Detection of Wi-Fi transmitter transients using statistical method
Lianfen Huang, Minghui Gao, Caidan Zhao, Xiongpeng Wu · 2013
Algorithms used to detect Wi-Fi transmitter transients are discussed in this paper, and the start of a Wi-Fi transmitter transient, in our opinion, has a new definition. Current algorithms, namely Variance Fractal Dimension Threshold Detection, Bayesian Step Change Detection and Phase Detection are analyzed at the beginning of this article. According to the disadvantages such as complexity, accuracy and a threshold needed in the final determination of these traditional methods, an improved algorithm based on Mean Change Point Detection is put forward. Threshold for determination and nonparametric estimation for hypothesis test are not needed in our improved approach, it detects the start of transient only by calculating the maximum of the difference of statistic. Moreover, the experimental results show that this improved method outperforms the other three methods, particularly in the case of low SNR.