Learn More
Analysis of the voice pronunciation mechanism and performance differences of normal voice in the frequency domain, wavelet transform is used to do signal decomposition, and emphasizing characteristics of voice, with these two characteristic parameters we recognize 242 normal voice using gaussian mixture model (GMM) respectively. Put forward wavelet(More)
Double tree after wavelet transform has good direction selectivity and invariant parallel movement. Based on analysing histogram of modulus sub-band corresponding to six high frequency sub-band after double tree wavelet decomposition, we put forwaord a new kind of subtle character, namely combination character of Lognormal distribution parameters and Gamma(More)
Put forward the method of Instantaneous feature extraction of non-stationary signal based on complex wavelet Morlet. Aiming at the characteristics of non-stationary signal signal, we construct two groups of combination information suitable for feature extraction combining amplitude and phase information which complex wavelet transform provide. The example(More)
It used to be difficult to precisely understand the situation of miners underground according to the existed miner safety management system. To solve this problem, we propose an improved safety management system based on iris identification and RFID (Radio Frequency Identification) technique. It combines several modern identification and communication(More)
The study reported here examined, as the research subject, surface soils in the Liuxin mining area of Xuzhou, and explored the heavy metal content and spectral data by establishing quantitative models with Multivariable Linear Regression (MLR), Generalized Regression Neural Network (GRNN) and Sequential Minimal Optimization for Support Vector Machine(More)
This paper discuss model and algorithm of confirming standard value of communication equipment indected, including confirming methods of two or more detection data, at last we attempt to use least squares algorithm and recursive least squares algorithm to confirm detection standard value, this have definite action for advancing computation precision and(More)
This paper uses generalized congruence function instead of transfer function of classical BP neural network, and improve convergence rate of neural network. We introduce the subsection generalized derivation, error back propagation derivation mechanism of classical BP algorithm to adjust weight vector in generalized congruence neural network, and modify(More)
The distance of microphones in sound intensity probe have great relations with effective sound frequency band measured during measuring sound intensity,. To adapt different measured frequencies, the position of every microphone in sound intensity probe should be adjusted. On the basis of discussing the theory of measuring sound intensity with four(More)
General neural networks always converge to local optimal position when solving global optimal problem but dual symmetrical neural networks can overcome this shortcoming . The model and algorithms that dual symmetrical neural networks is used to solve direction finding(DF) and frequency measurement are presented in this paper, dual symmetrical neural(More)