摘要
使用4种类型的循环神经网络模型(RNN、GRU、LSTM、BLSTM)处理手机传感器采集的异构时间序列数据,用于人体行为识别研究.针对4种模型,分别构建自动特征提取方法,并对参数设置进行优化.在公开数据集UCI HAR上进行了行为识别测试实验,实验结果表明,BLSTM模型的识别精度高达95.7%,可以有效地用于行为识别,其识别率和性能优于其他3种循环神经网络,且高于卷积神经网络深度学习方法.
Four recurrent neural network models(RNN,GRU,LSTM and BLSTM)are selected to process heterogeneous time series data collected by mobile phone sensors for human behavior recognition research.For the four models,an automatic feature extraction method is constructed respectively and their parameter settings are optimized.The behavior recognition test experiment is carried out on the public data set of UCI HAR.The experimental results show that the accuracy of BLSTM model is as high as 95.7%,which can be effectively used for behavior recognition.The recognition rate and performance of BLSTM is not only far higher than the other three models,but also higher than the existing deep learning method of the convolutional neural network.
作者
宿通通
孙华志
马春梅
姜丽芬
SU Tongtong;SUN Huazhi;MA Chunmei;JIANG Lifen(College of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China)
出处
《天津师范大学学报(自然科学版)》
CAS
北大核心
2018年第6期58-62,76,共6页
Journal of Tianjin Normal University:Natural Science Edition
基金
国家自然科学基金资助项目(61702370)
天津市国际科技合作资助项目(14RCGFGX00847)
天津市自然科学基金资助(17JCYBJC16400)
天津市科技计划资助项目(17ZLZXZF00530)
天津师范大学131三层次人选资助项目(043/135305QS20)
天津师范大学博士基金资助项目(043/135202XB1615
043/135202XB1705)
关键词
行为识别
时序数据
循环神经网络
BLSTM
behavior recognition
time series data
recurrent neural network
BLSTM