INSENGA: Inertial Sensor Gait Recognition Method Using Data Imputation and Channel Attention Weight Redistribution

In the realm of inertial sensor-based gait recognition, data loss during collection, arising from device-related issues or interruptions in the transmission process, introduces complexities for processing. Moreover, extracting identity-distinguishing features for identity recognition encounters challenges due to diverse sensor modalities. To solve those two issues, we propose a method named INSENGA for inertial sensor gait recognition incorporating Multi-GRU variational autoencoding (VAE) data imputation and channel attention weight redistribution (CAWR). INSENGA consists of Multi-GRU VAE and CAWR gait recognition network (CAWR-GRN) two modules. Multi-GRU VAE is introduced to tackle the data loss, in which inertial sensor data of diverse modality are variational autoencoded through separate hybrid CNN and GRU networks and GRU networks are served as decoders to capture temporal features. CAWR-GRN is featured by the CAWR mechanism, which utilizes Expected Channel Damage Matrix (ECDM) to score channel weights, and employs channel attention for weight redistribution to improve gait recognition performance. CAWR-GRN also integrates a hybrid CNN and BLSTM network to capture temporal features and a pre-training network transferring weights to CNNs. To evaluate the performance of INSENGA, experiments are conducted on one self-built dataset and two widely used public datasets. The experimental results show that INSENGA achieved an accuracy of 90.06% on the ID-Sensor dataset, 97.26% on the whuGait #1 dataset, 99.52% on the whuGait #2 dataset, and 93.49% on the OU-ISIR dataset, indicating that INSENGA has reached state-of-the-art gait recognition performance.