自然科学版
陕西师范大学学报(自然科学版)
人工智能专题
融合特征熵的轨迹结构异常检测方法
PDF下载 ()
裴浩然1, 袁冠1,2*, 张艳梅1,2, 李月娥3, 李思宁1
(1 中国矿业大学 计算机科学与技术学院;2 教育部 矿山数字化工程研究中心;3 中国矿业大学 档案馆,江苏 徐州 221116)
袁冠,男,副教授,博士,主要从事时空数据挖掘的研究。E-mail: yuanguan@cumt.edu.cn
摘要:
从轨迹结构特征出发,分析轨迹内部及整体特征,提出融合特征熵的轨迹结构异常检测方法(TSAD-FE,trajectory structure anomaly detection method based on feature entropy)。根据开放角将轨迹划分为轨迹片段,运用线性回归模型对轨迹片段局部特征进行拟合,完成轨迹片段划分;引入轨迹结构框架描述轨迹内部特征属性,应用轨迹结构距离衡量轨迹片段之间的距离,并提出利用熵对特征权重赋值的方法,全面考虑轨迹内部特征对轨迹的影响;运用DBSCAN(density-based spatial clustering of applications with noise)聚类算法将轨迹集划分为若干簇并提取代表轨迹;通过比较轨迹片段与代表轨迹的结构相似度,提取异常轨迹片段,从轨迹整体上考虑异常轨迹片段占比,进而挖掘出异常轨迹。使用多个数据集的实验表明,融合特征熵的轨迹结构异常检测方法能够从轨迹空间形态及内部特征属性上发现异常,可以全面地发现明显异常轨迹及其分段,使检测结果更具有实际意义。
关键词:
熵;轨迹;结构相似度;异常检测;轨迹划分;人工智能
收稿日期:
2019-04-15
中图分类号:
TP391
文献标识码:
A
文章编号:
1672-4291(2019)05-0016-09
基金项目:
国家自然科学基金(71774159);中国博士后基金(2018M642358);绿色安全管理与政策科学智库(2018WHCC03);徐州市科技项目(KC17132)
Doi:
Trajectory structure anomaly detection method based on feature entropy
PEI Haoran1 , YUAN Guan1,2*, ZHANG Yanmei1,2, LI Yuee3, LI Sining1
(1 School of Computer Science and Technology, China University of Mining and Technology;2 Digitization of Mine, Engineering Research Center of Ministry of Education;3 Archives of China University of Mining and Technology, Xuzhou 221116, Jiangsu, China)
Abstract:
At present, the trajectory anomaly detection algorithm is mainly based on the trajectory space shape, ignoring the internal feature information of the trajectory. In this paper, based on the characteristics of trajectory structure, the internal and overall characteristics of trajectory are analyzed, and a trajectory structure anomaly detection method based on feature entropy is proposed. Firstly, the trajectory is divided into trajectory segments according to the opening angle, and the local features of the trajectory segments are fitted by linear regression model to complete the trajectory segment division. Secondly, the trajectory structure framework is introduced to describe the internal characteristic attributes of the trajectory, and the trajectory structure distance is used to measure the distance between trajectory segments. Meanwhile, the method of feature assignment based on entropy is proposed, which comprehensively considers the influence of the internal characteristics of the trajectory. Then, DBSCAN clustering algorithm is used to divide the trajectory set into several clusters and extract representative trajectories. Finally, by comparing the structural similarity between the trajectory segments and the representative trajectories, the abnormal trajectory segments are extracted, and then the abnormal trajectories are excavated as a whole. Experiments using multiple data sets show that the trajectory structure anomaly detection method based on feature entropy can detect information anomaly from the trajectory spatial shape and internal feature attributes. Obvious abnormal trajectories and their segments can be found in an all-round way, which makes the detection results more meaningful.
KeyWords:
entropy; trajectory; structural similarity; anomaly detection; trajectory partition; artificial intelligence