In this paper, we consider the problem of selective radio channel identification. Two technics are used, the first one is based on Higher Order Statistics (HOS), the second is based on Takagui-Sugeno (TS) fuzzy systems. In order to evaluate the proposed algorithms, we have used two practical selective frequency fading channels called Broadband Radio Access Network (BRAN A and BRAN E) normalized for MC-CDMA systems are considered to perform the proposed technics. The simulation results, for different Signal to Noise Ratio (SNR), demonstrates that: the algorithm based on Higher Order Statistics (HOS) is more efficiency than the TS algorithms in noisy environment - smallest SNR- but the TS algorithm more efficient than the HOS algorithms for highest SNR values.