Cross-Frequency Classification of Indoor Activities with DNN Transfer Learning
Cross-Frequency Classification of Indoor Activities with DNN Transfer Learning
复制标题
DOI：
10.1109/radar.2019.8835844
复制
发表时间：
2019-01
期刊：
影响因子：
--
通讯作者：
Aman Shrestha;Corben Murphy;Ivan Johnson;Ajaymehul Anbulselvam;F. Fioranelli;J. Le Kernec;S. Gurbuz
中科院分区：
文献类型：
--
作者：
Aman Shrestha;Corben Murphy;Ivan Johnson;Ajaymehul Anbulselvam;F. Fioranelli;J. Le Kernec;S. Gurbuz
对人体运动和活动的远程、非接触识别是辅助生活设施中健康监测的核心，但目前的系统面临着训练兼容性、训练数据集最少以及不同频率的雷达传感器之间缺乏互操作性等问题。这是第一次考虑深度神经网络(DNN)的有效性和迁移学习，以弥补当多种类型的雷达同时观测人类活动时现象学方面的差距。用5.8 GHz和25 GHz雷达在室内同时记录了6种不同的人类活动。首先，DNN的瓶颈特征性能表明达到了76%的基线。在仅用25 GHz数据训练的模型上，当5.8 GHz数据用于测试时，准确率达到81%。在没有特定频率的雷达的大型数据集的情况下，我们证明来自不同频率的雷达的信息比光学图像更适合于生成分类模型，并且通过使用时间-速度图(TVD)，可以实现一定程度的互操作性。
Remote, non-contact recognition of human motion and activities is central to health monitoring in assisted living facilities, but current systems face the problems of training compatibility, minimal training data sets and a lack of interoperability between radar sensors at different frequencies. This paper represents a first work to consider the efficacy of deep neural networks (DNNs) and transfer learning to bridge the gap in phenomenology that results when multiple types of radars simultaneously observe human activity. Six different human activities are recorded indoors simultaneously with 5.8 GHz and 25 GHz radars. Firstly, the bottleneck feature performance of the DNNs show that a baseline of 76% is achieved. On models trained only with 25 GHz data when 5.8 GHz data is used for testing 81% accuracy is achieved. in absence of a large dataset for radar at a certain frequency, we demonstrate information from a different frequency radar is better suited for generating the classification models than optical images and by using time-velocity diagrams (TVD), a degree of interoperability can be achieved.