review: PCA-based anomaly detection

最新推荐文章于 2024-11-12 20:45:11 发布

朗泰乐

最新推荐文章于 2024-11-12 20:45:11 发布

阅读量191

点赞数 1

分类专栏：数学文章标签： pca降维机器学习

原文链接：https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/pca-based-anomaly-detection

版权

数学专栏收录该内容

3 篇文章 1 订阅

订阅专栏

本文介绍 Principal Component Analysis (PCA) 在数据探索和异常检测中的关键作用。通过分析多变量数据，PCA揭示变量间的关联，构建主成分来压缩特征空间。新的输入通过投影和重建误差判断异常程度，高误差表示实例越异常。

摘要由CSDN通过智能技术生成

Transfered from: https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/pca-based-anomaly-detection

Principal Component Analysis, which is frequently abbreviated to PCA, is an established technique in machine learning. PCA is frequently used in exploratory data analysis because it reveals the inner structure of the data and explains the variance in the data.

PCA works by analyzing data that contains multiple variables. It looks for correlations among the variables and determines the combination of values that best captures differences in outcomes. These combined feature values are used to create a more compact feature space called the principal components.

For anomaly detection, each new input is analyzed, and the anomaly detection algorithm computes its projection on the eigenvectors, together with a normalized reconstruction error.(???) The normalized error is used as the anomaly score. The higher the error, the more anomalous the instance is.