$textbf{Trajectory Data Mining: An Overview}$

很好的一篇概述,清晰明了地阐述了其框架,涉及内容又十分宽泛。值得细读。

未完成,需要补充。

  1. $textbf{Trajectory Data}$:主要分为四个类别
    1. $texttt{Mobility of people}$
    2. $texttt{Mobility of transportation}$
    3. $texttt{Mobility of animals}$
    4. $texttt{Mobility of natural phenomena}$
  2. $textbf{Trajectory Data Preprocessing}$
    1. $texttt{Noise Filtering}$
      1. $textit{Mean Filter}$
      2. $textit{Kalman and Particle Filters}$
      3. $textit{Heuristics-Based Outlier Detection}$
    2. $texttt{Stay Point Detection}$
    3. $texttt{Trajectory Compression}$:对轨迹数据进行压缩,以减少计算量
      1. $textit{Distance Metric}$
      2. $textit{Offline Compression}$
      3. $textit{Online Data Reduction}$
      4. $textit{Compression with Semantic Meaning}$
    4. $texttt{Trajectory Segmentation}$:对轨迹数据进行切割
      1. $textit{time interval}$
      2. $textit{shape of a trajectory}$
      3. $textit{semantic meanings}$
    5. $texttt{Map Matching}$:对原始的经纬度数据转化为路网数据
      1. $textit{geometric}$
      2. $textit{topological}$
      3. $textit{probabilis 大专栏  VI.应用-Trajectory Data Miningtic}$
      4. $textit{other advanced techniques}$
  3. $textbf{Trajectory Data Management}$
    1. $texttt{Trajectory Indexing and Retrieval}$:没看懂是为了解决什么问题
    2. $texttt{Distance/Similarity of Trajectories}$:了解一下度量方式
  4. $textbf{Uncertainty in Trajectory Data}$
    1. $texttt{Reducing Uncertainty from Trajectory Data}$:解决因采样率低,造成数据稀疏,不确定性增大等问题
      1. $textit{Modeling Uncertainty of a Trajectory for Queries}$
      2. $textit{Path Inference from Uncertain Trajectories}$
    2. $texttt{Privacy of Trajectory Data}$:为保护隐私性,需要增大数据的不确定性。
  5. $textbf{Trajectory Pattern Mining}$
    1. $texttt{Moving Together Patterns}$
    2. $texttt{Trajectory Clustering}$
    3. $texttt{Mining Sequential Patterns from Trajectories}$
    4. $texttt{Mining Periodical Patterns from Trajectories
      }$
  6. $textbf{Trajectory Classification}$:做运动状态分类、交通方式分类等分类任务
  7. $textbf{Anomalies Detection From Trajectories}$
    1. $texttt{Detecting Outlier Trajectories}$
    2. $texttt{Identifying Anomalous Events by Trajectories}$
  8. $textbf{Transfer Trajectory To Other Representations}$
    1. $texttt{From Trajectory to Graph}$
    2. $texttt{From Trajectory to Matrix}$
    3. $texttt{From Trajectory to Tensor}$

VI.应用-Trajectory Data Mining的更多相关文章

  1. Distributed Databases and Data Mining: Class timetable

    Course textbooks Text 1: M. T. Oszu and P. Valduriez, Principles of Distributed Database Systems, 2n ...

  2. What is the most common software of data mining? (整理中)

    What is the most common software of data mining? 1 Orange? 2 Weka? 3 Apache mahout? 4 Rapidminer? 5 ...

  3. What’s the difference between data mining and data warehousing?

    Data mining is the process of finding patterns in a given data set. These patterns can often provide ...

  4. A web crawler design for data mining

    Abstract The content of the web has increasingly become a focus for academic research. Computer prog ...

  5. Datasets for Data Mining and Data Science

    https://github.com/mattbane/RecommenderSystem http://grouplens.org/datasets/movielens/ KDDCUP-2012官网 ...

  6. cluster analysis in data mining

    https://en.wikipedia.org/wiki/K-means_clustering k-means clustering is a method of vector quantizati ...

  7. Weka 3: Data Mining Software in Java

    官方网站: Weka 3: Data Mining Software in Java 相关使用方法博客 WEKA使用教程(经典教程转载) (实例数据:bank-data.csv) Weka初步一.二. ...

  8. data mining,machine learning,AI,data science,data science,business analytics

    数据挖掘(data mining),机器学习(machine learning),和人工智能(AI)的区别是什么? 数据科学(data science)和商业分析(business analytics ...

  9. 数据挖掘(data mining),机器学习(machine learning),和人工智能(AI)的区别是什么? 数据科学(data science)和商业分析(business analytics)之间有什么关系?

    本来我以为不需要解释这个问题的,到底数据挖掘(data mining),机器学习(machine learning),和人工智能(AI)有什么区别,但是前几天因为有个学弟问我,我想了想发现我竟然也回答 ...

随机推荐

  1. 吴裕雄--天生自然 PYTHON3开发学习:迭代器与生成器

    list=[1,2,3,4] it = iter(list) # 创建迭代器对象 for x in it: print (x, end=" ") import sys # 引入 s ...

  2. Rikka with Prefix Sum

    Rikka with Prefix Sum 题目 https://www.nowcoder.com/acm/contest/148/D 题目有三个操作 l到r都添加一个数 取一次前缀和 查询区间和 这 ...

  3. log4j中%5p的含义

    因为日志级别分别有error,warn,info,debug,fatal5种,有些是5个字母的,有些是4个字母的,如果直接写%p就会对不齐,%-5p的意思是日志级别输出左对齐,右边以空格填充,%5p的 ...

  4. 华为路由器AR1220E-S通过web页面不能登录

    问题原因:由于在WEB页面配置了“远程信任主机”,但是信任主机和路由器不在一个网段,导致所有IP都不能通过WEB页面管理路由器 解决方案:通过console口直接连接路由器,删除信任主机,此次咨询了华 ...

  5. 吴裕雄--天生自然python机器学习:朴素贝叶斯算法

    分类器有时会产生错误结果,这时可以要求分类器给出一个最优的类别猜测结果,同 时给出这个猜测的概率估计值. 概率论是许多机器学习算法的基础 在计算 特征值取某个值的概率时涉及了一些概率知识,在那里我们先 ...

  6. LeetCode No.97,98,99

    No.97 IsInterleave 交错字符串 题目 给定三个字符串 s1, s2, s3, 验证 s3 是否是由 s1 和 s2 交错组成的. 示例 输入: s1 = "aabcc&qu ...

  7. 怎么保证RabbitMQ和kafuka集群的高可用性?

    rabbitMQ有三种模式:单机模式,普通集群模式,镜像集群模式 RabbitMQ的高可用性   RabbitMQ是比较有代表性的,因为是基于主从做高可用性的,我们就以他为例子讲解第一种MQ的高可用性 ...

  8. Spring Cloud服务的注册与发现(Eureka)

    一.spring cloud简介 spring cloud 为开发人员提供了快速构建分布式系统的一些工具,包括配置管理.服务发现.断路器.路由.微代理.事件总线.全局锁.决策竞选.分布式会话等等.它运 ...

  9. input之按键输入

    通过直接操作驱动来监控键盘,只要程序一旦在后台启动,无论在任何页面都可以监控到按键的数值. 步骤如下: 1.找到键盘挂在点:有两种方法 方法一:在   /dev/input路径下通过  cat eve ...

  10. 2019牛客多校(第十场)F Popping Balloons —— 线段树+枚举

    https://ac.nowcoder.com/acm/contest/890/F 题意:二维平面中有n个气球,你可以横着社三法子弹,竖着射三发子弹,且横着子弹的关系是y,y+r,y+2*r,竖着是x ...