摘要
Using the hypothesis that data transmitted by different users are statistically independent of each other,this paper proposes a fixed-point blind adaptive multiuser detection algorithm for Time-Hopping (TH) Impulse Radio (IR) Ultra Wide Band (UWB) systems in multipath channel,which is based on Independent Component Analysis (ICA) idea. The proposed algorithm employs maximizing negentropy criterion to separate the data packets of different users. Then the user characteristic se-quences are utilized to identify the data packet order of the desired user. This algorithm only needs the desired user’s characteristic sequence instead of channel information,power information and time-hoping code of any user. Due to using hypothesis of statistical independence among users,the proposed algorithm has the outstanding Bit Error Rate (BER) performance and the excellent ability of near-far resistance. Simulation results demonstrate that this algorithm has the performance close to that of Maximum-Likelihood (ML) algorithm and is a suboptimum blind adaptive multiuser detection algorithm of excellent near-far resistance and low complexity.
Using the hypothesis that data transmitted by different users are statistically independent of each other, this paper proposes a fixed-point blind adaptive multiuser detection algorithm for Time-Hopping （TH） Impulse Radio （IR） Ultra Wide Band （UWB） systems in multipath channel, which is based on Independent Component Analysis （ICA） idea. The proposed algorithm employs maximizing negentropy criterion to separate the data packets of different users. Then the user characteristic sequences are utilized to identify the data packet order of the desired user. This algorithm only needs the desired user＇s characteristic sequence instead of channel information, power information and time-hoping code of any user. Due to using hypothesis of statistical independence among users, the proposed algorithm has the outstanding Bit Error Rate （BER） performance and the excellent ability of near-far resistance. Simulation results demonstrate that this algorithm has the performance close to that of Maximum-Likelihood （ML） algorithm and is a suboptimum blind adaptive multiuser detection algorithm of excellent near-far resistance and low complexity.
