• 전기학회논문지
• /
• 제58권12호
• /
• pp.2520-2528
• /
• 2009

In this paper, we proposed tracking detection methodology using information granulation-based fuzzy radial basis function neural networks (IG-FRBFNN). According to IEC 60112, tracking device is manufactured and utilized for experiment. We consider 12 features that can be used to decide whether tracking phenomenon happened or not. These features are considered by signal processing methods such as filtering, Fast Fourier Transform(FFT) and Wavelet. Such some effective features are used as the inputs of the IG-FRBFNN, the tracking phenomenon is confirmed by using the IG-FRBFNN. The learning of the premise and the consequent part of rules in the IG-FRBFNN is carried out by Fuzzy C-Means (FCM) clustering algorithm and weighted least squares method (WLSE), respectively. Also, Hierarchical Fair Competition-based Parallel Genetic Algorithm (HFC-PGA) is exploited to optimize the IG-FRBFNN. Effective features to be selected and the number of fuzzy rules, the order of polynomial of fuzzy rules, the fuzzification coefficient used in FCM are optimized by the HFC-PGA. Tracking inference engine is implemented by using the LabVIEW and loaded into embedded system. We show the superb performance and feasibility of the tracking detection system through some experiments.

• 한국지능시스템학회논문지
• /
• 제15권4호
• /
• pp.457-466
• /
• 2005

본 논문에서는 다중 입$\cdot$출력을 갖는 이동 로봇의 경로 추종을 위해 웨이블깃 신경 회로망에 기반한 예측 제어 방법을 제안한다. 제안된 방법에서 상태 예측기로는 학습 능력이 뛰어난 신경 회로망의 특성 및 웨이블릿 분해의 특성을 합성한 웨이블릿 신경 회로망을 사용한다. 예측기는 경사 하강법을 사용하여 웨이블릿 신경회로망의 출력에 대한 실제 이동 로봇의 상태 오차를 최소화하도록 학습된다. 또한 이동 로봇의 제어 신호인 직진 속도 및 각속도는 추종하고자 하는 기준 경로에 대한 이동 로봇의 예측 상태 오차를 이용하여 정의된 비용 함수를 최소화하도록 구해진다. 컴퓨터 모의 실험에서 변화되는 기준 경로에 대한 경로 추종 성능을 통해 제안한 예측 제어 시스템의 적용 가능성 및 효율성을 보인다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 1999년도 추계학술대회-지능형 정보기술과 미래조직 Information Technology and Future Organization
• /
• pp.365-373
• /
• 1999

Recently, numerous studies have demonstrated that artificial intelligence such as neural networks can be an alternative methodology for classification problems to which traditional statistical methods have long been applied. In building neural network model, the selection of independent and dependent variables should be approached with great care and should be treated as a model construction process. Irrespective of the efficiency of a learning procedure in terms of convergence, generalization and stability, the ultimate performance of the estimator will depend on the relevance of the selected input variables and the quality of the data used. Approaches developed in statistical methods such as correlation analysis and stepwise selection method are often very useful. These methods, however, may not be the optimal ones for the development of neural network models. In this paper, we propose a genetic algorithms approach to find an optimal or near optimal input variables for neural network modeling. The proposed approach is demonstrated by applications to bankruptcy prediction modeling. Our experimental results show that this approach increases overall classification accuracy rate significantly.

• 지구물리와물리탐사
• /
• 제23권3호
• /
• pp.117-130
• /
• 2020

지구물리탐사 자료의 잡음은 물리탐사 자료를 왜곡시켜 잘못된 결과 해석을 유도한다. 잡음을 만들어내는 원인으로는 인간의 활동으로 인하며 만들어지는 잡음과 자연 현상 및 기기 소음 등이 있으며 이러한 잡음을 제거하기 위한 다양한 연구들이 진행되고 있다. 하지만, 전통적인 잡음제거 방법들은 요소파 변환이나 필터링 과정에서 개인의 주관과 높은 계산 비용 그리고 많은 시간이 소모된다는 단점이 있으며 이런 문제를 해결하기 위해 영상 전처리 및 잡음제거를 위한 개선된 신경망을 구현하고자 하였다. 이 연구는 인공신경망, 합성곱 신경망, 오토인코더, 잔차 및 파형신경망의 다양한 유형의 신경망과 탄성파, 시간영역 전자탐사, 지표투과레이더 및 자기지전류의 잡음을 분석하고, 훈련 과정에 실제로 이용한 인공 신경망과 제시된 핵심 해결책을 분석 정리하였다. 이러한 분석을 통해 개선된 신경망이 지구물리탐사 자료의 잡음제거에 유용한 기법임을 알 수 있었다.

• 전자공학회논문지S
• /
• 제35S권2호
• /
• pp.70-78
• /
• 1998

Spike detection in long-term EEG monitoring forepilepsy by wavelet transform(WT), artificial neural network(ANN) and the expert system is presented. First, a small set of wavelet coefficients is used to represent the characteristics of a singlechannel epileptic spikes and normal activities. In this stage, two parameters are also extracted from the relation between EEG activities before the spike event and EEG activities with the spike. then, three-layer feed-forward network employing the error back propagation algorithm is trained and tested using parameters obtained from the first stage. Spikes are identified in individual EEG channels by 16 identical neural networks. Finally, 16-channel expert system based on the context information of adjacent channels is introducedto yield more reliable results and reject artifacts. In this study, epileptic spikes and normal activities are selected from 32 patient's EEG in consensus among experts. The result showed that the WT reduced data input size and the preprocessed ANN had more accuracy than that of ANN with the same input size of raw data. Ina clinical test, our expert rule system was capable of rejecting artifacts commonly found in EEG recodings.

• 전자공학회논문지CI
• /
• 제39권6호
• /
• pp.47-52
• /
• 2002

웨이블릿 함수의 경우 스케일링 함수에서 비롯되었으며, 스케일과 중심을 결정함으로써 신경회로망의 노드로 구성된다. 본 논문에서는 웨이블릿 함수를 이용하여 망을 구성하는 과정에 스케일링 함수를 은닉층의 노드로 복합 구성한 구조를 제안하고자 한다. 제안한 구조의 특징은 스케일링 함수를 이용하여 대강 근사(rough approximation)를 행한 다음, 웨이블릿 함수를 이용하여 미세 근사(fine approximation)를 행하도록 신경회로망의 은닉층을 복합 구성하는 데 있다. 또한, 복합 신경회로망을 구성하는 과정에서 미세 근사에 필요한 웨이블릿 함수의 개수를 유전 알고리즘을 이용하여 결정하는 초기 구조의 최적화를 도모하고자 한다.

• 한국수자원학회논문집
• /
• 제54권spc1호
• /
• pp.1037-1051
• /
• 2021

주요한 수질지표 중의 하나인 생물화학적 산소요구량(BOD) 농도는 호소와 하천에서 생태학적 측면에서 관측항목으로 취급하고 있다. 본 연구에서는 대한민국의 도산 및 황지지점에서 BOD 농도예측을 위하여 새로운 이단계 하이브리드 패러다임(웨이블릿 기반 게이트 순환 유닛, 웨이블릿 기반 일반화된 회귀신경망, 그리고 웨이블릿 기반 랜덤 포레스트) 을 활용하였다. 이러한 모형들은 각 대응하는 독립모형들(게이트 순환 유닛, 일반화된 회귀신경망, 그리고 랜덤 포레스트) 과 함께 평가되었다. 다양한 수질 및 수량지표들이 여러 개의 입력조합(분류1-5) 을 기본으로 하여 독립 및 이단계 하이브리드 모형을 개발하기 위하여 구현되었다. 언급한 모형들은 root mean squared error (RMSE), Nash-Sutcliffe efficiency (NSE), 그리고 correlation coefficient (CC) 를 포함한 세 개의 통계지표로서 평가되었으며, 통계결과치를 분석하면 이단계 하이브리드 모형들이 항상 대응하는 독립모형들의 예측 정도를 개선하지 않은 것으로 나타났다. 대한민국의 도산관측소에서는 DWT-RF5 (RMSE = 0.108 mg/L) 모형이 다른 최적모형과 비교하여 BOD 농도의 더 정확한 예측을 나타내었으며, 황지관측소에서는 DWT-GRNN4 (RMSE = 0.132 mg/L) 모형이 BOD 농도를 예측하는 최고의 모형이다.

• 지능정보연구
• /
• 제5권1호
• /
• pp.103-123
• /
• 1999

Input filtering as a preprocessing method is so much crucial to get good performance in time series forecasting. There are a few preprocessing methods (i.e. ARMA outputs as time domain filters, and Fourier transform or wavelet transform as time-frequency domain filters) for handling time series. Specially, the time-frequency domain filters describe the fractal structure of financial markets better than the time domain filters due to theoretically additional frequency information. Therefore, we, first of all, try to describe and analyze specially some issues on the effectiveness of different filtering methods from viewpoint of the performance of a neural network based forecasting. And then we discuss about neural network model architecture issues, for example, what type of neural network learning architecture is selected for our time series forecasting, and what input size should be applied to a model. In this study an input selection problem is limited to a size selection of the lagged input variables. To solve this problem, we simulate on analyzing and comparing a few neural networks having different model architecture and also use an embedding dimension measure as chaotic time series analysis or nonlinear dynamic analysis to reduce the dimensionality (i.e. the size of time delayed input variables) of the models. Throughout our study, experiments for integration methods of joint time-frequency analysis and neural network techniques are applied to a case study of daily Korean won / U. S dollar exchange returns and finally we suggest an integration framework for future research from our experimental results.

• Structural Engineering and Mechanics
• /
• 제64권6권
• /
• pp.803-817
• /
• 2017

Structural health monitoring has increasingly been a focus within the civil engineering research community over the last few decades. With increasing application of sensor networks in large structures and infrastructure systems, effective use and development of robust algorithms to analyze large volumes of data and to extract the desired features has become a challenging problem. In this paper, we grasp some precautions and key points of the signal processing approach, wavelet, establish a relative reliable framework, and analyze three problems that require attention when applying wavelet based damage detection approach. The cases studies how to use optimal scales for extracting mode shapes and modal curvatures in a reinforced concrete beam and how to effectively identify damages using maximum curves of wavelet coefficient differences. Moreover, how to make a recognition based on the wavelet multi-resolution analysis, wavelet packet energy, and fuzzy sets is a meaningful topic that has been addressed in this work. The relative systematic work that compasses algorithms, structures and evaluation paves a way to a framework regarding effective structural health monitoring, orientation, decision and action.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1299-1311
• /
• 2017

Sounds based machine fault diagnosis recovers all the studies that aim to detect automatically faults or damages on machines using the sounds emitted by these machines. Conventional methods that use mathematical models have been found inaccurate because of the complexity of the industry machinery systems and the obvious existence of nonlinear factors such as noises. Therefore, any fault diagnosis issue can be treated as a pattern recognition problem. We present here an automatic fault diagnosis system of hand drills using discrete wavelet transform (DWT) and pattern recognition techniques such as principal component analysis (PCA) and artificial neural networks (ANN). The diagnosis system consists of three steps. Because of the presence of many noisy patterns in our signals, we first conduct a filtering analysis based on DWT. Second, the wavelet coefficients of the filtered signals are extracted as our features for the pattern recognition part. Third, PCA is performed over the wavelet coefficients in order to reduce the dimensionality of the feature vectors. Finally, the very first principal components are used as the inputs of an ANN based classifier to detect the wear on the drills. The results show that the proposed DWT-PCA-ANN method can be used for the sounds based automated diagnosis system.