摘要
为克服传统BP神经网络在运算过程的不足,提出一种基于高维粒子群算法的神经网络优化方法。通过在高维PSO算法中引入随机变化的加速常数来获得最优权值,对BP神经网络进行优化和训练,再将优化好的高维BP神经网络运用到交通事件自动检测中,通过检测训练算法,并对训练后的数据进行分类测试,把分类测试的结果与传统BP神经网络和经典事件检测算法比较。结果显示,经过优化后的高维粒子群BP神经网络的检测率、算法性能均优于BP神经网络算法和经典算法,其中97,50个测试样本中仅有2个测试样本与应该达到的数值不一致,其他样本都满足测试要求,并且平均优化测试时间是传统BP神经网络检测时间的一半,因此,优化后的BP神经网络算法的性能十分优越。
In order to eliminate the shortcomings of the traditional BP neural network in the operation process,a neural net?work optimization method based on the high?dimensional particle swarm optimization algorithm is proposed. The acceleration con?stant with random variation is introduced into the high?dimensional PSO algorithm to acquire the optimal weight to optimize and train the BP neural network. The optimized high?dimensional BP neural network is applied to the automatic detection of the traf?fic incident. The trained data is performed with class test with the detection and training algorithm,and its result is compared with those tested with the traditional BP neural network algorithm and classical event detection algorithm. The results show thatthe detection rate and performance of the algorithm optimized with high?dimensional particle swarm optimization BP neural net?work algorithm are better than those optimized with BP neural network algorithm and classical algorithm,the values of 2 testsamples are different with the expected values of 97 and 50 test samples,the rest samples can meet the test requirement,and the average optimal testing time is half of the detection time of the traditional BP neural network. The optimized BP neural net?work algorithm has excellent performance.
作者
黄余
HUANG Yu(College of Computer Science,Chongqing University,Chongqing 400044,China;Yibin Vocational and Technical College,Yibin 644003,China)
出处
《现代电子技术》
北大核心
2017年第3期157-159,163,共4页
Modern Electronics Technique
基金
四川省教育厅自然科学类重点项目:复杂曲面零件模块化参数宏程序编程应用与研究(14ZB0470)
关键词
高维BP神经网络
粒子群算法
神经网络
结构优化
high-dimensional BP neural network
particle swarm optimization
neural network
structure optimization
