Journal of Applied Sciences1812-56541812-5662Asian Network for Scientific Information10.3923/jas.2009.4071.4075AyanzadehR.HassaniK.MoghaddasY.GheibyH.SetayeshiS.122009922Generating random numbers plays outstanding role in computer simulations. Most applications demand for uniform random numbers more than other distributions. In this study concept of two-layer cellular automata and a novel neighborhood structure are introduced. According to these concepts, a novel approach for uniform random number generating is proposed. First layer consists of binary cellular automata which are responsible for activation and inactivation of cells in next layer. A cellular automaton with integer values is used for second layer. Interaction between layers of represented cellular automata leads to a dynamic and complex behavior of proposed model. To evaluate the quality of proposed model, several simulations were implemented. Results prove that two-layer cellular automata generate better uniform random numbers in comparison with MATLAB. Simulation of innovative RNG based on cellular automata, shows promising results, which encourage further research with the proposed techniques in this and related domains.]]>Ayanzadeh , R., M. Teshnehlab and S. Setayeshi,2008Banks, J., J. Carson, B.L. Nelson and D. Nicol,2004Bar-Yam, Y.,1997Chen, T.Y. and R. Merkel,2005Hortensius, P.D., R.D. McLeod, W. Pries, D.M. Miller and H.C. Card,1989Jang, J.S.R., C.T. Sun and E. Mizutani,1997Kalos, M.H.,2007Kohlbrenner, P. and K. Gaj,2004Lecuyer, P.,2003Moghaddas, Y., R. Ayanzadeh and A.T. Hagigat,2008Sarkar, P.,2000Viega, J.,2003Wolfram, S.,1986