On the frequency of symbols in sequences generated by nonlinear Feedforward generators

Due to their simple construction, LFSRs are commonly used as building blocks in various random number generators. Nonlinear feedforward logic is incorporated in LFSRs to increase the linear complexity of the generated sequences. This work deals with Nonlinear Feedforward Generators (NLFGs) that generate sequences over arbitrary finite fields. We analyze the frequency of symbols in sequences generated by such configurations. Further, we propose a method of using nonlinear feedforward logic with word-based σ-LFSRs wherein vectors over a finite field are seen as elements of an extension field. We then briefly analyze sequences generated by an existing scheme and show that sequences generated by the proposed scheme are statistically more balanced.