基于融合注意力机制与CNN-LSTM的人体行为识别算法

为解决单一的卷积神经网络（CNN）缺乏利用时序信息与单一循环神经网络（RNN）对局部信息把握不全问题，提出了融合注意力机制与时空网络的深度学习模型（CLA-net）的人体行为识别方法。首先，通过CNN的强学习能力提取局部特征；其次，利用长短时记忆网络（LSTM）提取时序信息；再次，运用注意力机制获取并优化最重要的特征；最后使用softmax分类器对识别结果进行分类。仿真实验结果表明，CLA-net模型在UCI HAR和DaLiAc数据集上的准确率分别达到95.35%、99.43%，F1值分别达到95.35%、99.43%，均优于对比实验模型，有效提高了识别精度。

Human Action Recognition Based on fusion of Attention Mechanism and CNN-LSTM

In order to solve the problem that a single convolutional neural network (CNN) lacks the use of sequential information and a single recurrent neural network (RNN) cannot fully grasp the local information, a deep learning model (CLA-net) that integrates attention mechanism and spatiotemporal network is proposed for human activity recognition. First, the local features are extracted by the strong learning ability of CNN. Secondly, the temporal sequence information is extracted by using the long short-term memory network (LSTM). Thirdly, the most important features are obtained and optimized by the attention mechanism, and finally use the softmax classifier to classify the recognition results. The simulation results show that the accuracy of CLA-NET model on UCI HAR and DaLiAc data sets reaches 95.35% and 99.43% respectively, and the F1 value reaches 95.35% and 99.43% respectively. All of them are better than the comparative experimental model proposed in this paper, and the recognition accuracy is effectively improved.