• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.428-432
• /
• 2005

영상 데이터와 같은 대용량의 데이터를 분류하고자 할 경우, 입력 데이터의 차원을 줄여서 특징 벡터를 뽑아내는 전처리 과정은 필수적이다. 이 경우 특징 벡터가 입력 데이터의 정보를 최대한 포함하도록 하는 것이 중요하다. 특징 벡터를 뽑는 대표적인 방법으로는 PCA, ICA, LDA, MLP와 같은 특징 추출(feature extraction) 방법을 들 수 있다. PCA와 LDA는 무감독 학습 방식이고, LDA, MLP는 감독 학습 방식에 해당한다. 감독학습 방식의 경우 입력 정보와 함께 클래스 정보를 사용하기 때문에 데이터를 분류하기에 더 좋은 특징들을 뽑아낼 수 있는 장점이 있다. 본 논문에서는 무감독 학습 방식인 PCA에 클래스에 대한 정보를 함께 사용하여 특징을 추출함으로써 데이터 분류에 더욱 적합한 특징들을 뽑는 방법을 제안하였다. 그리고, Yale face database를 사용하여 제안한 알고리즘의 성능을 기존의 알고리즘과 비교, 테스트하였다.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.913-915
• /
• 1995

In this paper, a transient signal classification system using logistic regression and neural networks is presented, where four neural networks such as MLP, MLP-Class, RBF and LVQ are utilized to classify given transient signals, based on the logistic regression method. Also, some test results with experimental transient signal data are provided.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.910-912
• /
• 1995

This paper proposes an effective algorithm for automatic classification of power quality disturbances(PQD), where wavelet theory is utilized for the detection of PQD, and three neural networks such as MLP, RBF, MLP-Class are combined in parallel to classify PQD. To demonstrate the performance of the proposed system, simulation results are provided.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.2E
• /
• pp.56-62
• /
• 2007

This paper presents the automatic music emotion classification on acoustic data. A three-level structure is developed. The low-level extracts the timbre and rhythm features. The middle-level estimates the indication functions that represent the emotion probability of a single analysis unit. The high-level predicts the emotion result based on the indication function values. Experiments are carried out on 695 homogeneous music pieces labeled with four emotions, including pleasant, calm, sad, and excited. Three machine learning methods, GMM, MLP, and SVM, are compared on the high-level. The best result of 90.16% is obtained by MLP method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.6
• /
• pp.594-601
• /
• 1997

A new algorithm is proposed for training the multilayer perceptrion(MLP) in pattern classification problems to accelerate the learning speed. It is shown that the sigmoid activation function of the output node can have deterimental effect on the performance of learning. To overcome this detrimental effect and to use the information fully in supervised learning, an objective function for binary modes is proposed. This objective function is composed with two new output activation functions which are selectively used depending on desired values of training patterns. The effect of the objective function is analyzed and a training algorithm is proposed based on this. Its performance is tested in several examples. Simulation results show that the performance of the proposed method is better than that of the conventional error back propagation (EBP) method.

• Journal of Environmental Science International
• /
• v.11 no.3
• /
• pp.201-207
• /
• 2002

This study was carried out to evaluate the artificial neural network algorithm for water quality forecasting in Chungju lake, north Chungcheong province. Multi-layer perceptron(MLP) was used to train artificial neural networks. MLP was composed of one input layer, two hidden layers and one output layer. Transfer functions of the hidden layer were sigmoid and linear function. The number of node in the hidden layer was decided by trial and error method. It showed that appropriate node number in the hidden layer is 10 for pH training, 15 for DO and BOD, respectively. Reliability index was used to verify for the forecasting power. Considering some outlying data, artificial neural network fitted well between actual water quality data and computed data by artificial neural networks.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2030-2032
• /
• 2001

In recent years, many attempts have been made to predict the behavior of bonds, currencies, stock, or other economic markets. Most previous experiments used multilayer perceptrons(MLP) for stock market forecasting. The Kospi 200 Index is modeled using different neural networks and fuzzy system predictions. In this paper, a multilayer perceptron architecture, a dynamic polynomial neural network(DPNN) and a fuzzy system are used to predict the Kospi 200 index. The results of prediction is compared with the root mean squared error(RMSE) and the scatter plot. Results show that both networks can be trained to predict the index. And the fuzzy system is performing slightly better than DPNN and MLP.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.9B
• /
• pp.1775-1784
• /
• 1999

This paper proposes a method of removing unnecessary hidden nodes by a new cost function that evaluates the variance and the mean of hidden node outputs during training. The proposed cost function makes necessary hidden nodes be activated and unnecessary hidden nodes be constants. We can remove the constant hidden nodes without performance degradation. Using the CEDAR handwritten digit recognition, we have shown that the proposed method can remove the number of hidden nodes up to 37.2%, with higher recognition rate and shorter learning time.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2815-2817
• /
• 1999

본 연구에서는 영상처리 기법을 이용하여 조각으로 나누어진 강판의 표면정보를 계산하여 표면정보를 검사하는 새로운 검사 기법을 제안한다. 이는 냉연 표면의 입력영상으로부터 wavelets 변환기법을 이유하여 영상을 정량화하고, 이 영상으로 co-occurrence 행렬을 이용하여 데이터들 간의 주된 특징들을 추출하여, 표면 정보를 인식 후 흠을 분류하기 위한 분류기로서 신경망을 이용하여분류하는 과정을 거치게 된다. 제시하는 알고리즘은 기존의 벡터양자화 기법과 비교하여 우수한 성능을 보임을 실험을 통해 입증하였으며, 실시간 구현에 효과적으로 적용될 수 있음을 보였다.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2091-2093
• /
• 2003

Generally, the correlation between the responses of various sensors can be exploited to detect a possible malfunctioning sensor during operation. The sensor fault detection is implemented by using the regression ability of artificial neural networks(ANN). In this work, sensor fault detection scheme based on ANN is proposed. To verify its applicability, simulation study on the water data gathered from Saemangeum measurement stations is executed.