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

We introduce GeXSe (Generative Explanatory Sensor System), a novel frameworkdesigned to extract interpretable sensor-based and vision domain features fromnon-invasive smart space sensors. We combine these to provide a comprehensiveexplanation of sensor-activation patterns in activity recognition tasks. Thissystem leverages advanced machine learning architectures, including transformerblocks, Fast Fourier Convolution (FFC), and diffusion models, to provide a moredetailed understanding of sensor-based human activity data. A standout featureof GeXSe is our unique Multi-Layer Perceptron (MLP) with linear, ReLU, andnormalization layers, specially devised for optimal performance on smalldatasets. It also yields meaningful activation maps to explain sensor-basedactivation patterns. The standard approach is based on a CNN model, which ourMLP model outperforms.GeXSe offers two types of explanations: sensor-basedactivation maps and visual domain explanations using short videos. Thesemethods offer a comprehensive interpretation of the output fromnon-interpretable sensor data, thereby augmenting the interpretability of ourmodel. Utilizing the Frechet Inception Distance (FID) for evaluation, itoutperforms established methods, improving baseline performance by about 6\%.GeXSe also achieves a high F1 score of up to 0.85, demonstrating precision,recall, and noise resistance, marking significant progress in reliable andexplainable smart space sensing systems.

GeXSe (Generative Explanatory Sensor System): An Interpretable Deep Generative Model for Human Activity Recognition in Smart Spaces