http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
센서노드의 RSS 및 가속도 센서를 이용한 상황 분류 기법에 관한 연구
장총위(Yui-Su Youk),채부경(Bu-Kyung Chae),김성호(Sung-Ho Kim) 한국지능시스템학회 2008 한국지능시스템학회 학술발표 논문집 Vol.18 No.2
유비쿼터스 컴퓨팅 기술의 여러 응용 서비스에서 가장 핵심적인 요소 기술 중의 하나는 상황인식기술이다. 최근 가속도 센서를 이용하여 상황을 분류하는 기술에 대한 연구가 다양하게 진행되고 있으며, 이를 통해 다양한 상황분류 알고리즘과 기술들이 출현하게 되었다. 하지만 가속도 센서는 사용자의 제스쳐의 분류는 가능하지만 사용자의 이동상황 중 발생되는 다양한 동작에 대한 분류가 어렵다는 문제를 갖는다. 본 논문에서는 최근 위치추적시스템에 적극적으로 도입ㆍ운영되고 있는 센서노드의 RSS(Received Signal Strength)와 3축 가속도 센서를 활용하여 사용자의 이동상황 중 발생되는 상황을 효율적으로 분류하는 기법을 제안하고, 실제 테스트 베드에서의 실험을 통해 제한된 기법의 유용성을 확인하고자 한다.
Application of Kalman Filter to Cricket based Indoor localization system
Cong-Yi Zhang(장총위),Sung-Ho Kim(김성호) 한국지능시스템학회 2008 한국지능시스템학회 학술발표 논문집 Vol.18 No.1
Kalman Filter is an efficient recursive filter that estimates the state of a dynamic system from a series of incomplete and noisy measurement. The filter is very powerful in the field of autonomous and assisted navigation. In this paper, we carry out comparative stduy to validate the performance of the application of Kalman Filter. We will build personal localization system based on Cricket mote, our system can present the real-time position of person when the man with PDA moves around. The proposed system is composed of cricket sensor networks, PDA and host computer. There is one listener attached to the PDA. The PDA will get the distance data from the listener synchronously. It will calculate the position of the person in the coordinate of the Cricket system with the trilateration method. Furthermore, it sends the real-time position information to the host computer by Bluetooth. The host computer will use Kalman Filter to process data and get the final estimated track of the person.
Cong yi Zhang(장총위),Sui-jin Kim(김수진),Sung-Ho Kim(김성호) 한국지능시스템학회 2009 한국지능시스템학회 학술발표 논문집 Vol.19 No.1
In this paper, a fault diagnosis system for rotating machine using wavelet packet transform (WPT) and artificial neural network (ANN) is described. In most fault diagnosis for rotating machines, WPT is a well-known signal processing technique for previous work used for speech recognition. In previous work, WPT can improve the continuous wavelet transform (CWT) used over a longer computing time and huge operand. It can also solve the frequency-band disagreement by discrete wavelet transform (DWT) only breaking up the approximation version. In the experimental work, the wavelets are used as mother wavelets to build and perform the proposed WPT technique. In the classification, an Elman neural network is utilized.
A New Auto-Localization Scheme in Sensor Networks
김성호,장총위,Kim, Sung-Ho,Zhang, Cong Yi Institute of Control 2008 제어·로봇·시스템학회 논문지 Vol.14 No.9
Many sensor network applications require that each node's sensor data stream be annotated with its physical location in some coordinate system. Equipping GPS on every sensor node is often expensive and does not work in indoor deployments. Recently, cricket-based localization system is often used for indoor localization system. It is very important to know the exact position of beacons in cricket-based localization system for identifying moving sensor node's position. In this paper, a new method, Mobile Listener Detect Algorithm (MLD) which can automatically calculate the unknown newly installed beacons is proposed. For the verification of the feasibility of the proposed scheme, we have conducted several experiments.
A New Auto-Localization Scheme in Sensor Networks
Sung-Ho Kim(김성호),Cong yi Zhang(장총위) 제어로봇시스템학회 2008 제어·로봇·시스템학회 논문지 Vol.14 No.9
Many sensor network applications require that each node’s sensor data stream be annotated with its physical location in some coordinate system. Equipping GPS on every sensor node is often expensive and does not work in indoor deployments. Recently, cricket-based localization system is often used for indoor localization system. It is very important to know the exact position of beacons in cricket-based localization system for identifying moving sensor node’s position. In this paper, a new method, Mobile Listener Detect Algorithm (MLD) which can automatically calculate the unknown newly installed beacons is proposed. For the verification of the feasibility of the proposed scheme, we have conducted several experiments.