计算机应用 ›› 2019, Vol. 39 ›› Issue (6): 1614-1618.DOI: 10.11772/j.issn.1001-9081.2018112281

• 人工智能 • 上一篇    下一篇

模型聚合解聚的智能触发机制

宁进1,2,3, 陈雷霆1,2,3, 周川1,2,3, 张磊1,2,3   

  1. 1. 电子科技大学 计算机科学与工程学院, 成都 611731;
    2. 数字媒体技术四川省重点实验室(电子科技大学), 成都 611731;
    3. 电子科技大学 广东电子信息工程研究院, 广东 东莞 523808
  • 收稿日期:2018-11-15 修回日期:2018-12-20 出版日期:2019-06-10 发布日期:2019-06-17
  • 通讯作者: 宁进
  • 作者简介:宁进(1991-),女,四川成都人,博士研究生,主要研究方向:离群点检测、数据挖掘;陈雷霆(1966-),男,四川成都人,教授,博士,主要研究方向:图像处理、计算机图形、虚拟现实;周川(1977-),男,四川成都人,讲师,博士,主要研究方向:计算机动画、机器视觉、医学图像分析、数据挖掘;张磊(1986-),男,重庆人,博士研究生,主要研究方向:深度学习、图形学、跨媒体检索。
  • 基金资助:
    广东省应用型科技研发专项资金资助项目(2015B010131002);东莞市重大科技项目(2015215102);广东省科技计划项目(2016A040403004)。

Intelligent trigger mechanism for model aggregation and disaggregation

NING Jin1,2,3, CHEN Leiting1,2,3, ZHOU Chuan1,2,3, ZHANG Lei1,2,3   

  1. 1. School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu Sichuan 611731, China;
    2. Digital Media Technology Key Laboratory of Sichuan Province(University of Electronic Science and Technology of China), Chengdu Sichuan 611731, China;
    3. Institute of Electronic and Information Engineering in Guangdong, University of Electronic Science and Technology of China, Dongguan Guangdong 523808, China
  • Received:2018-11-15 Revised:2018-12-20 Online:2019-06-10 Published:2019-06-17
  • Supported by:
    This work is partially supported by the Special Found for Research and Development of Application-Oriented Science and Technology of Guangdong Province (2015B010131002), the Major Science and Technology Project of Dongguan (2015215102), the Science and Technology Planning Project of Guangdong Province (2016A040403004).

摘要: 针对现有模型聚合解聚(AD)触发机制人工依赖性高、频繁聚合解聚的问题,提出了一种基于关注域的多实体时序离群点检测算法的智能触发机制。首先,基于关注近邻划分关注域;然后,计算关注域中实体的k距离离群值,得到关注域的离群值;最后,结合一种基于最强关注域阈值判定方法,构建聚合解聚触发机制。在真实数据集上的实验结果表明,与传统的单实体时序离群点检测算法相比,所提算法在指标Precision、Recall和综合指标F1-score上均提升了10个百分点以上,不仅能及时地判断聚合解聚操作的触发时机,而且能使得仿真系统智能地检测出发生突发情况的仿真实体,满足了多分辨率建模的要求。

关键词: 聚合解聚, 触发机制, 时序离群点检测, k距离, 多分辨率建模

Abstract: Aiming at high manual dependence and frequent Aggregation and Disaggregation (AD) of existing model AD trigger mechanisms, an intelligent trigger mechanism based on focus-area multi-entity temporal outlier detection algorithm was proposed. Firstly, the focus-areas were divided based on attention neighbors. Secondly, the outlier score of focus-area was obtained by calculating the k-distance outlier score of entities in a focus-area. Finally, a trigger mechanism for AD was constructed based on strongest-focus-area threshold decision method. The experimental results on real dataset show that, compared with the traditional single-entity temporal outlier detection algorithms, the proposed algorithm improves the performance of Precision, Recall and F1-score by more than 10 percentage points. The proposed algorithm can not only judge the trigger time of the AD operation in time, but also enable the simulation system to intelligently detect the simulation entities with emergency situation and meet the requirements of multi-resolution modeling.

Key words: aggregation and disaggregation, trigger mechanism, temporal outlier detection, k-distance, multi-resolution modeling

中图分类号: