Metraipolis › archive › dc_366a14e40e5f

Signature-Based Feature Learning for Human Activity Recognition: A Reproducible Machine Learning Study of Representation, Depth, and Model Choice — arXiv:2610.06553

Source: arXiv
Original: https://arxiv.org/abs/2610.06553
License (as archived): CC0-1.0
Archived: 2026-10-06T05:25:38.842Z
SHA-256 of the archived text: c1958e405960f98681f6d8bfae9e03995a3802e8bfbe12dda45e5d1e1063667f
Stable URL of this page: https://metraipolis.com/documento/dc_366a14e40e5f

How to cite

Signature-Based Feature Learning for Human Activity Recognition: A Reproducible Machine Learning Study of Representation, Depth, and Model Choice — arXiv:2610.06553 — arXiv, https://arxiv.org/abs/2610.06553 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_366a14e40e5f (Metraipolis archive dc_366a14e40e5f, sha256 c1958e405960f98681f6d8bfae9e03995a3802e8bfbe12dda45e5d1e1063667f)

BibTeX

@misc{dc366a14e40e5f,
  title = {Signature-Based Feature Learning for Human Activity Recognition: A Reproducible Machine Learning Study of Representation, Depth, and Model Choice — arXiv:2610.06553},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06553},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_366a14e40e5f; sha256 c1958e405960f98681f6d8bfae9e03995a3802e8bfbe12dda45e5d1e1063667f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06553. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Human activity recognition (HAR) relies on transforming sensor signals into informative representations for classification. Although deep learning and handcrafted features are widely used, the role of representation itself is often not systematically isolated. Signature transforms provide a mathematically grounded way to encode temporal order and cross-channel interactions, but their value for HAR under a fully reproducible and leakage-aware framework remains unclear. To evaluate whether signature-based feature learning improves HAR performance compared with raw-signal baselines, and to assess the effects of embedding strategy, truncation depth, model choice, and sensor configuration. Experiments were conducted on the UCI HAR dataset using a fully reproducible pipeline with the original train--test split preserved and subject-disjoint validation to prevent leakage. Three representations were compared: raw flattened signals, time-augmented paths, and lead--lag transformed paths. Signature features were computed at multiple truncation depths and evaluated using multilayer perceptron (MLP) and Random Forest (RF) classifiers under identical preprocessing and validation procedures. A prior K-means-based feature reduction study was also reproduced for comparison. Signature-based representations improved performance when paired with RF models, the best configuration was time-augmented six-channel signatures at depth 6 using entropy-based RF achieving 0.858 accuracy and 0.859 macro F1, outperforming the strongest raw baseline (0.816 accuracy). Lead--lag representations were competitive at moderate depths but did not surpass the best time-augmented models. MLP models did not exceed raw baselines. Signature-based feature learning can improve HAR, but its benefit depends on alignment between representation design and classifier choice.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.06553 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:24:05.690Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).