• 한국산학기술학회논문지
• /
• 제22권2호
• /
• pp.714-720
• /
• 2021

머신 러닝 및 신호처리에 활용되고 있는 정보이론적 학습법(ITL, information theoretic learning)은 커널 사이즈(σ) 설정이 매우 민감한 어려움을 지닌다. ITL의 성능지표중 하나인 코렌트로피 함수를 최대화하는 성능지표에 대해, 기울기에 존재하는 1/σ2를 제거한 뒤 남은 커널 사이즈에 대해 적응적으로 조절하는 방법들이 연구되었다. 이 논문에서는, 1/σ2의 커널 사이즈가 실제 시스템의 민감성이나 불안정에 큰 역할을 하고 있으며 남은 부분에 존재하는 커널 사이즈에 대한 최적해는 오차의 절대값 근방에 수렴함에 따라 오히려 수렴 후 가중치 갱신을 멈추게 하는 부작용이 나타남을 밝혔다. 이에 적응적 커널 사이즈 조절 대신 적절한 상수를 선택하는 것이 보다 효과적이라는 것을 제안하였고, 실험결과에서 동일한 수렴 속도에 약 2dB 향상된 정상상태 MSE를 보였다. 제안한 방식을 더욱 열악한 다경로 채널환경에 적용하여 실험한 결과 4dB 이상의 성능향상을 보여 제안한 방식은 열악한 상황일수록 더욱 향상된 성능을 보임을 알 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권9호
• /
• pp.3120-3137
• /
• 2021

Small-sized IoT wireless sensing devices can be deployed with small aircraft such as drones, and the deployment of mobile IoT devices can be relocated to suit data collection with efficient relocation algorithms. However, the terrain may not be able to predict its shape. Mobile IoT devices suitable for these terrains are hopping devices that can move with jumps. So far, most hopping sensor relocation studies have made the unrealistic assumption that all hopping devices know the overall state of the entire network and each device's current state. Recent work has proposed the most realistic distributed network environment-based relocation algorithms that do not require sharing all information simultaneously. However, since the shortest path-based algorithm performs communication and movement requests with terminals, it is not suitable for an area where the distribution of obstacles is uneven. The proposed scheme applies a simple Monte Carlo method based on relay nodes selection random variables that reflect the obstacle distribution's characteristics to choose the best relay node as reinforcement learning, not specific relay nodes. Using the relay node selection random variable could significantly reduce the generation of additional messages that occur to select the shortest path. This paper's additional contribution is that the world's first distributed environment-based relocation protocol is proposed reflecting real-world physical devices' characteristics through the OMNeT++ simulator. We also reconstruct the three days-long disaster environment, and performance evaluation has been performed by applying the proposed protocol to the simulated real-world environment.

• 정보보호학회논문지
• /
• 제9권4호
• /
• pp.11-22
• /
• 1999

LMS 적응필터는 많은 신호처리 응용분야에서 광범위하게 사용되고 있으나 반복 적 최소 자승 (RLS) 적응 필터와 비교해서 주어진 안정상태 평균 자승 에러에 대한 수렴특성이 떨어진 다. 본 논문은 LMS 알고리즘의 수렴속도를 향상시키기 위해 폐기된 탭 입력 데이터를 몇 개의 한정된 버퍼를 이용 탭 가중치를 적응적으로 조절하여 수렴특성을 개선한다. 컴퓨터 시뮬레이션 결과를 통해 스텝 크기 매 개변수 $\mu$값의 증가는 보다 빠른 수렴속도와 평균 자승에러를 감소시키는 효과를 가지므로 데이터 재순 환 버퍼 구조에서 탭 가중치의 갱신에 비례하여 평균 자승 에러의 수렴속도가 재순환 버퍼 B를 증가시 켜 수렴속도가 (B+1)배 만큼 증가한다. 데이터 버퍼 알고리즘을 이용한 제안된 TDL 필터가 LMS 알고 리즘과 동일한 수렴조건을 가지고 실행될 때 연산복잡성의 실질적 부담감을 배제하고 채널 간의 상호심 볼간섭을 보다 효율적으로 제어하면서 적응 횡단선 필터의 수렴속도를 증기시켜 개선한다.

• 전기학회논문지P
• /
• 제53권4호
• /
• pp.195-200
• /
• 2004

Many kinds of speed sensorless control system of induction motor had been developed. But it is difficult to implement at the real system because of complex algorithm and equations. This paper investigates a novel speed sensorless control of induction motor using neural networks. The proposed control strategy is based on neural networks using stator current and output of neural model based on state observer. The errors between the stator current and the output of neural model are back-propagated to adjust the rotor speed, so that adaptive state variable will coincide with the desired state variable. This algorithm may overcome several shortages of conventional model, such as integrator problems, small EMF at low speed and relatively large sensitivity of stator resistance variation. Also, this paper presents a newly developed optimal equation about the momentum constant and the learning rate. The proposed algorithms are verified through simulation.

• 한국산학기술학회논문지
• /
• 제7권3호
• /
• pp.379-384
• /
• 2006

본 논문은 컴포넌트 검색 성능을 향상시키기 위해 사용자 피드백을 효율적으로 수행하는 방법을 제안하고자 한다. 기존의 퍼지 기법이 적용된 피드백의 단점을 극복하기 위하여 검색된 컴포넌트의 선택여부에 따라 동일한 함수이지만 학습률을 달리할 수 있는 가우시안 함수를 이용한 상호작용 함수를 제안한다. 또한 피드백 함수에 사용자 프로필을 적용하여 사용자 등급에 따라 사용자 의견이 시스템에 반영되는 정도를 다르게 해주었다. 본 연구의 사용자 검색 피드백은 가우시안 함수를 적용한 피드백 함수와 사용자 프로필을 이용하여 시스템을 장기간에 걸쳐 서서히 변화시킬 수 있는 적응형 검색 방법이다.

• 대한음성학회지:말소리
• /
• 제66호
• /
• pp.73-86
• /
• 2008

Beamforming is one of the spatial filtering techniques which extract only desired signals from noisy environments using microphone arrays. Fixed beamforming is a simple concept and easy to implement. However, it does not show good performance in real noisy conditions. As an adaptive beamforming, Frost algorithm can be a good candidate. It uses the concept of the linearly constrained minimum variance (LCMV) algorithm. The difference between the Frost and the LCMV algorithm is the error correction scheme which is very effective feature in the aspect of performance. In this paper, as quadrature mirror filtering (QMF)-based filterbank is utilized as the pre-processing of the Frost beamformning, the filter length and the learning rate of each band is optimized to improve the performance. The performance is measured by the signal-to-noise ratio (SNR) and the Bark's scale spectral distortion (BSD).

• 한국농공학회지
• /
• 제43권2호
• /
• pp.69-77
• /
• 2001

An artificial neural network model was developed to analyze and forecast daily steamflow flow a small watershed. Error Back propagation neural networks (EBPN) of daily rainfall and runoff data were found to have a high performance in simulating stremflow. The model adopts a gradient descent method where the momentum and adaptive learning rate concepts were employed to minimize local minima value problems and speed up the convergence of EBP method. The number of hidden nodes was optimized using Bayesian information criterion. The resulting optimal EBPN model for forecasting daily streamflow consists of three rainfall and four runoff data (Model34), and the best number of the hidden nodes were found to be 13. The proposed model simulates the daily streamflow satisfactorily by comparison compared to the observed data at the HS#3 watershed of the Baran watershed project, which is 391.8 ha and has relatively steep topography and complex land use.

• 한국정밀공학회지
• /
• 제5권4호
• /
• pp.32-38
• /
• 1988

Apaptive cintrol of machine tool is aimed to change cutting state satis- factorily without aid of a machine operator, if the cuting state is abnomal such as formation of tangled ribbon type chip, built-up edge and generation of chattering and so on. Among these the recognition of chip type is one of the most important since it has imlications relate to : 1. Safety of operator 2. Stoppage of work due to entanglment in tool and workpiece of chip 3. Problem of producted chip control In this paper the chip type is discriminatied by the pattern recognition technique. It is found that the power spectrum of cutting force for each chip type has it's own special pattern. Linear discriminant function for the recognition of the chip type is obtained by learning process. The discriminant function can be the basis of adaptive control for the rate of success of recognition by pattern recognition technique is at leasthigher than 83%.

• 전자공학회논문지S
• /
• 제34S권9호
• /
• pp.23-30
• /
• 1997

In this paper, a decision feedback recurrent neural equalization (DFRNE) scheme is proposed for adaptive equalization problems. The proposed equalizer models a nonlinear infinite impulse response (IIR) filter. The modified Real-Time recurrent Learning Algorithm (RTRL) is used to train the DFRNE. The DFRNE is applied to both linear channels with only intersymbol interference and nonlinear channels for digital video cassette recording (DVCR) system. And the performance of the DFRNE is compared to those of the conventional equalizaion schemes, such as a linear equalizer, a decision feedback equalizer, and neural equalizers based on multi-layer perceptron (MLP), in view of both bit error rate performance and mean squared error (MSE) convergence. It is shown that the DFRNE with a reasonable size not only gives improvement of compensating for the channel introduced distortions, but also makes the MSE converge fast and stable.

• 디지털융복합연구
• /
• 제10권11호
• /
• pp.377-382
• /
• 2012

본 논문은 반향 제거 평균 예측 LMS 알고리즘을 이용하여 반향 잡음에 강인한 연속 음성 인식 모델인 CHMM 모델을 구성하는 방법을 제안하였다. 변화하는 반향 잡음에 적응하고 연속 음성 인식 성능 향상을 위한 반향 잡음 제거 평균 예측 LMS 알고리즘을 이용하여 CHMM 모델을 구성하였다. 제안한 알고리즘에 의해 구성된 CHMM 모델에 대하여 연속 인식 성능을 평가하였다. 실험 결과 변화하는 환경 잡음을 제거하여 얻은 음성의 SNR은 평균 1.93dB이 향상되었고 연속 음성의 인식률은 2.1% 향상되었다.