Skip to main content

Smoothing Point Adjustment-based Evaluation of Time Series Anomaly Detection

Mingyu Liu ("National University of Defense Technology, China"); Yijie Wang (" National University of Defense Technology, China"); Hongzuo Xu (National University of Defense Technology); Xiaohui Zhou (National University of Defense Technology); Bin Li (National University of Defense Technology); Yongjun Wang (College of Computer, National University of Defense Technology)

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
07 Jun 2023

Anomalies in time series appear consecutively, forming anomaly segments. Applying the classical point-based evaluation metrics to evaluate the detection performance of segments leads to considerable underestimation, so most related studies resort to point adjustment. This operation treats all points as true positives within a segment equally when only one individual point alarms, resulting in significant overestimation and creating an illusion of superior performance. This paper proposes smoothing point adjustment, a novel range-based evaluation protocol for time series anomaly detection. Our protocol reflects detection performance impartially by carefully considering the specific location and frequency of alarms in the raw results. It is achieved by smoothly determining the adjustment range and rewarding early detection via a ranging function and a rewarding function. Compared with other evaluation metrics, experiments on different datasets show that our protocol can yield a performance ranking of various methods more consistent with the desired situation.

More Like This

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00