Jeong-Woong Ryu

Application of ANFIS for coagulant dosing process in a water purification plant

It is very important to optimize the turbidity of the treated water by dosing coagulant in water purification plant. The coagulant reaction to the turbidity is, however, not yet to be clarified and the amount of coagulant can not be easily calculated. In this work an adaptive network-based fuzzy inference system (ANFIS) based on conditional fuzzy c-means is employed to model the coagulant reaction to the turbidity of the treated water and the historical jar-test data are used to train the ANFIS. From this, we obtained a better performance than previous works using neural network and finally validated its efficiency by a set of real field data.

Speech recognition using integra-normalizer and neuro-fuzzy method

This paper represents a new method of recognizing speech using the metric defined by the integra-normalizer (IN) and the neuro-fuzzy method. A codebook contains a set of feature vectors that is extracted from raw speech data. The degree of similarity between speech is measured as the distance between the speech feature vectors. The method of measuring distance between feature vectors is obtained by using the new metric presented in this paper using the IN that possesses some advantage to conventional metrics such as the metric defined to measure the least square error. With the approach used in this paper, information on the shape of the speech patterns is mapped to the feature vectors and the metric measures the difference between speech patterns considering the shape of the patterns also. The results of the computer simulation are shown for the validity of this proposed method.

The Performance Improvement of Speech Recognition System based on Stochastic Distance Measure

In this paper, we propose a robust speech recognition system under noisy environments. Since the presence of noise severely degrades the performance of speech recognition system, it is important to design the robust speech recognition method against noise. The proposed method adopts a new distance measure technique based on stochastic probability instead of conventional method using minimum error. For evaluating the performance of the proposed method, we compared it with conventional distance measure for the 10-isolated Korean digits with car noise. Here, the proposed method showed better recognition rate than conventional distance measure for the various car noisy environments.

Detection and Diagnosis of Induction Motor Using Conditional FCM and Radial Basis Function Network

In this paper, we propose a hierarchical hybrid neural network for detecting faults of induction motor. Implementing the classifier based on the input and output data, we apply appropriate transform and classification method at each step. In the proposed method, after obtaining the current of state of motor for each period, we transform it by Principle Component Analysis(PCA) to reduce its dimension. Before the training process, we use the conditional Fuzzy C-means(FCM) for obtaining the initial parameters of neural network for more effective learning procedure. From the various simulations, we find that the proposed method shows better performance to detect and diagnosis of induction motor and compare than other methods.

A Neuro-Fuzzy Modeling using the Hierarchical Clustering and Gaussian Mixture Model

In this paper, we propose a neuro-fuzzy modeling to improve the performance using the hierarchical clustering and Gaussian Mixture Model(GMM). The hierarchical clustering algorithm has a property of producing unique parameters for the given data because it does not use the object function to perform the clustering. After optimizing the obtained parameters using the GMM, we apply them as initial parameters for Adaptive Network-based Fuzzy Inference System. Here, the number of fuzzy rules becomes to the cluster numbers. From this, we can improve the performance index and reduce the number of rules simultaneously. The proposed method is verified by applying to a neuro-fuzzy modeling for Box-Jenkins s gas furnace data and Sugeno`s nonlinear system, which yields better results than previous oiles.

Robust Speech Recognition with Car Noise based on the Wavelet Filter Banks

This paper proposes a robust speech recognition algorithm based on the wavelet filter banks. Since the proposed algorithm adopts a multiple band decision-making scheme, it performs robustness for noise as the presence of noisy severely degrades the performance of speech recognition system. For evaluating the performance of the proposed scheme, we compared it with the conventional speech recognizer based on the VQ for the 10-isolated korean digits with car noise. Here, the proposed method showed more 9~27% improvement of the recognition rate than the conventional VQ algorithm for the various car noisy environments.

A frequency domain identification method using total least squares

This paper presents a frequency domain identification method for the rational transfer function using TLS (total least squares) approach. The proposed method identifies the coefficients of rational polynomial transfer function for continuous time system, after rearranging the two-dimensional input matrices and output vectors obtained from the observed frequency responses.

A method of designing nonlinear channel equalizer using conditional fuzzy c-means clustering

We propose a new method of designing a nonlinear channel equalizer using an adaptive neuro-fuzzy clustering method called a conditional fuzzy c-means. The structure identification of an adaptive neuro-fuzzy system is performed by the conditional fuzzy c-means clustering method with the homogeneous properties of the given input and output data. The parameter identification is established by hybrid learning using the back-propagation algorithm and recursive least squares estimation. Experimental results demonstrate that the proposed method improves the performance of the neuro-fuzzy system. Finally. we apply the proposed method to designing a nonlinear channel equalizer and obtain better results than previous methods.

A Neuro-Fuzzy System Modeling using Gaussian Mixture Model and Clustering Method

There have been a lot of considerations dealing with improving the performance of neuro-fuzzy system. The studies on the neuro-fuzzy modeling have largely been devoted to two approaches. First is to improve performance index of system. The other is to reduce the structure size. In spite of its satisfactory result, it should be noted that these are difficult to extend to high dimensional input or to increase the membership functions. We propose a novel neuro-fuzzy system based on the efficient clustering method for initializing the parameters of the premise part. It is a very useful method that maintains a few number of rules and improves the performance. It combine the various algorithms to improve the performance. The Expectation-Maximization algorithm of Gaussian mixture model is an efficient estimation method for unknown parameter estimation of mirture model. The obtained parameters are used for fuzzy clustering method. The proposed method satisfies these two requirements using the Gaussian mixture model and neuro-fuzzy modeling. Experimental results indicate that the proposed method is capable of giving reliable performance.

A New Learning Algorithm of Neuro-Fuzzy Modeling Using Self-Constructed Clustering

In this paper, we proposed a learning algorithm for the neuro-fuzzy modeling using a learning rule to adapt clustering. The proposed algorithm includes the data partition, assigning the rule into the process of partition, and optimizing the parameters using predetermined threshold value in self-constructing algorithm. In order to improve the clustering, the learning method of neuro-fuzzy model is extended and the learning scheme has been modified such that the learning of overall model is extended based on the error-derivative learning. The effect of the proposed method is presented using simulation compare with previous ones.