Human Posture Recognition Based on Bidirectional Long Short-Term Memory Neural Network
Huan Huang, Lixin Guo, Shuo Hu · 2021 13th International Symposium on Antennas, Propagation and EM Theory (ISAPE) · 2021
Sensor-based human posture recognition is an important research direction in the field of pattern recognition and plays an important role in many fields. The extracted features will directly affect the accuracy of pattern recognition. In this paper, the posture recognition method based on a Bidirectional Long Short-Term Memory neural network (Bi-LSTM) is designed and validated, the neural network is adopted in this algorithm for extracting features instead of manual extraction. Finally, the accuracy of the algorithm is verified by experimental data. The results show that the posture recognition algorithm constructed by the Bi-LSTM has a high recognition accuracy.