Research on Urban Street Order based on Data Mining Technology

来源 :第六届中国计算机学会大数据学术会议 | 被引量 : 0次 | 上传用户:wwb518
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
  With the promotion of urbanization,more and more people enjoy the happiness brought about by the urban development,but the type of problems and the amount of problems in urban management are increasing.Under the background of new era,the direction and requirement of the city governance has promoted influenced by the “Internet Plus” strategy and big data strategy.In the construction of information and intelligent construction of urban management,a large number of city operation and management data have been emerged and accumulated,which provide favorable basic conditions for urban research.Through literature reading and field research,this paper made an in-depth study of the current situation of urban management in a city of Zhejiang province.In view of the actual demand of a city in the street order,this paper takes the data fusion cleaning of the street sequence data combined with data mining technology.It builds a Street classification and prediction model by using the decision tree C5.0 algorithm,and a high incidence area classification prediction model by using the Apriori algorithm.The information and knowledge of street order are analyzed.On this basis,this paper designs a street order decision support system,and uses web technology and visualization technology to realize the function modules of street order data service,analysis application,scene display and decision support.The research content of this paper is oriented to the actual demand in the citys street sequencing work,which provides a favorable support for the actual business of urban management,and also provides decision support for urban management.
其他文献
Big data computing and analysis can uncover hidden patterns,correlations and other insights by examining large amounts of data.Comparing with the traditional processor,the new types of processors,just
为了高效地从海量的水文传感器数据中检测出异常值,提出了一种基于SparkR的水文时间序列异常检测方法.对数据进行清洗后,采用滑动窗口配合自回归积分滑动平均模型在SparkR平台上进行预测,然后对预测的结果计算置信区间,在区间范围以外的,将其判定为异常值.基于检测结果,利用K均值算法对原数据进行聚类,同时计算其状态转移概率,对检测出的异常值进行质量评估.以在滁河获取的水文传感器数据为实验数据,分别在
Research on pollution localization using sensor monitoring networks has important significance for environmental protection.There are some challenges in the detection and localization of water polluti
In the real-world many complex systems exist in the form of heterogeneous networks.As we all know,heterogeneous networks consist of various types of vertices and relations,so it is difficult to deal d
基于语义抽取的机器阅读理解是目前人工智能与大数据相结合的热点应用之一。针对复杂多文本机器阅读理解任务中的语义理解与答案提取问题,提出一种结合外部知识的动态多层次语义理解与答案抽取模型。首先,利用改进的门控单元循环神经网络匹配文本内容与问题集;然后,分别在向量化文本内容及问题集上实施多维度动态双向注意力机制分析,提高语义匹配精度;接着,利用动态指针网络确定问题答案范围,改进网络模型语义匹配效率,降低
Caricature face recognition is an interesting but also a hard task for studying owing to the huge exaggeration between two quite different face modalities,photos and caricatures.So,we propose a new re
头脑风暴优化(Brain Storm Optimization,BSO)算法是一种新型的群体智能优化算法,启发于众人集思广益求解问题的模式,适合求解复杂多峰函数优化问题.但BSO求解多峰极值时需进行重复的迭代运算,面对大规模数据集时会出现计算效率与求解精度过低的现象.为解决上述问题,本文设计并实现了一种基于Spark的并行化头脑风暴优化算法,通过将BSO算法中计算复杂度最高的聚类与新解产生过程并行
With the development of social informatization technology,the problems of individual information security are becoming serious.Now-adays identity identification has been required essentially in govern
机器学习涉及一些隐含的敏感数据,当受到模型查询或模型检验等模型攻击时,可能会泄露用户隐私信息.针对上述问题,本文提出一种敏感数据隐私保护“师徒”模型PATE-T,为机器学习模型的训练数据提供强有力的隐私保证.该方法以“黑盒”方式组合了由不相交敏感数据集训练得到的多个“师父”模型,这些模型直接依赖于敏感训练数据.“徒弟”由“师父”集合迁移学习得到,不能直接访问“师父”或基础参数,“徒弟”所在数据域与
频繁封闭子图挖掘被证明是NP-难问题.多年来,虽然已有许多算法被提出用于解决该问题,但在挖掘大规模图数据时,却面临着共同的计算效率问题.特别是,当图中节点的平均度数增加时,挖掘效率更是急剧下降.针对以上问题,本文提出一种面向大规模图数据的高效分布式挖掘算法Desu-FSM.与现有基于水平分解的分布式挖掘框架不同,该算法首次采用了基于垂直分解的分布式挖掘框架.其基本思想可概括为“快速抵近,双向搜索”