Frequency Domain Incremental Strategies Over Distributed Network
This paper presents a frequency-domain adaptive strategy based on incremental techniques. The proposed scheme represents the problem of linear estimation using frequency-domain transformation methods like discrete cosine transform (DCT) and discrete Fourier transform (DFT) in a cooperative manner, where nodes are having the computing ability to find the local estimation in frequency domain and sharing them among the predefined neighbors. This algorithm is distributed and cooperative in nature. In addition to this, it also responds to real-time environments and produces a better result than that of the incremental time-domain adaptive method under colored input. Each node shares information with its immediate neighbors to fully exploit the spatial dimension, thereby lowering the communication burden. Computer simulation result illustrates the performance of the new algorithm.
KeywordsIncremental algorithm Distributed processing Incremental DCTLMS Incremental DFTLMS
- 2.Estrin, D., Pottie, G., Srivastava, M.: Instrumenting the world with wireless sensor networks. In: Proceedings IEEE International Conference Acoustics, Speech, Signal Processing (ICASSP), pp. 2033–2036. Salt Lake City, UT (2001)Google Scholar
- 4.Widrow, B., Stearns, S.D.: Adaptive Signal Process. Englewood Cliffs, NJ (1985)Google Scholar
- 5.Sayed, A.H.: Fundamentals of Adaptive Filtering. Wiley, New York (2003)Google Scholar