摘要
为充分利用港口既有的建设规模、提高经济效益,对集装箱码头的泊位分配进行研究.采用神经网络和聚类分析两种数据挖掘技术分析相关数据,得到相应的数据挖掘模型.先通过反向传播(Back Propagation,BP)神经网络分析各因素对泊位分配的影响程度,确定出主要因素;然后通过聚类分析中的两步聚类算法进行分析;最终制定集装箱码头泊位分配策略.该方法可为提高集装箱码头生产效率提供帮助.
To make full use of existing port scale and improve economic efficiency, the berth allocation in container terminals is studied. Two data mining methods, namely, neural network and cluster analysis, are employed to analyze related data and the corresponding data mining model is proposed. First, the Back Propagation （BP） neural network is used to analyze the effects of various factors on berth allocation to figure out main factors. Then, the two-step clustering algorithm in cluster analysis is used to finally es- tablish the berth allocation strategy. The proposed method can help to improve the productivity in contain- er terminals.
出处
《上海海事大学学报》
北大核心
2013年第3期8-12,47,共6页
Journal of Shanghai Maritime University
基金
国家自然科学基金(71101090)
交通运输部项目(2012-329-810-180)
上海市教育委员会科研创新项目(12ZZ148
13YZ080)
上海海事大学校基金(20120102
20110019)
关键词
集装箱码头
泊位分配
数据挖掘
神经网络
聚类分析
container terminal
berth allocation
data mining
neural network
cluster analysis
