融合多尺度卷积和BiGRU网络的人类活动识别模型  

Human activity recognition model based on multi-scale convolution and BiGRU network

作　　者：魏雄[1] 王子樊 WEI Xiong;WANG Zifan(School of Computer Science and Artificial Intelligence,Wuhan Textile University,Wuhan Hubei 430200,China)

机构地区：[1]武汉纺织大学计算机与人工智能学院,武汉430200

出　　处：《计算机应用》2023年第S02期72-76,共5页journal of Computer Applications

摘　　要：基于深度学习的人类活动识别(HAR)方法在处理时间序列数据时存在手工特征提取过程复杂、复杂时序依赖性难以挖掘问题,如何有效自动提取人类活动的多尺度特征并挖掘时序前后的关联性特征,是提高HAR准确率的关键因素。为解决上述问题,提出一种多尺度一维卷积-双向门控循环单元(1DMCNN-BiGRU)模型。使用多尺度卷积提取精细化感知信号特征,同时融合双向门控循环单元(BiGRU)提取的前后整体信号的相关性特征,从而提高模型的识别准确率。在真实场景数据集USC-HAD、WISDM、PAMAP2上的实验结果表明,相较于次优的CNN-LSTM(Convolutional Neural Network with Long Short-Term Memory)模型,所提模型的识别准确率分别提高了1.06%、1.23%和1.71%,具有较高的识别准确度,验证了所提模型用于HAR的有效性。Deep learning based HAR(Human Activity Recognition)methods suffer from the complexity of manual feature extraction process and the difficulty of mining complex time-series dependencies when dealing with time-series data.How to effectively and automatically extract multi-scale features of human activities and mine the correlation features of time series is the key factor to improve the accuracy of HAR.To address the above issues,a Multi-scale one-Dimensional Convolutional Neural Network Bidirectional Gated Recurrent Unit(1DMCNN BiGRU)model was proposed.Refined perceptual signal features were extracted by multi-scale convolution,while correlation features of the overall signal before and after extracted by BiGRU(Bidirectional Gated Recurrent Unit)were fused to improve the recognition accuracy of the model.Experimental results on real-life scene datasets USC-HAD,WISDM,and PAMAP2 show that compared to the suboptimal CNN-LSTM(Convolutional Neural Network with Long Short-Term Memory)model,the proposed model has improved the recognition accuracy by 1.06%,1.23% and 1.71%,respectively,with high recognition accuracy,which verifies the effectiveness of the proposed model for HAR.

关 键 词：特征提取 卷积神经网络 双向门控循环单元 人类活动识别 深度学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]