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

Inertial sensor-based human activity recognition (HAR) is the base of manyhuman-centered mobile applications. Deep learning-based fine-grained HAR modelsenable accurate classification in various complex application scenarios.Nevertheless, the large storage and computational overhead of the existingfine-grained deep HAR models hinder their widespread deployment onresource-limited platforms. Inspired by the knowledge distillation's reasonablemodel compression and potential performance improvement capability, we design amulti-level HAR modeling pipeline called Stage-Logits-Memory Distillation(SMLDist) based on the widely-used MobileNet. By paying more attention to thefrequency-related features during the distillation process, the SMLDistimproves the HAR classification robustness of the students. We also propose anauto-search mechanism in the heterogeneous classifiers to improveclassification performance. Extensive simulation results demonstrate thatSMLDist outperforms various state-of-the-art HAR frameworks in accuracy and F1macro score. The practical evaluation of the Jetson Xavier AGX platform showsthat the SMLDist model is both energy-efficient and computation-efficient.These experiments validate the reasonable balance between the robustness andefficiency of the proposed model. The comparative experiments of knowledgedistillation on six public datasets also demonstrate that the SMLDistoutperforms other advanced knowledge distillation methods of students'performance, which verifies the good generalization of the SMLDist on otherclassification tasks, including but not limited to HAR.

A Light-weight Deep Human Activity Recognition Algorithm Using Multi-knowledge Distillation