Application of human motion recognition utilizing deep learning and smart wearable device in sports

The convolutional neural network (CNN) is analyzed in sports motion identification to study human motion recognition based on deep learning and smart wearable devices in sports. First, the convolution feature extraction algorithms are introduced, which include the one-dimensional (1D) convolution feature extraction algorithm, the two-dimensional (2D) convolution feature extraction algorithm, and the combination of the 1D convolution and recurrent neural network (RNN) algorithm. Then, the human motion behavior recognition is studied based on an RNN that includes simple RNN, long short-term memory network (LSTM), bilateral recurrent neural network (BLSTM), and gated recurrent unit (GRU). Finally, the 1D CNN + LSTM algorithm is chosen as the optimal algorithm through experimental analysis and comparison. Meanwhile, two kinds of sensors supported by smart wearable devices are chosen through the above methods, and a network model is constructed for human sports behavior recognition to process data collected through smart wearable devices. Smart wearable devices can operate under any circumstances. Due to low energy consumption and cost, they have been widely used in various sports events. The sensitivity and accuracy of the sensors in the smart wearable devices can be improved through the proposed 1D + LSTM algorithm, promoting their application in various sport events.