Recent applications of clustering and neural network techniques to channel
equalization have revealed the classification nature of this problem. This
paper illustrates an implementation of a global system for mobile communica
tions (GSM) receiver in which channel equalization and demodulation are rea
lized by means of the nearest neighbor (NN) classifier algorithm. The most
important advantage in using such techniques is the significant reduction i
n terms of computational complexity compared with the maximum likelihood se
quence estimation (MLSE) equalizer. The proposed approach involves symbol-b
y-symbol interpretation and the knowledge of the channel is embedded in the
mapping process of the received symbols over the symbols of the training s
equence. This means that no explicit channel estimation need be carried out
, either with correlative blocks or using neural networks thus speeding up
the entire process. The performance of the proposed receiver, evaluated thr
ough a channel simulator for mobile radio communications, is compared with
the results obtained by means of a 16-state Viterbi algorithm and other sub
optimal receivers. It is shown that the presented algorithm increases the b
it error rate (BER) compared with the MLSE demodulator, but the performance
degradation, despite the simplicity of the receiver, is kept within the li
mits imposed by the GSM specifications.