• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>NAFOSTED Conference on Information and Computer Science >Systematic Evaluation of Deep Learning Models for Human Activity Recognition Using Accelerometer
【24h】

Systematic Evaluation of Deep Learning Models for Human Activity Recognition Using Accelerometer

机译：使用加速度计对人类活动识别深层学习模型的系统评价

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Human Activity Recognition (HAR) based on data from wearable sensors has become an attractive research topic thanks to its applications in different fields such as healthcare and smart environments. Recently, the advancement of deep learning with capability to perform automatically high-level feature extraction has achieved promising results. However, the performance of the deep learning models depends deeply on the characteristics of the datasets such as the number of classes, the inter-similarity and intra-variation. Therefore, directly comparing these models has become difficult since a wide variety of experimental protocols, evaluation metrics, and datasets are employed. In this paper, for the first time, a systematic evaluation of several deep learning models for HAR from wearable sensors is provided. In particular, three models named Convolutional Neural Network (CNN) [1], DeepConvLSTM - a combination of CNN and Long Short Term Memory (LSTM) [2], and SensCapsNet - a Capsule Neural Network for wearable sensor-based HAR [3] were implemented and evaluated on three benchmark datasets that are 19NonSens, CMDFall, and UCI-HAR dataset. Moreover, to have an intuitive explanation of deep learning models, a visualization of features learnt from these models is given. The evaluation codebase and results will be made publicly available for community use.
机译：基于来自可穿戴传感器的数据的人类活动识别（HAR）已成为一种有吸引力的研究课题，因为它在不同领域的应用程序，如医疗保健和智能环境。最近，深入学习的进步与能够进行自动高级别特征提取取得了有希望的结果。然而，深度学习模型的性能深深地取决于数据集的特征，例如类别数量，相互相互作用和帧内变化。因此，由于采用了各种实验协议，评估度量和数据集，因此直接比较这些模型变得困难。本文首次提供了从可穿戴传感器的钩子的几个深层学习模型的系统评估。特别是，三个模型名为卷积神经网络（CNN）[1]，DeepConvlstm - CNN和长短期内存（LSTM）[2]的组合，以及Senscapsnet - 一种用于基于可穿戴传感器的Har [3]的胶囊神经网络[3]在19nonsens，cmdfall和UCI-Har DataSet上实现并评估了三个基准数据集。此外，为了对深度学习模型进行直观的解释，给出了从这些模型中学到的特征的可视化。评估码库和结果将公开可供社区使用。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号