bandpass channels and second/third order polynomial channels.