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

In this work, we propose an open-source scalable end-to-end RTL frameworkFieldHAR, for complex human activity recognition (HAR) from heterogeneoussensors using artificial neural networks (ANN) optimized for FPGA or ASICintegration. FieldHAR aims to address the lack of apparatus to transformcomplex HAR methodologies often limited to offline evaluation to efficientrun-time edge applications. The framework uses parallel sensor interfaces andinteger-based multi-branch convolutional neural networks (CNNs) to supportflexible modality extensions with synchronous sampling at the maximum rate ofeach sensor. To validate the framework, we used a sensor-rich kitchen scenarioHAR application which was demonstrated in a previous offline study. Throughresource-aware optimizations, with FieldHAR the entire RTL solution was createdfrom data acquisition to ANN inference taking as low as 25\% logic elements and2\% memory bits of a low-end Cyclone IV FPGA and less than 1\% accuracy lossfrom the original FP32 precision offline study. The RTL implementation alsoshows advantages over MCU-based solutions, including superior data acquisitionperformance and virtually eliminating ANN inference bottleneck.

FieldHAR: A Fully Integrated End-to-end RTL Framework for Human Activity Recognition with Neural Networks from Heterogeneous Sensors