BriefGPT.xyz
Nov, 2023
异常检测的设备特征
Set Features for Anomaly Detection
HTML
PDF
Niv Cohen, Issar Tzachor, Yedid Hoshen
TL;DR
本文提出了一种用于检测由正常元素组合而成的样本中异常的集合特征。通过使用简单的密度估计方法，我们计算每个样本的异常分数，进而克服了先前图像级逻辑异常检测和序列级时间序列异常检测方法的限制。
Abstract
This paper proposes
set features
for detecting anomalies in samples that consist of
unusual combinations
of normal elements. Many leading methods discover anomalies by detecting an unusual part of a sample. For e
→