摘要
提出了一种结合遗传算法和神经网络算法的测试用例生成方法,算法融合了误差反向传播算法在避免陷入局部最优和保持种群多样性方面的优势,克服了遗传算法局部搜索能力差及其早熟现象。实验结果表明,新方法在测试用例自动生成的效率和效果方面,优于传统遗传算法。
In the software testing technology, efficient test case generation is a means for simplifying the testing work, and improving the efficiency of the test. A newly kind of software test Qase automated generation method based on genetic algorithm and neural network algorithm is proposed. The algorithm combirnes genetic algorithm with back propagation algorithm to overcome the disadvantages of local optimum and keep the advantages of specics diversity.The experiment results show that this algorithm is superior to the traditional genetic algorithin in efficiency and effectivencss of test case generation.
出处
《长春理工大学学报（自然科学版）》
2010年第3期137-139,47,共4页
Journal of Changchun University of Science and Technology(Natural Science Edition)
关键词
遗传算法
神经网络
测试用例生成
genetic algorithm
neural network
test case generation
