English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Timeseries partitioning is an essential step in most machine-learning driven,sensor-based IoT applications. This paper introduces a sample-efficient,robust, time-series segmentation model and algorithm. We show that by learninga representation specifically with the segmentation objective based on maximummean discrepancy (MMD), our algorithm can robustly detect time-series eventsacross different applications. Our loss function allows us to infer whetherconsecutive sequences of samples are drawn from the same distribution (nullhypothesis) and determines the change-point between pairs that reject the nullhypothesis (i.e., come from different distributions). We demonstrate itsapplicability in a real-world IoT deployment for ambient-sensing based activityrecognition. Moreover, while many works on change-point detection exist in theliterature, our model is significantly simpler and can be fully trained in 9-93seconds on average with little variation in hyperparameters for data acrossdifferent applications. We empirically evaluate Cadence on four popular changepoint detection (CPD) datasets where Cadence matches or outperforms existingCPD techniques.

Cadence: A Practical Time-series Partitioning Algorithm for Unlabeled IoT Sensor Streams