Papers by Author: Hai Yan Liu

Abstract: This paper presents an optimizing method of competitive neural network(CNN):During clustering analysis fixed on the optimum number of output neurons according to the change of DB value，and then adjusted connected weight including increasing ,dividing , delete. Each neuron had the different variety trend of learning rate according with the change of the probability of neurons. The optimizing method made classification more accurate. Simulation results showed that optimized network structure had a strong ability to adjust the number of clusters dynamically and good results of classification.

Abstract: Five kinds of vinegars were measured by a gas sensor array composed of six TGS gas sensors. The sensor array should be optimized by the minimal Wilks statistic value, then, the four best sensor array used to detect the type of vinegars were formed, Principal Component Analysis (PCA) and Linear discriminant analysis (LDA) were applied to analyze the data of primary and optimized sensor array. The results indicated that optimization sensor array could be more adaptable to recognize the five kinds of vinegars. Thereby the given optimization method is effective.

Abstract: An electronic tongue which composed of selective electrodes is applied to mineral water recognition (optimization of sensor array). The task of the system is to distinguish among five brands of mineral water. For this purpose, various pattern recognition (PARC) procedures are employed: principle components analysis (PCA), independent component analysis, linked-like adaptive genetic algorithm (LAGA), et al. LAGA networks are proved to exhibit the best performance both in array optimization and mineral water recognition. Their further advantages, such as fast training and robustness, make them the suggested pattern classifiers for sensor array data.