A serious limitation in microarray analysis is the unreliability of the data generated from low signal intensities. Such data may produce erroneous gene expression ratios and cause unnecessary validation or post-analysis follow-up tasks. Therefore, elimination of unreliable signal intensities will enhance reproducibility and reliability of gene expression ratios produced from the microarray data. In this study, we applied Fuzzy c-Means classification method to separate microarray data into low (or unreliable) and high (or reliable) signal intensity populations. We compared results of fuzzy classification with that of classification based on normal mixture modeling. Both approaches were validated against reference sets of biological data consisting of only true positives and negatives. We observed that both methods performed equally well in terms of sensitivity and specificity. However, a comparison of the computation times indicated that the fuzzy approach is computationally more efficient.