面向智能感知活动识别的混合神经网络模型

Hybrid Neural Network Model for Smart Sensing Activity Recognition

人类活动识别(HAR)任务传统上使用人工提取的特征和一些浅层机器学习模型,但该方法限制较多。利用深度神经网络自动提取特征的能力,结合最近取得巨大成功的递归神经网络和卷积神经网络,提出了一种新颖的混合神经网络(HybridSense)模型,并在真实数据集上对模型进行了性能评估。试验结果表明,该模型在动作识别任务方面性能得到了显著提升。

Human activity recognition (HAR) tasks traditionally use some features artificially extracted and some shallow machine learning models,but the approach has many restrictions.Utilizing the feature automatically extracting ability of the deep neural network,combined with the recent successful recurrent neural network and the convolutional neural network,a novel hybrid neural network model (HybridSense) is proposed.The performance of the model is evaluated on a real data set.The results show that the performance of the model on HAR tasks is obviously enhanced.