摘要
提出了一种多宇宙并行量子遗传算法 ,并从理论上证明了算法的全局收敛性 .算法中将所有的个体按照一定的拓扑结构分成一个个独立的子群体 ,称为宇宙 ;采用多状态基因量子比特编码方式来表达宇宙中的个体 ;采用通用的量子旋转门策略和动态调整旋转角机制对个体进行演化 ;采用量子非门实现量子变异以阻止早熟收敛 ;各宇宙独立演化 ,宇宙之间采用最佳移民和量子交叉操作来交换信息 ,提高算法的执行效率 .将该算法与独立分量分析算法相结合 ,提出一种盲源分离新方法 .仿真结果表明
This paper first proposes a novel Multi-Universe Parallel Quantum Genetic Algorithm (MPQGA) and proves its global convergence in theory. In the algorithm, all individuals are divided into some independent sub-colonies, called universes, according to their definite topological structure. Individuals in a universe are represented by multi-state gene qubits. In the individual's updating, the general quantum rotation gate strategy and dynamic adjusting rotation angle mechanism are applied to accelerate convergence. Quantum NOT gate is used to realize quantum mutation to avoid premature convergence. Each universe evolving independently enlarges the search space. Information among the universes is exchanged by adopting the best emigration and the quantum crossover operation for the improvement of search efficiency. Then it puts forward a new Blind Source Separation (BSS) method based on the combination of MPQGA and Independent Component Analysis (ICA). The simulation results show that the efficiency of the new BSS method is obviously higher than that of the Conventional Genetic Algorithm (CGA) and the Quantum Genetic Algorithm (QGA).
出处
《电子学报》
EI
CAS
CSCD
北大核心
2004年第6期923-928,共6页
Acta Electronica Sinica
基金
国家自然科学基金 (No .60 1 71 0 2 9)
关键词
量子计算
遗传算法
量子遗传算法
多宇宙并行量子遗传算法
盲源分离
Blind source separation
Computer simulation
Convergence of numerical methods
Genetic algorithms
Independent component analysis
Topology
