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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This work proposes a low-power high-accuracy embedded hand-gesturerecognition algorithm targeting battery-operated wearable devices using lowpower short-range RADAR sensors. A 2D Convolutional Neural Network (CNN) usingrange frequency Doppler features is combined with a Temporal ConvolutionalNeural Network (TCN) for time sequence prediction. The final algorithm has amodel size of only 46 thousand parameters, yielding a memory footprint of only92 KB. Two datasets containing 11 challenging hand gestures performed by 26different people have been recorded containing a total of 20,210 gestureinstances. On the 11 hand gesture dataset, accuracies of 86.6% (26 users) and92.4% (single user) have been achieved, which are comparable to thestate-of-the-art, which achieves 87% (10 users) and 94% (single user), whileusing a TCN-based network that is 7500x smaller than the state-of-the-art.Furthermore, the gesture recognition classifier has been implemented on aParallel Ultra-Low Power Processor, demonstrating that real-time prediction isfeasible with only 21 mW of power consumption for the full TCN sequenceprediction network, while a system-level power consumption of less than 100 mWis achieved. We provide open-source access to all the code and data collectedand used in this work on tinyradar.ethz.ch.

TinyRadarNN: Combining Spatial and Temporal Convolutional Neural Networks for Embedded Gesture Recognition with Short Range Radars