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

arXiv: https://arxiv.org/abs/2503.23537 · HTML: https://mlsanity.com/paper/2503.23537/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 33 references that are in the map.
- First posted on arXiv 30 Mar 2025.

## Builds on (most cited first, 10 of 10)

- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Human Action Recognition from Various Data Modalities: A Review](https://mlsanity.com/paper/2012.11866/) (2020)
- [Deep Learning for Sensor-based Activity Recognition: A Survey](https://mlsanity.com/paper/1707.03502/) (2017)
- [Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities](https://mlsanity.com/paper/2001.07416/) (2020)
- [Ensembles of Deep LSTM Learners for Activity Recognition using Wearables](https://mlsanity.com/paper/1703.09370/) (2017)
- [Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention](https://mlsanity.com/paper/1810.04038/) (2018)
- [DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors](https://mlsanity.com/paper/2006.14435/) (2020)
- [TransSleep: Transitioning-aware Attention-based Deep Neural Network for Sleep Staging](https://mlsanity.com/paper/2203.12590/) (2022)
- [Gated Res2Net for Multivariate Time Series Analysis](https://mlsanity.com/paper/2009.11705/) (2020)

## Abstract (arXiv)

In the field of sensor-based Human Activity Recognition (HAR), deep neural networks provide advanced technical support. Many studies have proven that recognition accuracy can be improved by increasing the depth or width of the network. However, for wearable devices, the balance between network performance and resource consumption is crucial. With minimum resource consumption as the basic principle, we propose a universal attention feature purification mechanism, called MSAP, which is suitable for multi-scale networks. The mechanism effectively solves the feature redundancy caused by the superposition of multi-scale features by means of inter-scale attention screening and connection method. In addition, we have designed a network correction module that integrates seamlessly between layers of individual network modules to mitigate inherent problems in deep networks. We also built an embedded deployment system that is in line with the current level of wearable technology to test the practical feasibility of the HAR model, and further prove the efficiency of the method. Extensive experiments on four public datasets show that the proposed method model effectively reduces redundant features in filtered data and provides excellent performance with little resource consumption.