A Study on the Face Recognition Using PCA Algorithm

이준탁(John-Tark Lee),곽려혜(Lee-Hui Kueh) 한국지능시스템학회 2007 한국지능시스템학회논문지 Vol.17 No.2

In this paper, a face recognition algorithm system using Principal Component Analysis (PCA) is proposed. The algorithm recognized a person by comparing characteristics (features) of the face to those of known individuals of Intelligent Control Laboratory (ICONL) face database. Simulations are carried out to investigate the algorithm recognition performance, which classified the face as a face or non-face and then classified it as known or unknown one. Particularly, a Principal Components of Linear Discriminant Analysis (PCA + LDA) face recognition algorithm is also proposed in order to confirm the recognition performances and the adaptability of a proposed PCA for a certain specific system.

Newly Regularized LDA for SSS Problem with application to Face Recognition

곽려혜(Lee Hui Kueh),김권우(Kwon-Woo Kim),한동열(Dong-Yeol Han),이승호(Seung-Ho Lee),이준탁(John-Tark Lee),이권순(Kwon-Soon Lee) 대한전기학회 2010 대한전기학회 학술대회 논문집 Vol.2010 No.7

A newly proposed FR (Face Recognition) approach with a weighted regularization parameter based on the conventional R-LDA (Regularized Linear D iscriminant A nalysis) method was presented in this paper. SSS (Sm all Sample Size) problem refers to the total number of training samples is less than the dimension of face feature space and all the scatter matrices of LDA are singular. Therefore, it is impossible to apply the LDA algorithm to the FR. In this paper, it was attempted to optimize the revised Fisher's criterion with a weighted regularization parameter as a solution of the SSS problem. Simulations using ORL (Olivetti Research Lab) database in MATLAB were simulated in order to evaluate the recognition performance of the proposed FR. In addition, the recognition performance of the proposed approach was compared to the ones of the well-known conventional methods such as Eigenfaces and R-LDA, which were established in this paper.

기생용량을 고려한 원격 RF 센서 시스템의 수학적 모델링

김경엽(Kyung-yup Kim),이준탁(John-tark Lee) 한국정보기술학회 2008 한국정보기술학회논문지 Vol.6 No.5

In this paper, Passive Telemetry RF Sensor System considering stray parameter is proposed. Passive Telemetry RF Sensor System using inductive coupling is composed of passive components such as R, L and C which have stray parameters in the range of high frequency. In case that Passive Telemetry RF Sensor system operates disregarding stray parameters in high frequency, it is difficult to expect high accuracy of reading sensor. So, in order to improve the accuracy of reading sensor, the mathematical model considering stray parameters is proposed. The efficiency of derived model considering stray parameters is verified by comparing the measured output voltage with simulated output voltage.

임피던스 해석에 기반한 엔진 오일 열화 진단 시스템에 관한 연구

박가람(Ka-Ram Park),이준탁(John-Tark Lee) 한국정보기술학회 2018 한국정보기술학회논문지 Vol.16 No.1

In this study, the diagnosis system for degradation of engine oil based on the impedance analysis was designed to predict the degradation trend of engine oil and to estimate the degree of degradation. The electrical characteristics of the engine oil were interpreted through measured G and B using an impedance analyzer. The degradation equivalent circuit of engine oil was modeled based on the measured data, and the degradation trend of engine oil was estimated by the variation of the G<SUB>e</SUB> and B<SUB>e</SUB> which were estimated through modeling. To extract the G<SUB>m</SUB> and B<SUB>m</SUB> of the engine oil, the parallel plate electrode type sensor was fabricated and the Lock-in Amplifier was designed. The effectiveness of the degradation diagnosis system was verified by comparing the extracted data and the estimated data.

펄스파를 이용한 자왜 방식의 레벨 센서 시스템의 구현

최우진(Woo-Jin Choi),이준탁(John-Tark Lee) 한국정보기술학회 2012 한국정보기술학회논문지 Vol.10 No.6

In this paper, we introduced the implementation of the magnetostrictive type tank level sensor system for the ship. The conventional level measurement system uses Hall effect elements or reed switches in the stem, and these are placed in 10 ㎜ interval and turn on and off with the up-and-down liquid levels by the permanent magnet builtin float. These types have a feature of the compact construction. On the other hand, to increase the resolution, the more components and cost are needed. To implement the high accuracy, low cost and continuous measurement system for the liquid level, the proposed magnetostrictive type sensor consists of the pulse interrogation circuit and the resonant sensing circuit. This is a simple structure of transmitting the current pulse on the waveguide and sensing the reflected torsional signals by the magnetostrictive effect. The level can be calculated from the time difference between the interrogation and sensing signals. The implemented specification of sensor is 7,000 ㎜ range with 1mm resolution, less than 10 ㎜ error.

RLS 알고리즘을 이용한 원격 RF 센서 시스템의 정전용량 파라메타 추정

金璟燁(Kyung-Yup Kim),李浚柝(John-Tark Lee) 대한전기학회 2008 전기학회논문지 Vol.57 No.5

In this paper, Capacitive Telemetry RF Sensor System using Recursive Least Square (RLS) algorithm was proposed. General Telemetry RF Sensor System means that it should be "wireless", "implantable" and "batterless". Conventional Telemetry RF Sensor System adopts Integrated Circuit type, but there are many defects like complexity of structure and the limitation of large power consumption in some cases. In order to overcome these disadvantages, Telemetry RF Sensor System based on inductive coupling principle was proposed in this paper. Proposed Telemetry RF Sensor System is very simple because it consists of R, Land C and measures the changes of environment like pressure and humidity in the type of capacitive value. This system adopted RLS algorithm for estimation of this capacitive parameter. For the purpose of applying RLS algorithm, proposed system was mathematically modelled with phasor method and was quasi-linearized. As two parameters such as phase and amplitude of output voltage for estimation were needed, Phase Difference Detector and Amplitude Detector were proposed respectively which were implemented using TMS320C2812 made by Texas Instrument. Finally, It is verified that the capacitance of proposed telemetry RF Sensor System using RLS algorithm can be estimated efficiently under noisy environment.

Unscented Kalman Filter를 이용한 원격 RF 센서 시스템 구현

金璟燁(Kyung-Yup Kim),李浚柝(John-Tark Lee) 대한전기학회 2008 전기학회논문지 Vol.57 No.10

In this paper, Passive Telemerty RF Sensor System using Unscented Kalman Filter algorithm (UKF) is proposed. General Passive Telemerty RF Sensor System means that it should be "wireless", "implantable" and "batterless". Conventional Passive Telemerty RF Sensor System adopts Integrated Circuit type, but there are defects like complexity of structure and limit of large power consumption in some cases. In order to overcome these kinds of faults, Passive Telemetry RF Sensor System based on inductive coupling principle is proposed in this paper. Because passive components R, L, C have stray parameters in the range of high frequency such as about 200[㎑] used in this paper, Passive Telemetry RF Sensor System considering stray parameters has to be derived for accurate model identification. Proposed Passive Telemetry RF Sensor System is simple because it consists of R, L and C and measures the change of environment like pressure and humidity in the type of capacitive value. This system adopted UKF algorithm for estimation of this capacitive parameter included in nonlinear system like Passive Telemetry RF Sensor System. For the purpose of obtaining learning data pairs for UKF Algorithm, Phase Difference Detector and Amplitude Detector are proposed respectively which make it possible to get amplitude and phase between input and output voltage. Finally, it is verified that capacitive parameter of proposed Passive Telemetry RF Sensor System using UKF algorithm can be estimated in noisy environment efficiently.

Unscented Kalman Fiter를 이용한 원격 RF 센서 시스템의 파라메타 추정기법

김경엽(Kyung-Yup Kim),이준탁(John-Tark Lee) 한국지능시스템학회 2008 한국지능시스템학회 학술발표 논문집 Vol.18 No.1

본 연구는 UKF Algorithm올 이용한 정전용량형 원격RF센서시스템을 개발하였다. 원격 RF센서 시스템이란 wireless, implantable 그리고 batterless을 만족하는 센서 시스템을 의미한다. 기존의 원격 RF센서 시스템은 보편적으로 집적회로 타입을 채택하지만, 그 구조의 복잡성과 전력소모의 제약을 받는다. 이러한 제약을 해결하기 위해 본 연구에서는 R, L 그리고 C만으로 구성되어있는 유도결합원리를 이용한 원격 RF센서 시스템을 제안하였다. 제안된 RF 센서 시스템은 압력 혹은 습도와 같은 환경의 변화를 정전용량 값으로 측정할 수 있으며 센서의 정전 용량 값을 측정하기 위해 비선형시스템의 파라메타추정에 적합한 Unscented Kalman Filter(UKF) 기법을 채택하였다. UKF 기법을 이용하기 위해 제안된 시스템은 페이저법을 사용하여 수학적으로 모델링되었다. 마지막으로, 제안된 UKF 알고리즘을 이용한 원격 RF센서시스템이 잡음환경에서도 정전용량값을 비교적 정확하게 추정가능함을 확인하였다.

자왜센서 기반의 액위 계측 시스템에서의 합성적분을 이용한 탄성파 모델링

김현철(Hyeon-Cheol Kim),이준탁(John-Tark Lee) 대한전기학회 2018 대한전기학회 학술대회 논문집 Vol.2018 No.-

펄스파 자왜 센서를 이용한 고정밀 액위 센서 시스템의 실현에 관한 연구

최우진(Woo-Jin Choi),이준탁(John-Tark Lee) 대한전기학회 2013 전기학회논문지 Vol.62 No.3

In this paper, we introduce the implementation of high accurate level sensor system using the pulse wave type magnetostriction sensor. When a current pulse flows along the waveguide, the magnetic field also propagates towards the end of waveguide. When this magnetic field just passes the position of the magnet for level detection, the resultant magnetic field by these two magnetic fields makes a torsional reflected signal. This is used to calculate the time difference between a interrogation pulse wave and this torsional reflected signal. The key elements and characteristics were investigated to implement level sensor system based on this principle. We introduce a method to calculate the speed of ultrasonic reflected signal and how to make a model of sensing coil. In particular, we experiment with the characteristics of the torsional reflected signal according to the changes of the interrogation voltage and displacement. To make high accurate level sensor system, two methods were compared. One is to use the comparator and time counter, the other is STFT(Short Time FFT) which is capable of the time-frequency analysis.