• International Journal of Computer Science & Network Security
• /
• 제21권5호
• /
• pp.129-132
• /
• 2021

Two feature selection approaches are analyzed in this study. First Approach used in this paper is Filter Approach which comprises of correlation technique. It provides two reduced feature sets using positive and negative correlation. Secondly Approach used in this paper is the wrapper approach which comprises of Sequential Forward Selection technique. The reduced feature set obtained by positive correlation results comprises of Rate of Acceleration, Intensity and Formant. The reduced feature set obtained by positive correlation results comprises of Rasta PLP, Log energy, Log power and Zero Crossing Rate. Pitch, Rate of Acceleration, Log Power, MFCC, LPCC is the reduced feature set yield as a result of Sequential Forwarding Selection.

• 한국산업정보학회논문지
• /
• 제24권3호
• /
• pp.31-38
• /
• 2019

본 연구에서는 그린공급망(green supply chain: gSC) 네트워크 모델이 제안된다. 제안된 gSC 네트워크 모델은 환경적 요인 및 경제적 요인을 고려한다. 환경적 요인으로는 부품 및 제품 수송 과정에서 발생하는 CO2 발생량의 총비용 최소화를 고려하며, 경제적 요인으로는 부품 및 제품 생산처리에 필요한 처리비용, 수송과정에서 발생하는 수송비용, 각 단계에서 고려되는 설비들의 개설을 위한 개설비용의 최소화를 고려한다. 수리모형에서는 환경적 요인 및 경제적 요인을 위해 고려되는 다양한 비용들의 총합의 최소화를 목적함수로 사용하며, 각 단계 간 수송량의 제약 등 다양한 제약조건을 함께 고려한다. 제안된 수리모형의 이행을 위해 유전알고리즘(Genetic algorithm: GA) 접근법을 사용한다. 수치실험에서는 네 가지 규모의 gSC 네트워크 모델을 제시하고, 이를 다양한 수행도 척도들을 사용하여 GA 접근법을 통해 해결하였다. 실험결과는 제안된 gSC 네트워크 모델과 GA 접근법의 우수성을 입증하였다.

• Smart Structures and Systems
• /
• 제7권1호
• /
• pp.59-82
• /
• 2011

In this study, an output-only modal identification approach is proposed for decentralized wireless sensor nodes used for linear structural systems. The following approaches are implemented to achieve the objective. Firstly, an output-only modal identification method is selected for decentralized wireless sensor networks. Secondly, the effect of time-unsynchronization is assessed with respect to the accuracy of modal identification analysis. Time-unsynchronized signals are analytically examined to quantify uncertainties and their corresponding errors in modal identification results. Thirdly, a modified approach using complex mode shapes is proposed to reduce the unsynchronization-induced errors in modal identification. In the new way, complex mode shapes are extracted from unsynchronized signals to deal both with modal amplitudes and with phase angles. Finally, the feasibility of the proposed approach is evaluated from numerical and experimental tests by comparing with the performance of existing approach using real mode shapes.

• 한국ITS학회 논문지
• /
• 제7권4호
• /
• pp.118-129
• /
• 2008

차량 접근 경고 시스템(VAWS: Vehicle Approach Warning Systems)은 급커브 구간에 진입하는 차량에게 반대편 차선의 차량 진입 정보를 운전자에게 제공하여 사고 위험을 줄이는데 도움을 주기 위한 시스템이다. 본 논문에서는 VAWS를 위한 IEEE 802.15.4 기반 계층구조 센서 네트워크 모델을 제안한다. 제안하는 네트워크 모델에서 토폴로지 제어 프로토콜은 네트워크의 생존시간을 지속시킬 수 있도록 자가 구성(self-organizing) 방식으로 트리 기반 토폴로지를 형성한다. 또한, 간단하면서도 효율적인 라우팅 프로토콜은 이 토폴로지를 기반으로 라우팅 테이블을 구성하고 센서 노드에서 생성된 데이터 패킷을 노변 경고 메시지 디스플레이와 연결되어 있는 베이스 스테이션까지 멀티홉 방식으로 전달한다. 이 프로토콜들은 기존의 IEEE 802.15.4 MAC계층에 포함된 확장 MAC 형태로 설계되며, 급커브 구간을 모델링한 시나리오에서의 시뮬레이션을 통하여 제안하는 네트워크 모델이 에너지 효율 및 네트워크 처리량 면에서 높은 성능을 나타냄을 보인다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2003년도 추계학술대회 및 정기총회
• /
• pp.201-204
• /
• 2003

A hybrid artificial intelligence approach based on combining case based reasoning and neural networks is presented. The approach is designed to allow for solving blowing control of BOF(basic oxygen furnace), example of which lie at the core of steelmaking process control systems application in the steel industry. According to this hybrid approach, the system, when faced with a new problem, first retrieves similar cases and neural network is used to solve the problem. Experimental Results indicate that combining case based reasoning and neural network offers an efficient approach to solving control and prediction problem

• 산업공학
• /
• 제25권3호
• /
• pp.309-318
• /
• 2012

Forecasting probability or likelihood of technology development success has been a crucial factor for critical decisions in technology management such as R&D project selection and go or no-go decision of new product development (NPD) projects. This paper proposes an analytic network process (ANP) approach to forecasting of technology development success. Reviewing literature on factors affecting technology development success has constructed the ANP model composed of four criteria clusters : R&D characteristics, R&D competency, technological characteristics, and technological environment. An alternative cluster comprised of two elements, success and failure is also included in the model. The working of the proposed approach is provided with the help of a case study example of MRAM (magnetic random access memory) technology.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.281-286
• /
• 2005

The main objective of the research work presented in this article is to present a systematic approach for designing a multilayer feed-forward artificial neural network based self-tuning power system stabilizer (ST-ANNPSS). In order to suggest an approach for selecting the number of neurons in the hidden layer, the dynamic performance of the system with ST-ANNPSS is studied and hence compared with that of conventional PSS. Finally the effect of variation of loading condition and equivalent reactance, Xe is investigated on dynamic performance of the system with ST-ANNPSS. Investigations reveal that ANN with one hidden layer comprising nine neurons is adequate and sufficient for ST-ANNPSS. Studies show that the dynamic performance of STANNPSS is quite superior to that of conventional PSS for the loading condition different from the nominal. Also it is revealed that the performance of ST-ANNPSS is quite robust to a wide variation in loading condition.

• 한국멀티미디어학회논문지
• /
• 제19권9호
• /
• pp.1659-1668
• /
• 2016

Understanding 3D structure of scenes is of a great interest in various vision-related tasks. In this paper, we present a unified approach for estimating depth from a single monocular image. The key idea of our approach is to take advantages both of parametric learning and non-parametric sampling method. Using a parametric convolutional network, our approach learns the relation of various monocular cues, which make a coarse global prediction. We also leverage the local prediction to refine the global prediction. It is practically estimated in a non-parametric framework. The integration of local and global predictions is accomplished by concatenating the feature maps of the global prediction with those from local ones. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods both qualitatively and quantitatively.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.341-344
• /
• 2005

Mobile IPv6(MIPv6) allows a Mobile Node to talk directly to its peers while retaining the ability to move around and change the currently used IP address. One of the major issues regarding the basic Mobile IPv6 protocol is related to the handover management of a mobile node. This paper proposes efficient approach for adaptation of MIPv6 sing context information in roaming environments. To investigate on a efficient and secure handover procedure, proposed approach method will give us the following advantages: (l)the intention of context is to reduce latency, packet losses and avoid re-initiation of signaling to and from mobile nodes,(2) FMIPv6 aims to reduce handover latency due to IP protocol operations as small as possible in comparison to the inevitable link switching latency.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 춘계학술발표대회
• /
• pp.450-451
• /
• 2013

Considering the recent few years, the usage of mobile content has increased rapidly. This brings out the need for the new internet paradigm. Content-Centric Networking (CCN) caters this need as the future internet paradigm. However, so far, the issue of mobility in the network using CCN has not been considered very efficiently. In this paper, we propose clustering in the network. We apply clustered approach to CCN for catering the mobility of client node in the network. Through this approach we achieve better convergence time and control overhead in contrast to the basic CCN.