Part II: Classical Signal Processing and Feature Engineering
Chapter 8  [C]

Feature Engineering and Dimensionality Reduction

Placeholder chapter page. Sections are produced by the book-skills pipeline.

Sections

  1. 8.1 Time-domain features
  2. 8.2 Frequency- and time-frequency features
  3. 8.3 Statistical, shape, and entropy features
  4. 8.4 Domain-specific feature libraries (tsfresh, catch22)
  5. 8.5 Feature selection
  6. 8.6 PCA, ICA, and manifold methods (UMAP, t-SNE) for sensors
  7. 8.7 When handcrafted features still beat deep learning

Lab 8

build a feature-based activity/condition classifier; compare against a small neural baseline and analyze where each wins.