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

There has been a resurgence of applications focused on Human ActivityRecognition (HAR) in smart homes, especially in the field of ambientintelligence and assisted living technologies. However, such applicationspresent numerous significant challenges to any automated analysis systemoperating in the real world, such as variability, sparsity, and noise in sensormeasurements. Although state-of-the-art HAR systems have made considerablestrides in addressing some of these challenges, they especially suffer from apractical limitation: they require successful pre-segmentation of continuoussensor data streams before automated recognition, i.e., they assume that anoracle is present during deployment, which is capable of identifying timewindows of interest across discrete sensor events. To overcome this limitation,we propose a novel graph-guided neural network approach that performs activityrecognition by learning explicit co-firing relationships between sensors. Weaccomplish this by learning a more expressive graph structure representing thesensor network in a smart home, in a data-driven manner. Our approach mapsdiscrete input sensor measurements to a feature space through the applicationof attention mechanisms and hierarchical pooling of node embeddings. Wedemonstrate the effectiveness of our proposed approach by conducting severalexperiments on CASAS datasets, showing that the resulting graph-guided neuralnetwork outperforms the state-of-the-art method for HAR in smart homes acrossmultiple datasets and by large margins. These results are promising becausethey push HAR for smart homes closer to real-world applications.

Know Thy Neighbors: A Graph Based Approach for Effective Sensor-Based Human Activity Recognition in Smart Homes