<ul><li>Researchers propose a universal attention feature purification mechanism (MSAP) for Human Activity Recognition (HAR).</li><li>The mechanism effectively reduces feature redundancy caused by multi-scale features in wearable devices.</li><li>A network correction module is designed to mitigate inherent problems in deep networks.</li><li>Experiments show that the proposed method model effectively reduces redundant features with little resource consumption.</li></ul>

Redundant feature screening method for human activity recognition based on attention purification mechanism

Discover more