Parameter estimation of network signal normal distribution applied to carbonization depth in wireless networks

Abstract

AbstractFor the average state of the normal distribution parameter estimation, regular normal distribution parameter gives an estimation, but the carbonation depth of influence factors is more of a parameter estimation, shooting low deficiencies; therefore, putting forward application in the carbonation depth of the normal distribution parameter is estimated. A normal distribution parameter estimation model is constructed, and a normal distribution parameter estimation model framework is constructed by using the least squares method to determine the expression of normal distribution parameters. Based on the linear deviation calculation of normal distribution parameters and the determination of the maximum similar value of parameters, the parameter estimation is realized by using the Bayesian function of carbonization depth. The parameter estimation of network signal based on carbonization depth is proposed. Parameter estimation can play an important role in the intelligent analysis of big data, and it is also an important basic guarantee for machine learning algorithms. Using the integrity test results and error rate test result, variable parameters calculated from measured parameters, substitution shooting parameters calculation formula of parameter estimation is put forward by the conventional parameter estimation methods, which shot up to 22.12%, is suitable for the carbonation depth of the normal distribution parameter estimation.