On Neural Inertial Classification Networks for Pedestrian Activity Recognition

Abstract

Inertial sensors are crucial for recognizing pedestrian activity. Recent advances in deep learning have greatly improved inertial sensing performance and robustness. Different domains and platforms use deep-learning techniques to enhance network performance, but there is no common benchmark. The latter is crucial for fair comparison and evaluation within a standardized framework. The aim of this paper is to fill this gap by defining and analyzing ten data-driven techniques for improving neural inertial classification networks. In order to accomplish this, we focused on three aspects of neural networks: network architecture, data augmentation, and data preprocessing. The experiments were conducted across four datasets collected from 78 participants. In total, over 936 minutes of inertial data sampled between 50-200Hz were analyzed. Data augmentation through rotation and multi-head architecture consistently yields the most significant improvements. Additionally, this study outlines benchmarking strategies for enhancing neural inertial classification networks.

arXiv admin note: substantial text overlap with arXiv:2501.01327

References in corpus (7)

• Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks
• Inertial Navigation Meets Deep Learning: A Survey of Current Trends and Future Directions
• Data-Driven Denoising of Stationary Accelerometer Signals
• Data-Driven Meets Navigation: Concepts, Models, and Experimental Validation
• Pedestrian Inertial Navigation: An Overview of Model and Data-Driven Approaches
• Adaptive Attitude Estimation Using a Hybrid Model-Learning Approach
• Enhancement of Neural Inertial Regression Networks: A Data-Driven Perspective