Paul Caspi, Jacek Priotrowski and Raoul Velazco
IEEE Transactions on Computers 40(9), 1068-1071, 1991
This paper presents an evaluation of signature analysis efficiency which does not rely on assumptions about the distribution of the analyzed error sequence. This is achieved through the use of an a priori randomization technique which leads to a choice of LSFRs corresponding to randomly chosen irreducible polynomials of a given degree. As it does not make use of assumptions on the error distribution, the proposed evaluation is more pessimistic than the usual ones.Particularly, it takes into account the length of the analyzed sequence. However, it can be valuable when the efficiency of signature analysis has to be guaranteed, for high dependability purposes for instance. In this case, LFSRs of length 32 seem to be a practical choice with respect to both the maximum length of the analyzed sequences and the aliasing error probability.
Index-terms- Aliasing error probability, a priori randomization, irreducible polynomials, linear feedback registers (LFSR), signature analysis efficiency.