Disentangling Imperfect: A Wavelet-Infused Multilevel Heterogeneous Network for Human Activity Recognition in Flawed Wearable Sensor Data
This addresses the challenge of noisy and incomplete sensor data for human activity recognition, which is important for applications like health monitoring, but the approach appears incremental as it builds on existing deep learning methods with specific architectural improvements.
The paper tackles the problem of human activity recognition from flawed wearable sensor data by proposing a multilevel heterogeneous neural network (MHNN) that uses wavelet decomposition to extract multi-resolution features and suppress noise, achieving state-of-the-art performance on seven public datasets with demonstrated robustness to missing values and noise.
The popularity and diffusion of wearable devices provides new opportunities for sensor-based human activity recognition that leverages deep learning-based algorithms. Although impressive advances have been made, two major challenges remain. First, sensor data is often incomplete or noisy due to sensor placement and other issues as well as data transmission failure, calling for imputation of missing values, which also introduces noise. Second, human activity has multi-scale characteristics. Thus, different groups of people and even the same person may behave differently under different circumstances. To address these challenges, we propose a multilevel heterogeneous neural network, called MHNN, for sensor data analysis. We utilize multilevel discrete wavelet decomposition to extract multi-resolution features from sensor data. This enables distinguishing signals with different frequencies, thereby suppressing noise. As the components resulting from the decomposition are heterogeneous, we equip the proposed model with heterogeneous feature extractors that enable the learning of multi-scale features. Due to the complementarity of these features, we also include a cross aggregation module for enhancing their interactions. An experimental study using seven publicly available datasets offers evidence that MHNN can outperform other cutting-edge models and offers evidence of robustness to missing values and noise. An ablation study confirms the importance of each module.