arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.10185cs.LGeess.SP
收藏

人类活动识别中的迁移学习:综述

Transfer Learning in Human Activity Recognition: A Survey

Georgia Institute of Technology(佐治亚理工学院)

Sourish Gunesh Dhekane, Thomas Ploetz

AI总结:

本文综述了智能家居和可穿戴设备场景下基于传感器的人类活动识别中的迁移学习方法,从问题-解决方案视角分类现有工作,分析205篇论文并指出研究空白与未来路线图。

摘要:

基于传感器的人类活动识别(HAR)一直是一个活跃的研究领域,因为它在智能环境、辅助生活、健身、医疗保健等方面具有广泛应用。近年来,基于深度学习的端到端训练在计算机视觉和自然语言等领域取得了最先进的性能,而这些领域拥有大量标注数据。然而,基于传感器的HAR并不具备大量标注数据。此外,执行HAR的真实世界环境在传感器模态、分类任务和目标用户方面存在差异。为了解决这一问题,迁移学习已被广泛采用。在本综述中,我们重点关注智能家居和基于可穿戴设备的HAR应用领域中的迁移学习方法。特别地,我们通过按贡献及其所解决的挑战对工作进行分类和呈现,提供了一种问题-解决方案视角。我们还呈现了两个应用领域最新技术水平的最新视图。基于对205篇论文的分析,我们指出了文献中的空白,并提供了解决这些空白的路线图。本综述通过总结现有工作并提出有前景的研究议程,为HAR社区提供了参考。

英文摘要:

Sensor-based human activity recognition (HAR) has been an active research area, owing to its applications in smart environments, assisted living, fitness, healthcare, etc. Recently, deep learning based end-to-end training has resulted in state-of-the-art performance in domains such as computer vision and natural language, where large amounts of annotated data are available. However, large quantities of annotated data are not available for sensor-based HAR. Moreover, the real-world settings on which the HAR is performed differ in terms of sensor modalities, classification tasks, and target users. To address this problem, transfer learning has been employed extensively. In this survey, we focus on these transfer learning methods in the application domains of smart home and wearables-based HAR. In particular, we provide a problem-solution perspective by categorizing and presenting the works in terms of their contributions and the challenges they address. We also present an updated view of the state-of-the-art for both application domains. Based on our analysis of 205 papers, we highlight the gaps in the literature and provide a roadmap for addressing them. This survey provides a reference to the HAR community, by summarizing the existing works and providing a promising research agenda.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑