A virtual reconfigurable architecture(VRA)-based evolvable hardware is proposed for automatic synthesis of combinational logic circuits at gate-level.The proposed VRA is implemented by a Celoxica RC1000 peripheral component interconnect(PCI)board with an Xilinx Virtex xcv2000E field programmable gate array(FPGA).To improve the quality of the evolved circuits,the VRA works through a two-stage evolution: finding a functional circuit and minimizing the number of logic gates used in a feasible circuit.To optimize the algorithm performance in the two-stage evolutionary process and set free the user from the time-consuming process of mutation parameter tuning,a self-adaptive mutation rate control(SAMRC)scheme is introduced.In the evolutionary process,the mutation rate control parameters are encoded as additional genes in the chromosome and also undergo evolutionary operations.The efficiency of the proposed methodology is tested with the evolutions of a 4-bit even parity function,a 2-bit multiplier,and a 3-bit multiplier.The obtained results demonstrate that our scheme improves the evolutionary design of combinational logic circuits in terms of quality of the evolved circuit as well as the computational effort,when compared to the existing evolvable hardware approaches.
Rough set theory is an important tool to solve uncertain problems. Attribute reduction, as one of the core issues of rough set theory, has been proven to be an effective method for knowledge acquisition. Most of heuristic attribute reduction algorithms usually keep the positive region of a target set unchanged and ignore boundary region information. So, how to acquire knowledge from the boundary region of a target set in a multi-granulation space is an interesting issue. In this paper, a new concept, fuzziness of an approximation set of rough set is put forward firstly. Then the change rules of fuzziness in changing granularity spaces are analyzed. Finally, a new algorithm for attribute reduction based on the fuzziness of 0.5-approximation set is presented. Several experimental results show that the attribute reduction by the proposed method has relative better classification characteristics compared with various classification algorithms.
