基于大数据的交通处理平台的分析与应用
|
摘要
为了提高交通处理平台的大数据分析和管理能力,提出一种基于大数据融合调度模型的交通处理平台。对交通处理大数据进行信息聚类处理,采用关联规则特征提取方法进行交通处理平台大数据有效挖掘,结合信息融合理论,对交通处理平台中的文本信息、位置信息、图片、音频、视频等数据进行模式识别和信息融合,提高大数据计算资源的利用效率。建立实时性较高的有效算法库,快速形成面对不同模型大数据的知识库,实现大数据优化挖掘和智能调度,提高交通处理平台的智能信息管理能力。实验结果表明,采用该方法进行交通处理平台的大数据挖掘的聚类性较好,信息融合度较高,数据调度的准确率高达96%。运用该平台能够使数据调度和访问的效率得到有效提升。
In order to improve the large data analysis and management ability of traffic processing platform,a traffic processing platform based on large data fusion scheduling model is proposed. The large data of traffic processing are processed by information clustering,and the feature extraction method of association rules is used to mine the large data of traffic processing platform. Combining with information fusion theory,pattern recognition and information fusion of text information,location information,pictures,audio and video data in traffic processing platform are improved greatly. Data computing resource utilization efficiency. Establish an effective algorithm base with high real-time performance,quickly form a knowledge base facing large data of different models,realize large data optimal mining and intelligent scheduling,and improve the intelligent information management capability of traffic processing platform. The experimental results show that the clustering of large data mining in traffic processing platform is better,the degree of information fusion is higher,and the accuracy of data scheduling is as high as 96%. With the platform,the efficiency of data scheduling and access can be effectively improved.
In order to improve the large data analysis and management ability of traffic processing platform,a traffic processing platform based on large data fusion scheduling model is proposed. The large data of traffic processing are processed by information clustering,and the feature extraction method of association rules is used to mine the large data of traffic processing platform. Combining with information fusion theory,pattern recognition and information fusion of text information,location information,pictures,audio and video data in traffic processing platform are improved greatly. Data computing resource utilization efficiency. Establish an effective algorithm base with high real-time performance,quickly form a knowledge base facing large data of different models,realize large data optimal mining and intelligent scheduling,and improve the intelligent information management capability of traffic processing platform. The experimental results show that the clustering of large data mining in traffic processing platform is better,the degree of information fusion is higher,and the accuracy of data scheduling is as high as 96%. With the platform,the efficiency of data scheduling and access can be effectively improved.
引文
[1]张景祥,王士同,邓赵红,等.融合异构特征的子空间迁移学习算法[J].自动化学报,2014,40(2):236-246.
[2]彭丽英.改进滑模干扰控制律交通数据反步融合算法[J].控制工程,2014,21(4):515-519.
[3]陈秀锋,许洪国,倪安宁.并行微观交通动态负载平衡预测方法仿真[J].计算机仿真,2013,30(8):164-168.
[4] GUO H,LIU H,WU C,et al. Logistic discrimination based on G-mean and F-measure for imbalanced problem[J]. Journal of Intelligent and Fuzzy Systems,2016,31(3):1155-1166.
[5]吴建军,段淑敏.交通拥堵状态下的智能调度平台的设计与仿真[J].现代电子技术,2016,39(16):401-43.
[6]都琳,张莹,胡高歌,等.一种双寡头垄断Cournot-Puu模型的混沌控制研究[J].应用数学和力学,2017,38(2):224-232.
[7]芮兰兰,李钦铭.基于组合模型的短时交通流量预测算法[J].电子与信息学报,2016,38(5):1227-1233.
[8]张永,李卓然,刘小丹.基于主动学习SMOTE的非均衡数据分类[J].计算机应用与软件,2012,29(3):91-93.
[9]谷琼,袁磊,熊启军,等.基于非均衡数据集的代价敏感学习算法比较研究[J].微电子学与计算机,2011,28(8):146-149.
[10]王思臣,涂辉,张以文.基于不确定服务质量感知的云服务组合方法[J].计算机应用,2018,38(10):2753-2758.
[11] PARVIN H,MIRNABIBABOLI M,ALINEJAD-ROKNY H.Proposing a classifier ensemble framework based on classifier selection and decision tree[J]. Engineering Applications of Artificial Intelligence,2015,37:34-42.
[12]郭华平,董亚东,毛海涛,等.一种基于逻辑判别式的稀有类分类方法[J].小型微型计算机系统,2016,37(1):140-145.
[13]李建勋,佟瑞,张永进,等.基于趋势面与SSIM的时空数据相似度算法[J].计算机工程,2018,44(9):52-58. s.
[2]彭丽英.改进滑模干扰控制律交通数据反步融合算法[J].控制工程,2014,21(4):515-519.
[3]陈秀锋,许洪国,倪安宁.并行微观交通动态负载平衡预测方法仿真[J].计算机仿真,2013,30(8):164-168.
[4] GUO H,LIU H,WU C,et al. Logistic discrimination based on G-mean and F-measure for imbalanced problem[J]. Journal of Intelligent and Fuzzy Systems,2016,31(3):1155-1166.
[5]吴建军,段淑敏.交通拥堵状态下的智能调度平台的设计与仿真[J].现代电子技术,2016,39(16):401-43.
[6]都琳,张莹,胡高歌,等.一种双寡头垄断Cournot-Puu模型的混沌控制研究[J].应用数学和力学,2017,38(2):224-232.
[7]芮兰兰,李钦铭.基于组合模型的短时交通流量预测算法[J].电子与信息学报,2016,38(5):1227-1233.
[8]张永,李卓然,刘小丹.基于主动学习SMOTE的非均衡数据分类[J].计算机应用与软件,2012,29(3):91-93.
[9]谷琼,袁磊,熊启军,等.基于非均衡数据集的代价敏感学习算法比较研究[J].微电子学与计算机,2011,28(8):146-149.
[10]王思臣,涂辉,张以文.基于不确定服务质量感知的云服务组合方法[J].计算机应用,2018,38(10):2753-2758.
[11] PARVIN H,MIRNABIBABOLI M,ALINEJAD-ROKNY H.Proposing a classifier ensemble framework based on classifier selection and decision tree[J]. Engineering Applications of Artificial Intelligence,2015,37:34-42.
[12]郭华平,董亚东,毛海涛,等.一种基于逻辑判别式的稀有类分类方法[J].小型微型计算机系统,2016,37(1):140-145.
[13]李建勋,佟瑞,张永进,等.基于趋势面与SSIM的时空数据相似度算法[J].计算机工程,2018,44(9):52-58. s.