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

Human activity recognition (HAR) in ubiquitous computing is beginning toadopt deep learning to substitute for well-established analysis techniques thatrely on hand-crafted feature extraction and classification techniques. Fromthese isolated applications of custom deep architectures it is, however,difficult to gain an overview of their suitability for problems ranging fromthe recognition of manipulative gestures to the segmentation and identificationof physical activities like running or ascending stairs. In this paper werigorously explore deep, convolutional, and recurrent approaches across threerepresentative datasets that contain movement data captured with wearablesensors. We describe how to train recurrent approaches in this setting,introduce a novel regularisation approach, and illustrate how they outperformthe state-of-the-art on a large benchmark dataset. Across thousands ofrecognition experiments with randomly sampled model configurations weinvestigate the suitability of each model for different tasks in HAR, explorethe impact of hyperparameters using the fANOVA framework, and provideguidelines for the practitioner who wants to apply deep learning in theirproblem setting.

Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables