Litcius/Paper detail

Attention-Augmented Convolutional Autoencoder for Radar-Based Human Activity Recognition

Christopher Campbell, Fauzia Ahmad

202023 citationsDOI

Abstract

We propose an attention-augmented convolutional autoencoder for human activity recognition using radar micro-Doppler signatures. We use attention to overcome the limited receptive field of convolutional autoencoders (CAE), thereby enabling them to learn global information in addition to spatially localized features, while preserving their unsupervised pretraining characteristic. The augmentation is accomplished by concatenating convolutional local-feature maps with a set of attention feature maps that capture global dependencies. Using real data measurements of falls and activities of daily living, we demonstrate that the incorporation of the attention mechanism yields superior classification accuracy with respect to training sample size, compared to the conventional CAE.

Topics & Concepts

AutoencoderArtificial intelligenceComputer sciencePattern recognition (psychology)Convolutional neural networkFeature (linguistics)Deep learningRadarFeature extractionFeature learningData setDoppler radarConvolutional codeSet (abstract data type)Field (mathematics)MathematicsAlgorithmPhilosophyProgramming languageTelecommunicationsLinguisticsPure mathematicsDecoding methodsAdvanced SAR Imaging TechniquesGait Recognition and AnalysisRadar Systems and Signal Processing
Attention-Augmented Convolutional Autoencoder for Radar-Based Human Activity Recognition | Litcius