• 대한전자공학회논문지SP
• /
• 제38권5호
• /
• pp.583-597
• /
• 2001

Tracking the targets of interest has been one of the major research areas in radar surveillance system. We formulate the tracking problem as an incomplete data problem and apply the EM algorithm to obtain the MAP estimate. The resulting filter has a recursive structure analogous to the Kalman filter. The difference is that the measurement-update deals with multiple measurements and the parameter-update can estimate the system parameters. Through extensive experiments, it turns out that the proposed system is better than PDAF and NNF in tracking the targets. Also, the performance degrades gracefully as the disturbances become stronger.

• 한국음향학회지
• /
• 제7권4호
• /
• pp.98-109
• /
• 1988

본 연구는 이차 볼테라 필터 계수를 연속적으로 변화시키기 위하여 sequential regression (SER) 방법을 이용한 적응 비선형 디지탈 필터링 알고리즘에 대하여 서술하였다. 일반적으로 SER 방법은 Wiener 필터 이론을 볼테라필터에 직접 적용시킬때 생기는 큰 행렬을 역변환시키기 위하여 사용되었다. 그러나, 본 연구에서는 입력신호가 가우시안일 경우, 최소 자승해를 구하기 위하여 SER 방법을 이용하였다. 이 알고리즘에서, 역변환시킬 행렬의 크기는 일반적 접근 방법보다 작게 되기때문에, 일반적 비선형 시스템 인식 기술보다 본 연구에서 제시한 방법의 계산량이 적다. 본 연구에서 제안한 알고리즘의 성능을 검토하기 위하여 시뮬레이션 결과를 구했다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 추계종합학술대회
• /
• pp.320-322
• /
• 2002

A new simple spatial scheme for base station with adaptive antenna in Code Division Multiplexing Access (CDMA) systems is presented. In the proposed scheme, by applying the new spatial structure lot the receiver, the system can debate the problem of which the number of users exceeds the number of adaptive antenna elements existing in the conventional spatial scheme. An adaptive algorithm based on the Mean Square Error (MSE) criterion is also derived to update the weight matrix of the proposed scheme. The results of the system capacity enhancement can be achieved by using the proposed approach. Numerical simulations are included fer illustration and verification.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1289-1291
• /
• 1996

In this paper, we propose a new adaptive pre-processing technique for the linearization of a weakly nonlinear system which can be modeled by a Volterra series up to third order. To compensate the nonlinear effects of a given system, an update algorithm for the linear filter coefficients of the proposed adaptive pre-processor is introduced, and to compensate the linear distortion of the given system, the linear inverse filter is also utilized. For the performance test of the proposed adaptive pre-processor, computer simulation results obtained by analyzing an ANRSS loudspeaker model are provided.

• 한국통신학회논문지
• /
• 제18권11호
• /
• pp.1714-1725
• /
• 1993

본 논문에서는 스칼라 인수 a1, a2, a3를 매개변수화하여 갱신항을 첨가한 비선형 적응 알고리즘의 특성을 해석하고 그 구조를 나타낸다. 수렴 특성의 해석에서 평균 필터계수 벡터에 대하여 전이행열의 값이 기술된다. 그 알고리즘이 안정하기 위한 범위도 증명된다. 또한 본 알고리즘의 시정수도 유도되고, Sign 알고리즘, 기존의 LMS 알고리즘, LFG 알고리즘, QFG 알고리즘의 계산량도 비교해 본다. 평균자승의 수렴특성을 해석하고 평균자승 순환식과 초과 평균자승 오차(excess mean square error) 표현식을 유도하고 본 알고리즘이 안정하기 위한 조선도 정한다. 컴퓨터 모의실험(simulation)에서 CFG 알고리즘이 LMS, LFG 및 QFG 알고리즘보다 계산량이 증가하는 반면 수렴속도에서 현저한 향상을 보여준다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1991년도 하계학술대회 논문집
• /
• pp.666-669
• /
• 1991

This paper deals with the robustness of a direct adaptive pole-placement control algorithm for continuous time plants with unmodeled dynamics. In this paper, least squares method is used for controller parameter adaptation and covariance matrix update equation is modified by normalizing signal to guarantee the boundedness of all signals in the closed loop system. In the proposed algorithm, no a priori knowledge is required and it is shown that persistence of excitation condition is required to ensure the stability of the closed loop system.

• Journal of Power Electronics
• /
• 제14권6호
• /
• pp.1254-1262
• /
• 2014

Magneto-electric encoders have been widely used in industry and military applications because of their good shock resistance, small volume, and convenient data processing. However, the characteristics of a magneto-electric encoder's signal generator and hall sensor changes minimally with temperature variation. These changes cause an angle drift. The main purpose of this study is to construct the compensation system of a neural network and constantly update weight coefficients of temperature correction by finite iteration calculation so that the angle value modified can approach the angle value at the target temperature. This approach is used in adaptive correction of the angle value.

• Journal of Communications and Networks
• /
• 제9권4호
• /
• pp.408-418
• /
• 2007

In this paper, we address the question of dynamic network provisioning for time-varying traffic rates, with the objective of maximizing the system throughput. We assume that the network is capable of providing bandwidth guaranteed traffic tunnels for an ingress-egress pair and present an approach that (1) updates the tunnel routes and (2) adjusts the tunnel bandwidths, in an incremental, adaptive manner, based on the variations in the incoming traffic. First, we consider a simpler scenario where tunnel routes are fixed, and present an approach for adjusting the tunnel bandwidths dynamically. We show, through simulations, that our dynamic bandwidth assignment algorithm significantly outperforms the optimal static bandwidth provisioning policy, and yields a performance close to that of the optimal dynamic bandwidth provisioning policy. We also propose an adaptive route update algorithm, which can be used in conjunction with our dynamic bandwidth assignment policy, and leads to further improvement in the overall system performance.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.20-27
• /
• 2020

Sound event detection in real-world environments suffers from the interference of non-stationary and time-varying noise. This paper presents an adaptive noise reduction method for sound event detection based on non-negative matrix factorization (NMF). In this paper, we proposed a deep learning model that integrates Convolution Neural Network (CNN) with Non-Negative Matrix Factorization (NMF). To improve the separation quality of the NMF, it includes noise update technique that learns and adapts the characteristics of the current noise in real time. The noise update technique analyzes the sparsity and activity of the noise bias at the present time and decides the update training based on the noise candidate group obtained every frame in the previous noise reduction stage. Noise bias ranks selected as candidates for update training are updated in real time with discrimination NMF training. This NMF was applied to CNN and Hidden Markov Model(HMM) to achieve improvement for performance of sound event detection. Since CNN has a more obvious performance improvement effect, it can be widely used in sound source based CNN algorithm.

• 한국통신학회논문지
• /
• 제39A권5호
• /
• pp.237-243
• /
• 2014

이 논문에서는, 영확률을 최대화 (maximum zero-error probability, MZEP) 하도록 설계된 알고리듬에서 가중치 갱신에 쓰이는 기존의 블록 처리 방식의 합산 연산을 대신하여, 다음 기울기 계산에 현재 계산된 기울기를 활용할 수 있는 효율적인 가중치 갱신 계산 방식을 제안하였다. 실험 결과로부터, 제안한 방식은 원래의 MZEP 와 동일한 성능을 나타내면서도 오차 버퍼가 불필요하여 시스템의 복잡도를 감소시키며 연산 시간을 현저히 줄일 수 있다. 또한 제안한 알고리듬은 오차 엔트로피 (error-entropy)를 최소화하도록 설계된 알고리듬보다 우수한 수렴 속도를 지닌다.