摘要
对由可穿戴设备采集的针对人体活动识别的数据集进行处理,并用处理后的数据对一维卷积神经网络进行训练,测试并得到精准度结果.对数据集的处理使得原本数据集中一些噪音和无效数据被过滤排除掉,在训练神经网络时减少了运算量,提升了神经网络的效率.后经测试,在神经网络结构不变的情况下,处理后的数据集可以使神经网络性能得到提升.
The data set for human activity recognition collected by the wearable device was processed,and the processed data was used to train a one-dimensional convolutional neural network to test and obtain accuracy results.The processing of the data set allows some noise and invalid data in the original data set to be filtered out,which reduced the amount of calculation and improved the efficiency of the neural network when training the neural network.After testing,under the condition that the structure of the neural network was unchanged,the processed data set can improve the performance of the neural network.
作者
钟楚轶
朱建军
ZHONG Chuyi;ZHU Jianjun(Changchun Boli Electronic Technology Co.,LTd.,Changchun 130012,China;School of Information and Control Engineering,Jilin Institute of Chemical Technology,Jilin City 132022,China)
出处
《吉林化工学院学报》
CAS
2020年第3期81-84,共4页
Journal of Jilin Institute of Chemical Technology
关键词
数据集处理
卷积神经网络
人体活动识别
dataset processing
concolutional neural network
human activity recognitio
