• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2000년도 하계학술발표대회 논문집 제19권 1호
• /
• pp.337-338
• /
• 2000

The perceptual filter for speech enhancement was analytically derived where the frequency content of the input noisy signal was made the same as that of the estimated clean signal in auditory domain. However, the analytical derivation should rely on the deconvolution associated with the spreading function in the psychoacoustic model, which results in an ill-conditioned problem. In order to cope with the problem associated with the deconvolution, we propose a novel psychoacoustic model based speech enhancement filter whose principle is the same as the perceptual filter, however the filter is derived by a constrained optimization which provides solutions to the ill-conditioned problem.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
• /
• pp.621-628
• /
• 2005

Scalability of clustering algorithms is critical issues facing the data mining community. This is particularly true for computationally intense tasks such as data clustering. Random sampling of instances is one possible means of achieving scalability but a pervasive problem with this approach is how to deal with the noise that this introduces in the evaluation of the learning algorithm. This paper develops a new optimization based clustering approach using an algorithms specifically designed for noisy performance. Numerical results illustrate that with this algorithm substantial benefits can be achieved in terms of computational time without sacrificing solution quality.

• Smart Structures and Systems
• /
• 제15권5호
• /
• pp.1253-1270
• /
• 2015

In this paper Magnetic Charged System Search (MCSS) and Particle Swarm Optimization (PSO) are applied to the problem of damage detection using frequencies and mode shapes of the structures. The objective is to identify the location and extent of multi-damage in structures. Both natural frequencies and mode shapes are used to form the required objective function. To moderate the effect of noise on measured data, a penalty approach is applied. A variety of numerical examples including two beams and two trusses are considered. A comparison between the PSO and MCSS is conducted to show the efficiency of the MCSS in finding the global optimum. The results show that the present methodology can reliably identify damage scenarios using noisy measurements and incomplete data.

• Journal of Electrical Engineering and Technology
• /
• 제13권3호
• /
• pp.1371-1376
• /
• 2018

Photoplethysmography (PPG) is a convenient method for monitoring a heart rhythm. In addition to specialized devices, smartphones can be used to obtain PPG signals. However, as smartphones are not intended for this purpose, optimization is required to efficiently obtain PPG signals. Determining the optimal region of interest (ROI) is one such optimization method. There are two significant advantages in employing an optimized ROI. One is that the computing load is decreased by reducing the image size used to extract the PPG signal. The other is that stronger and more reliable PPG signals are obtained by removing noisy regions. In this paper, we propose an optimal ROI determination method by recursively splitting regions to locate the region that produces the strongest PPG signal.

• 제어로봇시스템학회논문지
• /
• 제22권3호
• /
• pp.199-203
• /
• 2016

A brain-computer interface or BCI provides an alternative method for acting on the world. Brain signals can be recorded from the electrical activity along the scalp using an electrode cap. By analyzing the EEG, it is possible to determine whether a person is thinking about his/her hand or foot movement and this information can be transferred to a machine and then translated into commands. However, we do not know which information relates to motor imagery and which channel is good for extracting features. A general approach is to use all electronic channels to analyze the EEG signals, but this causes many problems, such as overfitting and problems removing noisy and artificial signals. To overcome these problems, in this paper we used a new optimization method called the Fruit Fly optimization algorithm (FOA) to select the best channels and then combine them with CSP method to extract features to improve the classification accuracy by linear discriminant analysis. We also used particle swarm optimization (PSO) and a genetic algorithm (GA) to select the optimal EEG channel and compared the performance with that of the FOA algorithm. The results show that for some subjects, the FOA algorithm is a better method for selecting the optimal EEG channel in a short time.

• 한국통신학회논문지
• /
• 제28권3C호
• /
• pp.315-326
• /
• 2003

본 논문은 분류 벡터 양자화(CVQ)기법을 이용한 통신 시스템에서 채널 오류를 감소시키기 위한 인덱스벡터할당 방식을 다루고 있다. 제안된 시스템은 크게 내부 인덱스 할당방식(IIA inner index assignment)과 교차인덱스 할당방식(CIA : cross index assignment)으로 구성된다. IIA는 부(Sub)코드북 내에서 유사한 코드벡터들에 Hamming거리가 가까운 인덱스들을 할당함으로써 채널에러에 의해 발생된 화질저하를 감소시킨다. CIA는 인덱스 벡터의 클래스 정보를 나타내는 클래스 비트에 발생하는 채널 오류의 영향을 최소화할 수 있는 방법으로서 IIA에 의해 할당된 인덱스 벡터들을 수정한다. 본 논문에서 실시된 컴퓨터 모의실험은 제안된 시스템이 채널 부호화기법을 사용하지 않고도 채널 잡음을 극복할 수 있음을 보여준다.

• 지능정보연구
• /
• 제13권3호
• /
• pp.31-45
• /
• 2007

대용량의 데이터 처리에 관한 문제는 데이터 마이닝 내 중요한 이슈 중의 하나이다. 특히 데이터 클러스터링과 같이 컴퓨터 시뮬레이션으로 인한 부하가 큰 경우 더더욱 그러하다. 그러나 대개 이러한 문제는 Random sampling 으로 어느 정도 해결이 가능하다. 문제는 이런 샘플링을 통해서 발생하는 noise의 해결이다. 본 논문에서는 그러한 noise문제를 극복할 수 있도록 설계된 새로운 데이터클러스터링 알고리즘을 소개한다. 기존의 데이터 클러스팅 알고리즘과의 컴퓨터 비교 실험을 통해 본 알고리즘의 우수성을 밝혔으며 아울러 더 나아가 데이터 set의 일부만을 사용한 시뮬레이션 결과를 통해, 해의 정확도와 상관없이 실험 시간 또한 단축되었음을 보여주고 있다.

• ETRI Journal
• /
• 제39권2호
• /
• pp.151-162
• /
• 2017

With the remarkable growth in rich media in recent years, people are increasingly exposed to visual information from the environment. Visual information continues to play a vital role in rich media because people's real interests lie in dynamic information. This paper proposes a novel discrete dynamic swarm optimization (DDSO) algorithm for video object tracking using invariant features. The proposed approach is designed to track objects more robustly than other traditional algorithms in terms of illumination changes, background noise, and occlusions. DDSO is integrated with a matching procedure to eliminate inappropriate feature points geographically. The proposed novel fitness function can aid in excluding the influence of some noisy mismatched feature points. The test results showed that our approach can overcome changes in illumination, background noise, and occlusions more effectively than other traditional methods, including color-tracking and invariant feature-tracking methods.

• 정보과학회 논문지
• /
• 제44권7호
• /
• pp.726-732
• /
• 2017

무선 센서 네트워크의 분산 센싱 및 예측에 대한 실제 Application에서 네트워크 환경 센싱 기능은 움직이는 소스 신호의 잡음 및 많은 센싱 정보들 때문에 매우 동적인 기능을 요구한다. 최근의 Distributed Online Convex Optimization 프레임워크는 분산된 방식으로 센서 네트워크를 통해 확률적인 학습 문제를 해결하기 위한 유망한 접근법으로 개발되었다. 기존의 Distributed Saddle Point Algorithm (DSPA)의 학습 결과에서 수렴 속도와 안정성은 이동성의 영향을 받을 수 있다. 이에 본 논문에서는 움직이는 소스 신호 시나리오의 동시 검출에서 예측을 안정화하고 보다 나은 수렵 속도를 달성하기 위해 통합 Sliding Windows 메커니즘을 제안한다.

• Structural Engineering and Mechanics
• /
• 제83권5호
• /
• pp.593-607
• /
• 2022

To solve the problem of detecting structural damage, a two-stage method using the Kalman filter and Particle Swarm Optimization (PSO) is proposed. In this method, the first PSO population is enhanced using the Kalman filter method based on dynamic responses. Due to noise in the sensor responses and errors in the damage detection process, the accuracy of the damage detection process is reduced. This method proposes a novel approach for solve this problem by integrating the Kalman filter and sensitivity analysis. In the Kalman filter, an approximate damage equation is considered as the equation of state and the damage detection equation based on sensitivity analysis is considered as the observation equation. The first population of PSO are the random damage scenarios. These damage scenarios are estimated using a step of the Kalman filter. The results of this stage are then used to detect the exact location of the damage and its severity with the PSO algorithm. The efficiency of the proposed method is investigated using three numerical examples: a 31-element planer truss, a 52-element space dome, and a 56-element space truss. In these examples, damage is detected for several scenarios in two states: using the no noise responses and using the noisy responses. The results show that the precision and efficiency of the proposed method are appropriate in structural damage detection.