冷链物流配送大数据实时监控优化仿真
|
摘要
为了监控冷链物流在配送过程中产生的大数据,需要对冷链物流配送大数据实时监控方法进行优化。采用当前冷链物流配送大数据实时监控方法对冷链物流配送过程中的大数据进行实时监控时,得到的动态特征可信度低、目标定位结果精准度低。提出一种冷链物流配送大数据实时监控优化方法。结合Odds特征算法和BNS特征算法,融合差异率和BNS特征值的方差及权值得到冷链物流配送大数据的动态特征。根据动态特征得到相似性函数的最大位置,通过Bhattacharyya系数确定自适应加权和特征选择,完成冷链物流配送过程中目标数据的定位,对冷链物流配送大数据的目标数据进行实时跟踪,完成冷链物流配送大数据的实时监控。仿真结果表明,所提方法得到的动态特征可信度高、目标定位结果精准度高。
In order to monitor the big data of cold chain logistics during the distribution process, it is necessary to optimize the real-time monitoring method. Therefore, a method of real-time monitoring and optimization for big data in cold chain logistics distribution was proposed. At first, this research combined Odds feature algorithm with BNS feature algorithm and integrated variance and weight of the difference rate and the BNS feature value to obtain the dynamic feature of big data during the cold-chain logistics distribution. Then, the research obtained the maximum position of similarity function based on the dynamic feature. Meanwhile, our research used the Bhattacharyya coefficient to determine the adaptive weighting and the feature selection, so as to complete the positioning of target data during the cold-chain logistics distribution. Finally, we tracked the target data of bid data in cold chain logistics distribution in real time. Thus, we completed the real-time monitoring for big data during the cold chain logistics distribution. Simulation results prove that the proposed method has high reliability of dynamic feature and high accuracy of target positioning result.
In order to monitor the big data of cold chain logistics during the distribution process, it is necessary to optimize the real-time monitoring method. Therefore, a method of real-time monitoring and optimization for big data in cold chain logistics distribution was proposed. At first, this research combined Odds feature algorithm with BNS feature algorithm and integrated variance and weight of the difference rate and the BNS feature value to obtain the dynamic feature of big data during the cold-chain logistics distribution. Then, the research obtained the maximum position of similarity function based on the dynamic feature. Meanwhile, our research used the Bhattacharyya coefficient to determine the adaptive weighting and the feature selection, so as to complete the positioning of target data during the cold-chain logistics distribution. Finally, we tracked the target data of bid data in cold chain logistics distribution in real time. Thus, we completed the real-time monitoring for big data during the cold chain logistics distribution. Simulation results prove that the proposed method has high reliability of dynamic feature and high accuracy of target positioning result.
引文
[1] 何亚平. 基于网络实时监控的液压元件数据监测与系统研究[J]. 现代电子技术, 2016,39(1):76-80.
[2] 刘帆,等. 基于LwIP的APF实时数据采集监控系统设计[J]. 电测与仪表, 2018,55(2): 118-122.
[3] 赵安新,等. 基于实时数据流的煤矿监测数据流计算模式分析[J]. 煤炭技术, 2017,36(12):202-204.
[4] 吴向阳,等. 使用过滤与放大技术的微博数据监控分析系统[J]. 计算机辅助设计与图形学学报, 2016,28(11):1872-1880.
[5] 杨建亮,侯汉平. 冷链物流大数据实时监控优化研究[J]. 科技管理研究, 2017,37(6): 198-203.
[6] 曹伟,等. 基于RFID技术的离散制造车间实时数据采集与可视化监控方法[J]. 计算机集成制造系统, 2017,23(2):273-284.
[7] 马大中,胡旭光,孙秋野. 基于大维数据驱动的油气管网泄漏监控模糊决策方法[J]. 自动化学报, 2017,43(8):1370-1382.
[8] 朱宏,等. 天津市地震局数据监控与展示系统的设计与实现[J]. 地震工程学报, 2016,38(s2):231-235.
[9] 刘安民,尹兰,沈航. CXK650型数控机床切削参数优化及实时监控系统开发研究[J]. 机械科学与技术, 2016,35(1):113-117.
[10] 叶康林. 基于实时数据库的数据可视化分析系统[J]. 计算机仿真, 2017,34(1): 129-131.
[2] 刘帆,等. 基于LwIP的APF实时数据采集监控系统设计[J]. 电测与仪表, 2018,55(2): 118-122.
[3] 赵安新,等. 基于实时数据流的煤矿监测数据流计算模式分析[J]. 煤炭技术, 2017,36(12):202-204.
[4] 吴向阳,等. 使用过滤与放大技术的微博数据监控分析系统[J]. 计算机辅助设计与图形学学报, 2016,28(11):1872-1880.
[5] 杨建亮,侯汉平. 冷链物流大数据实时监控优化研究[J]. 科技管理研究, 2017,37(6): 198-203.
[6] 曹伟,等. 基于RFID技术的离散制造车间实时数据采集与可视化监控方法[J]. 计算机集成制造系统, 2017,23(2):273-284.
[7] 马大中,胡旭光,孙秋野. 基于大维数据驱动的油气管网泄漏监控模糊决策方法[J]. 自动化学报, 2017,43(8):1370-1382.
[8] 朱宏,等. 天津市地震局数据监控与展示系统的设计与实现[J]. 地震工程学报, 2016,38(s2):231-235.
[9] 刘安民,尹兰,沈航. CXK650型数控机床切削参数优化及实时监控系统开发研究[J]. 机械科学与技术, 2016,35(1):113-117.
[10] 叶康林. 基于实时数据库的数据可视化分析系统[J]. 计算机仿真, 2017,34(1): 129-131.