Metraipolis › archive › dc_34286cbab943

Anomaly Detection on Resource-Constrained Devices with Reservoir Computing — arXiv:2611.04835

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04835
License (as archived)
CC0-1.0
Archived
2026-11-04T21:51:47.425Z
SHA-256 of the archived text
a55bcee070676cd038a90dde1ccacfa84d35c4097a3677fc380eab9a922e6771
Stable URL of this page
https://metraipolis.com/documento/dc_34286cbab943

How to cite

Anomaly Detection on Resource-Constrained Devices with Reservoir Computing — arXiv:2611.04835 — arXiv (en), https://arxiv.org/abs/2611.04835 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_34286cbab943 (Metraipolis archive dc_34286cbab943, sha256 a55bcee070676cd038a90dde1ccacfa84d35c4097a3677fc380eab9a922e6771)
BibTeX
@misc{dc34286cbab943,
  title = {Anomaly Detection on Resource-Constrained Devices with Reservoir Computing — arXiv:2611.04835},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04835},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_34286cbab943; sha256 a55bcee070676cd038a90dde1ccacfa84d35c4097a3677fc380eab9a922e6771},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04835. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Anomaly detection at the edge requires the deployment of models that achieve competitive performance, while minimizing computational cost and memory footprint. In this article, we investigate the suitability of the Mahalanobis Distance of Reservoir States (MDRS), an unsupervised time-series anomaly detection method, for resource-constrained devices and propose two optimizations to reduce its computational requirements. Specifically, we replace random reservoir connectivity (MDRS-Rand) with a circular shift (MDRS-Circ) and show that the anomaly score for an entire time series can be computed from the final reservoir state alone. Furthermore, we show that exploiting the reservoir's temporal memory enables more efficient input preprocessing, further reducing computational cost. We evaluate the MDRS variants on the MLPerf Tiny anomaly detection benchmark against the reference autoencoder and other anomaly detection methods, and deploy their inference kernels on a NUCLEO-F401RE microcontroller to assess latency, estimate energy consumption, and measure memory footprint. Among the evaluated methods, only MDRS and the autoencoder meet the benchmark's performance target, with MDRS requiring fewer operations and smaller models. With optimized preprocessing, MDRS achieves an ROC AUC of 0.869, a model size of 24 KB, an estimated energy consumption of 24 uJ per inference, and a latency of 0.32 ms, corresponding to a 75.9x speedup over the autoencoder with standard preprocessing.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.04835 — 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 2026-11-04T21:38:49.735Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).