| 基于PSO的BP神经网络-Markov船舶交通流量预测模型 |
| |
| 引用本文： | 范庆波,江福才,马全党,马勇.基于PSO的BP神经网络-Markov船舶交通流量预测模型[J].上海海事大学学报,2018,39(2):22-27. |
| |
| 作者姓名： | 范庆波 江福才 马全党 马勇 |
| |
| 作者单位： | 武汉理工大学航运学院;武汉理工大学内河航运技术湖北省重点实验室 |
| |
| 基金项目： | 国家自然科学基金（51579202， 51309186） |
| |
| 摘 要： | 为对船舶交通流量进行准确预测,结合BP神经网络和Markov算法,构建BP神经网络-Markov预测模型。引入粒子群优化(particle swarm optimization,PSO)算法对模型进行优化,克服利用Markov模型选取白化系数的不足。用该模型预测武汉长江大桥船舶交通流量的月度数据,结果表明:与BP神经网络的预测精度82.439 0%相比,基于PSO的BP神经网络-Markov预测模型的预测精度提高到91.050 8%,该模型的合理性和准确性得到验证。
|
| 关 键 词： | 船舶交通流量预测 BP神经网络 马尔科夫模型（Markov模型） 粒子群优化（PSO） |
| 收稿时间： | 2017/11/10 0:00:00 |
| 修稿时间： | 2018/1/17 0:00:00 |
PSO-based BP neural network-Markov prediction model of ship traffic flow |
| |
| Abstract: | In order to predict ship traffic flow accurately, a BP neural network Markov prediction model is constructed by combing BP neural network with Markov algorithm. The particle swarm optimization (PSO) algorithm is adopted to optimize the model so as to overcome the deficiency of using Markov model to select a whitening coefficient. The model is used to predict the monthly data of ship traffic flow of Wuhan Yangtze River Bridge. The results show that, compared to the prediction accuracy 82.439 0%of BP neural network, the prediction accuracy of the PSO based BP neural network Markov prediction model is improved to91.050 8%. The rationality and accuracy of the model are verified. |
| |
| Keywords: | ship traffic flow prediction BP neural network Markov model particle swarm optimization (PSO) |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《上海海事大学学报》浏览原始摘要信息 |
| 点击此处可从《上海海事大学学报》下载免费的PDF全文 |
