首页> 美国卫生研究院文献>Data in Brief >Multi-sensor dataset of human activities in a smart home environment
【2h】

Multi-sensor dataset of human activities in a smart home environment

机译:智能家居环境中的人类活动多传感器数据集

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

Time series data acquired from sensors deployed in smart homes present valuable information for intelligent systems to learn activity patterns of occupants. With the increasing need to enable people to age in place independently, the availability of such data is key to the development of home monitoring solutions. In this article we describe an unlabelled dataset of measurements collected from multiple environmental sensors placed in a smart home to capture human activities of daily living. Various sensors were used including passive infrared, force sensing resistors, reed switches, mini photocell light sensors, temperature and humidity, and smart plugs. The sensors record data from the user’s interactions with the environment, such as indoor movements, pressure applied on the bed, or current consumption when using electrical appliances. Millions of raw sensor data samples were collected continuously at a frequency of 1 Hz over a period of six months between 26 February 2020 and 26 August 2020. The dataset can be useful in the analysis of different methods, including data-driven algorithms for activity or habit recognition. In particular, the research community might be interested in investigating the performance of algorithms when applied on unlabelled datasets and not necessarily on annotated datasets. Furthermore, by applying artificial intelligence (AI) algorithms on such data collected over long periods, it is possible to extract patterns that reveal the user’s habits as well as detect changes in the habits. This can benefit in detecting deviations in order to provide timely interventions for patients, e.g., people with dementia.
机译:从智能房屋中部署的传感器获取的时间序列数据为智能系统提供了有价值的信息,以学习占用者的活动模式。随着人们越来越需要独立地到位,这些数据的可用性是家庭监控解决方案发展的关键。在本文中,我们描述了从位于智能家居的多个环境传感器中收集的测量的未标记数据集,以捕获日常生活的人类活动。使用各种传感器包括被动红外,力传感电阻,簧片开关,迷你光电池光传感器,温度和湿度和智能插头。传感器记录来自用户与环境的相互作用的数据,例如室内运动,在床上施加的压力,或使用电器时的电流消耗。在2020年2月26日和2020年8月26日期间,在六个月的六个月内连续收集数百万原始传感器数据样本。数据集可用于分析不同方法,包括用于活动的数据驱动算法或习惯认可。特别是,研究社区可能有兴趣在在未标记的数据集上应用时调查算法的性能,而不一定在注释数据集上。此外,通过在长期收集的这些数据上应用人工智能(AI)算法,可以提取揭示用户习惯的模式以及检测习惯的变化。这可以有利于检测偏差,以便为患者提供及时的干预患者,例如患有痴呆症的人。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

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