Differential Entropy Driven Spectrum Sensing Under Generalized Gaussian Noise

Feature extraction and classification method for switchgear faults based on sample entropy and cloud model

“…In solving the minimum of the Lagrange function, three equality constraints can be obtained by setting the partial derivative of ω, b, and ξ i to 0. Then, they are substituted into (10) in forming the dual form of the optimisation model…”

“…The conventional time-frequency signal processing technologies, including short-time Fourier transform [7] and data envelope analysis [8], essentially focus on analysing stationary time series. Given the non-stationarity of the fault features of switchgears, nonlinear analysis methods, such as the Lyapunov exponent and entropy [9][10][11], must be used to achieve the fault information accurately and effectively.…”

Unilateral left‐tail Anderson Darling test‐based spectrum sensing with Laplacian noise

“…Thus it may be not appropriate to employ them directly in the presence of Laplacian noise. Although detectors in [30] and [31] are discussed in Laplacian noise, the detection performance is not satisfied. Considering the efficiency of the FLOM method, it can be combined with the GoF test to ameliorate the performance degradation caused by heavy-tailed Laplacian noise.…”

“…Based on the GoF theory, several fitting criteria have been applied in spectrum sensing, such as the Cramervon Mises (CM) test, the Kolmogorov–Smirnov (KS) test, the order statistic test, the Anderson Darling (AD) test etc [21–31]. Nevertheless, the proposed detectors in [21–29] have assumed Gaussian noise.…”

“…Based on it, we propose a novel GoF test, named as unilateral left‐tail AD (ULAD) test, and employ it in spectrum sensing to derive a powerful ULAD detector with low complexity. There are three reasons for proposing the ULAD test instead of using the existing GoF tests in [21–31] under Laplacian noise. Firstly, for any given , the p th order moments of received samples are monotonically increasing with samples' absolute value.…”