• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권1호
• /
• pp.16-21
• /
• 2003

The accuracy in maneuvering target tracking using multiple models is resulted in by the suitability of each target motion model to be used. The interacting multiple model (IMM) method and the adaptive IMM (AIMM) method require the predefined sub-models and the predetermined acceleration intervals, respectively, in consideration of the properties of maneuvers in order to construct multiple models. In this paper, to solve these problems, a genetic algorithm(GA) based-IMM method using fuzzy logic is proposed. In the proposed method, the acceleration input is regarded as an additive noise and a sub-model is represented as a set of fuzzy rules to calculate the time-varying variances of the process noises of a new piecewise constant white acceleration model. The proposed method is compared with the AIMM algorithm in simulation.

• Journal of Information Processing Systems
• /
• 제9권2호
• /
• pp.333-348
• /
• 2013

Mobile authentication/identification has grown into a priority issue nowadays because of its existing outdated mechanisms, such as PINs or passwords. In this paper, we introduce gait recognition by using a mobile accelerometer as not only effective but also as an implicit identification model. Unlike previous works, the gait recognition only performs well with a particular mobile specification (e.g., a fixed sampling rate). Our work focuses on constructing a unique adaptive mechanism that could be independently deployed with the specification of mobile devices. To do this, the impact of the sampling rate on the preprocessing steps, such as noise elimination, data segmentation, and feature extraction, is examined in depth. Moreover, the degrees of agreement between the gait features that were extracted from two different mobiles, including both the Average Error Rate (AER) and Intra-class Correlation Coefficients (ICC), are assessed to evaluate the possibility of constructing a device-independent mechanism. We achieved the classification accuracy approximately $91.33{\pm}0.67%$ for both devices, which showed that it is feasible and reliable to construct adaptive cross-device gait recognition on a mobile phone.

• 대한의용생체공학회:의공학회지
• /
• 제14권1호
• /
• pp.41-50
• /
• 1993

This paper proposes an adaptive technique for the cardiac output regulation of a pendulum type electromechanical TAH. This techinque, which consists of two RLSE's and two PASTC' 5, performs Its controllability over the TAIB so that the m(RAP) and m(LAP) values re- main close to their desired values under she assumption that the variation of m(RAP) and m (LAP) are dominated by the variation of C.0. and the difference between the left and right ventricular output, respectively. To evaluate the performance of the proposed control system, a simulation is performed by using a human model which contains physiologic, drug and treatment, artificial heart and noise models. As a result, dual adaptive controller showed that abnormal m(LAP) and m(RAP) could be recovered to the normal range within 10minute and maintained desired value in steady state. The operation of this controller prored to be robust in spite of the rapid variation of human status.

• 대한전기학회논문지:전기기기및에너지변환시스템부문B
• /
• 제49권5호
• /
• pp.338-344
• /
• 2000

This paper proposes a field-oriented control strategy without speed sensor in overall speed range. At low speed region including zero speed, the electrical saliency which is due to the main flux saturation is used in order to estimate an instantaneous flux position. This electrical saliency can be obtained from the difference of high frequency impedance by the high frequency signal injection. This method enables the stable operation at zero speed or stator frequency even under heavily loaded condition. However, because of the high frequency signal injection the loss and noise in motor increase and the voltage margin is reduced as the motor speed increases. Therefore, this algorithm must be supplemented with the algorithm based on the electrical model of motor, which is conventionally used in the region except the low speed. This paper proposes the combination algorithm between the high frequency signal infection method and the adaptive observer, in which the rotor flux and motor speed can be simultaneously estimated by the adaptive control theory. This combination algorithm enables the stable operation of field-oriented speed control without speed sensor in overall speed range. This is verified by experimental results.

• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.545-557
• /
• 2018

The Global Positioning System (GPS) has become popular and widely used in many fields from military to civilian applications. However, GPS signals are suffered from interference due to its weak signal over wireless channel. There are many types of interference, such as jamming, blocking multipath, and spoofing, which can mislead the operation of GPS receiver. In this paper, vector-based tracking loop model with integrity check is proposed to detect and mitigate the harmful effect of interference on GPS receiver operation. The suggested methods are implemented in the tracking loop of GPS receiver. As a first method, integrity check with carrier-to-noise ratio (C/No) monitoring technique is applied to detect the presence of interference and prevent contaminated channels out of tracking channels to calculate position. As a second method, a vector-based tracking loop using Extended Kalman Filter with adaptive noise covariance according to C/No monitoring results. The proposed methods have been implemented on simulated dataset. The results demonstrates that the suggested methods significantly mitigate interference of Additive White Gaussian Noise (AWGN) and improve position calculation by 44%.

• 한국통신학회논문지
• /
• 제40권9호
• /
• pp.1837-1845
• /
• 2015

도심지환경에서 정확한 차량 위치를 추정하기 위해서는 종방향 속도가 필요하다. 이러한 종방향 속도는 노면경사, 즉 차량의 피치각(Pitch) 산출을 통해서 가능하다. 하지만 단일 센서와 알고리즘을 이용한 피치각 추정에는 정확한 값을 기대할 수 없다. 본 논문에서는 정확한 피치각 추정을 위해 AKF(Adaptive Kalman Filter)와 CF(Complementary Filter)로 구성된 ACF(Adaptive Complementary Filter)를 이용하여 IMU(Inertial Measurement Unit)의 프로세스 노이즈와 측정에러를 주행환경에 맞게 조절하고, 이에 GPS(Global Positioning System)와 OBD(Onboard Equipment) 데이터를 융합한다. 그리고 노면 경사 모델에 따른 필터에 시스템 모델 최적화를 위해 IMMKF(Interactive Multiple Model Kalman Filter)를 사용하여 주행환경에 적합한 최종 피치각을 추정한다.

• 한국음향학회지
• /
• 제28권3호
• /
• pp.268-272
• /
• 2009

본 논문에서는 화자확인을 위해서 가우시안혼합모델에 forgetting factor를 갖는 점진적 강인적응 방법을 제안하였다. 화자인식 시스템에서 적은 양의 데이터로 좋은 성능을 얻기 위하여 화자모델 적응방법이 사용되고 있다. 그러나, 현재 사용되고 있는 적응방법은 불규칙한 발성변화와 잡음 같은 이씨에 취약하고, 그것은 부정확한 화자모델을 만들 수 있다. 또한 시간이 지날수록 모델에 새로운 데이터가 적응되는 비율이 줄어들게 되는 문제점이 있다. 제안된 알고리즘은 가우시안혼합모델을 이용한 화자모델에서 이상치에 의한 왜곡과 새로운 데이터에 대한 적응 비율을 일정이상으로 유지할 수 있도록 하기 위하여 점진적 강인적응 방법을 제안하였다. 점진적 강인적응은 화자인식에서 적은 양의 데이터로 등록하고 테스트된 새로운 데이터로 모델을 적응시키는 방법이다. 실험결과는 7개월에 걸쳐서 수집된 데이터로부터 제안된 방법이 이상치에 강인하고 새로운 데이터의 적응 비율을 일정하게 유지시킴을 보였다.

• Structural Engineering and Mechanics
• /
• 제72권6호
• /
• pp.689-712
• /
• 2019

Time-series models like AR-ARX and ARMAX, provide a robust way to capture the dynamic properties of structures, and their residuals can be effectively used as features for damage detection. Even though several research papers discuss the implementation of AR-ARX and ARMAX models for damage diagnosis, they are basically been exploited so far for detecting the time instant of damage and also the spatial location of the damage. However, the inverse problem associated with damage quantification i.e. extent of damage using time series models is not been reported in the literature. In this paper, an approach to detect the extent of damage by combining the ARMAX model by formulating the inverse problem as a multi-constrained optimization problem and solving using a newly developed hybrid adaptive differential search with dynamic interaction is presented. The proposed variant of the differential search technique employs small multiple populations which perform the search independently and exchange the information with the dynamic neighborhood. The adaptive features and local search ability features are built into the algorithm in order to improve the convergence characteristics and also the overall performance of the technique. The multi-constrained optimization formulations of the inverse problem, associated with damage quantification using time series models, attempted here for the first time, can considerably improve the robustness of the search process. Numerical simulation studies have been carried out by considering three numerical examples to demonstrate the effectiveness of the proposed technique in robustly identifying the extent of the damage. Issues related to modeling errors and also measurement noise are also addressed in this paper.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제30권11호
• /
• pp.1072-1079
• /
• 2003

본 논문은 점층적으로 대규모 문서 분류를 할 수 있는 새로운 클러스터링 알고리즘에 대한 것으로, 고차원의 대규모 문서 집합에 대한 클러스터링을 수행하는 spherical k-means (SKM) 알고리즘과 점층적인 방식으로 클러스터링을 수행하는 퍼지(fuzzy) ART(adaptive resonance theory) 신경망의 특징을 이용하였다. 즉, SKM의 벡터 공간 모델과 개념벡터를 토대로 퍼지 ART의 경계변수의 개념을 결합한 것이다. 제시하는 알고리즘은 점층적 클러스터링의 지원과 함께 최적의 클러스터 수를 자동으로 결정할 뿐 아니라 이상치(outlier)와 노이즈(noise)에 의한 overfitting의 문제도 해결하였다. 또한 생성된 클러스터들의 질을 평가할 수 있는 응집도를 측정하는 목적 함수의 값에 있어서도 CLASSIC3 데이타 집합으로 실험한 결과 기존의 SKM에 비해 평균 8.04%의 향상된 응집도를 나타냈다.

• 한국정보처리학회논문지
• /
• 제7권1호
• /
• pp.286-295
• /
• 2000

본 논문은 MR 영상의 비지도 분할을 위하여 MDL원리를 이용한 통계적 모델기반의 적응적 방법을 제안한다. 이 방법에서 조직 영역을 MRF로 모델링함으로써 잡음에 대응하고, 창으로 정의되는 국소영역 내의 밝기값을 가우스 혼합으로 모델링함으로써 영상의 비균일성을 흡수한다. 분할 알고리즘은 ICM을 기반으로 하며 MAP를 근사적으로 추정하고, 모델 파라미터를 국소영역으로부터 구한다. 파라미터 추정과 분할을 위한 창의 크기는 MDL원리를 이용하여 영상으로부터 추정한다. 실험에서 제안한 방법이 특히 비균일성이 있는 MR영상의 분할에서 국소영역의 영상특성을 잘 반영하였으며, 기존의 방법보다 더 좋은 결과를 보여주었다.