T-WaveNet: Tree-Structured Wavelet Neural Network for Sensor-Based Time Series Analysis
This work provides a more effective representation for sensor information, which is important for applications like activity recognition and brain-computer interfaces, offering strong specific gains over existing DNN-based techniques.
This paper proposes T-WaveNet, a novel tree-structured wavelet neural network for sensor-based time series analysis. It decomposes input signals into frequency subbands and uses invertible neural networks for wavelet transforms, achieving state-of-the-art performance on various sensor datasets including UCI-HAR and OPPORTUNITY.
Sensor-based time series analysis is an essential task for applications such as activity recognition and brain-computer interface. Recently, features extracted with deep neural networks (DNNs) are shown to be more effective than conventional hand-crafted ones. However, most of these solutions rely solely on the network to extract application-specific information carried in the sensor data. Motivated by the fact that usually a small subset of the frequency components carries the primary information for sensor data, we propose a novel tree-structured wavelet neural network for sensor data analysis, namely \emph{T-WaveNet}. To be specific, with T-WaveNet, we first conduct a power spectrum analysis for the sensor data and decompose the input signal into various frequency subbands accordingly. Then, we construct a tree-structured network, and each node on the tree (corresponding to a frequency subband) is built with an invertible neural network (INN) based wavelet transform. By doing so, T-WaveNet provides more effective representation for sensor information than existing DNN-based techniques, and it achieves state-of-the-art performance on various sensor datasets, including UCI-HAR for activity recognition, OPPORTUNITY for gesture recognition, BCICIV2a for intention recognition, and NinaPro DB1 for muscular movement recognition.