Title :
A hybrid digital signal processing-neural network CDMA multiuser detection scheme
Author :
Kechriotis, George ; Manolakos, Elias S.
Author_Institution :
Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA
fDate :
2/1/1996 12:00:00 AM
Abstract :
We present a new hybrid digital signal processing-neural network two-step multiuser detection scheme whose small computational complexity makes it attractive for real-time CDMA multiuser detection. An investigation on the nature of the local minima of the Optimal Multiuser Detector´s (OMD) objective function leads to the development of an efficient algorithmic stage that can reduce significantly the size of the OMD optimization problem. This stage may then be followed by a Hopfield neural network employed to solve a smaller size residual problem of the same form. The performance of the hybrid detector is evaluated via simulations and it is shown to exceed that of other suboptimal receivers at a much lower computational cost in both synchronous and asynchronous CDMA transmission cases
Keywords :
Hopfield neural nets; VLSI; code division multiple access; computational complexity; mixed analogue-digital integrated circuits; neural chips; optimisation; real-time systems; signal detection; spread spectrum communication; telecommunication computing; CDMA multiuser detection scheme; Hopfield neural network; asynchronous CDMA transmission; computational complexity; digital signal processing; hybrid DSP-neural network; local minima; objective function; real-time multiuser detection; synchronous CDMA transmission; Computational efficiency; Detectors; Digital signal processing; Hopfield neural networks; Multiaccess communication; Multiuser detection; Neural networks; Signal processing; Signal processing algorithms; Spread spectrum communication;
Journal_Title :
Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on