使用惯性、生理和环境传感器的人类活动识别：全面综述。
Human Activity Recognition using Inertial, Physiological and Environmental Sensors: A Comprehensive Survey.
作者信息
Demrozi Florenc, Pravadelli Graziano, Bihorac Azra, Rashidi Parisa
机构信息
Department of Computer Science, University of Verona, Italy.
Division of Nephrology, Hypertension, & Renal Transplantation, College of Medicine, University of Florida, Gainesville, FL, USA.
出版信息
IEEE Access. 2020;8:210816-210836. doi: 10.1109/access.2020.3037715. Epub 2020 Nov 16.
Abstract
In the last decade, Human Activity Recognition (HAR) has become a vibrant research area, especially due to the spread of electronic devices such as smartphones, smartwatches and video cameras present in our daily lives. In addition, the advance of deep learning and other machine learning algorithms has allowed researchers to use HAR in various domains including sports, health and well-being applications. For example, HAR is considered as one of the most promising assistive technology tools to support elderly's daily life by monitoring their cognitive and physical function through daily activities. This survey focuses on critical role of machine learning in developing HAR applications based on inertial sensors in conjunction with physiological and environmental sensors.
摘要
在过去十年中，人类活动识别（HAR）已成为一个充满活力的研究领域，尤其是因为我们日常生活中存在的智能手机、智能手表和摄像机等电子设备的普及。此外，深度学习和其他机器学习算法的进步使研究人员能够在包括体育、健康和福祉应用在内的各个领域使用HAR。例如，HAR被认为是最有前途的辅助技术工具之一，通过日常活动监测老年人的认知和身体功能来支持他们的日常生活。本综述重点关注机器学习在结合生理和环境传感器开发基于惯性传感器的HAR应用中的关键作用。
相似文献
1
Human Activity Recognition using Inertial, Physiological and Environmental Sensors: A Comprehensive Survey.使用惯性、生理和环境传感器的人类活动识别：全面综述。
IEEE Access. 2020;8:210816-210836. doi: 10.1109/access.2020.3037715. Epub 2020 Nov 16.
2
Human Activity Recognition Using Inertial Sensors in a Smartphone: An Overview.基于智能手机惯性传感器的人体活动识别：综述。
Sensors (Basel). 2019 Jul 21;19(14):3213. doi: 10.3390/s19143213.
3
Using Inertial Sensors to Determine Head Motion-A Review.利用惯性传感器确定头部运动——综述
J Imaging. 2021 Dec 6;7(12):265. doi: 10.3390/jimaging7120265.
4
A brief survey on human activity recognition using motor imagery of EEG signals.关于使用脑电图信号的运动想象进行人类活动识别的简要综述。
Electromagn Biol Med. 2024 Oct;43(4):312-327. doi: 10.1080/15368378.2024.2415089. Epub 2024 Oct 19.
5
Body Temperature Monitoring for Regular COVID-19 Prevention Based on Human Daily Activity Recognition.基于人体日常活动识别的常规 COVID-19 预防体温监测。
Sensors (Basel). 2021 Nov 12;21(22):7540. doi: 10.3390/s21227540.
6
w-HAR: An Activity Recognition Dataset and Framework Using Low-Power Wearable Devices.w-HAR：一个使用低功耗可穿戴设备的活动识别数据集和框架。
Sensors (Basel). 2020 Sep 18;20(18):5356. doi: 10.3390/s20185356.
7
A Wearable Inertial Sensor Approach for Locomotion and Localization Recognition on Physical Activity.基于可穿戴惯性传感器的身体活动中运动和定位识别方法。
Sensors (Basel). 2024 Jan 23;24(3):735. doi: 10.3390/s24030735.
8
Using a Hybrid Neural Network and a Regularized Extreme Learning Machine for Human Activity Recognition with Smartphone and Smartwatch.使用混合神经网络和正则化极限学习机进行智能手机和智能手表的人体活动识别。
Sensors (Basel). 2023 Mar 22;23(6):3354. doi: 10.3390/s23063354.
9
A hybrid deep approach to recognizing student activity and monitoring health physique based on accelerometer data from smartphones.基于智能手机加速度计数据的混合深度学习方法，用于识别学生活动和监测健康体质。
Sci Rep. 2024 Jun 18;14(1):14006. doi: 10.1038/s41598-024-63934-8.
10
Wearable Sensor-Based Human Activity Recognition in the Smart Healthcare System.基于可穿戴传感器的智能医疗保健系统中的人体活动识别。
Comput Intell Neurosci. 2022 Feb 24;2022:1391906. doi: 10.1155/2022/1391906. eCollection 2022.
引用本文的文献
1
The application of suitable sports games for junior high school students based on deep learning and artificial intelligence.基于深度学习和人工智能的适合初中生的体育游戏应用
Sci Rep. 2025 May 16;15(1):17056. doi: 10.1038/s41598-025-01941-z.
2
Recent Advancements in Rubber Composites for Physical Activity Monitoring Sensors: A Critical Review.用于身体活动监测传感器的橡胶复合材料的最新进展：批判性综述
Polymers (Basel). 2025 Apr 17;17(8):1085. doi: 10.3390/polym17081085.
3
Activity and Behavioral Recognition Using Sensing Technology in Persons with Parkinson's Disease or Dementia: An Umbrella Review of the Literature.利用传感技术对帕金森病或痴呆症患者进行活动和行为识别：文献综述
Sensors (Basel). 2025 Jan 23;25(3):668. doi: 10.3390/s25030668.
4
An Approach to Fall Detection Using Statistical Distributions of Thermal Signatures Obtained by a Stand-Alone Low-Resolution IR Array Sensor Device.一种利用独立低分辨率红外阵列传感器设备获取的热特征统计分布进行跌倒检测的方法。
Sensors (Basel). 2025 Jan 16;25(2):504. doi: 10.3390/s25020504.
5
Wearable sensors based on artificial intelligence models for human activity recognition.基于人工智能模型的可穿戴传感器用于人类活动识别。
Front Artif Intell. 2024 Jun 27;7:1424190. doi: 10.3389/frai.2024.1424190. eCollection 2024.
6
The Effect of Sensor Feature Inputs on Joint Angle Prediction across Simple Movements.传感器特征输入对简单运动中关节角度预测的影响。
Sensors (Basel). 2024 Jun 5;24(11):3657. doi: 10.3390/s24113657.
7
A CNN Model for Physical Activity Recognition and Energy Expenditure Estimation from an Eyeglass-Mounted Wearable Sensor.基于眼镜式可穿戴传感器的活动识别和能量消耗估计的 CNN 模型。
Sensors (Basel). 2024 May 11;24(10):3046. doi: 10.3390/s24103046.
8
Human Activity Recognition Algorithm with Physiological and Inertial Signals Fusion: Photoplethysmography, Electrodermal Activity, and Accelerometry.基于光电容积脉搏波、皮肤电活动和加速度计的生理和惯性信号融合的人体活动识别算法。
Sensors (Basel). 2024 May 9;24(10):3005. doi: 10.3390/s24103005.
9
Semi-supervised ensemble learning for human activity recognition in casas Kyoto dataset.用于CASAS京都数据集中人类活动识别的半监督集成学习
Heliyon. 2024 Apr 15;10(8):e29398. doi: 10.1016/j.heliyon.2024.e29398. eCollection 2024 Apr 30.
10
Sports activity (SA) recognition based on error correcting output codes (ECOC) and convolutional neural network (CNN).基于纠错输出码（ECOC）和卷积神经网络（CNN）的体育活动（SA）识别
Heliyon. 2024 Mar 19;10(6):e28258. doi: 10.1016/j.heliyon.2024.e28258. eCollection 2024 Mar 30.
本文引用的文献
1
Toward a Wearable System for Predicting Freezing of Gait in People Affected by Parkinson's Disease.开发一种用于预测帕金森病患者步态冻结的可穿戴系统。
IEEE J Biomed Health Inform. 2020 Sep;24(9):2444-2451. doi: 10.1109/JBHI.2019.2952618. Epub 2019 Nov 11.
2
Human Activity Recognition Using Inertial Sensors in a Smartphone: An Overview.基于智能手机惯性传感器的人体活动识别：综述。
Sensors (Basel). 2019 Jul 21;19(14):3213. doi: 10.3390/s19143213.
3
Sensor Data Acquisition and Multimodal Sensor Fusion for Human Activity Recognition Using Deep Learning.使用深度学习进行人体活动识别的传感器数据采集和多模态传感器融合。
Sensors (Basel). 2019 Apr 10;19(7):1716. doi: 10.3390/s19071716.
4
TSE-CNN: A Two-Stage End-to-End CNN for Human Activity Recognition.TSE-CNN：一种用于人体活动识别的两阶段端到端 CNN
IEEE J Biomed Health Inform. 2020 Jan;24(1):292-299. doi: 10.1109/JBHI.2019.2909688. Epub 2019 Apr 9.
5
Accelerometer-Based Human Fall Detection Using Convolutional Neural Networks.基于加速度计的卷积神经网络人体跌倒检测
Sensors (Basel). 2019 Apr 6;19(7):1644. doi: 10.3390/s19071644.
6
Applying Multivariate Segmentation Methods to Human Activity Recognition From Wearable Sensors' Data.应用多元分割方法于可穿戴传感器数据的人类活动识别。
JMIR Mhealth Uhealth. 2019 Feb 7;7(2):e11201. doi: 10.2196/11201.
7
Accuracy of Samsung Gear S Smartwatch for Activity Recognition: Validation Study.三星 Gear S 智能手表活动识别准确性：验证研究。
JMIR Mhealth Uhealth. 2019 Feb 6;7(2):e11270. doi: 10.2196/11270.
8
Smartphone-Based Activity Recognition for Indoor Localization Using a Convolutional Neural Network.基于卷积神经网络的智能手机室内定位活动识别。
Sensors (Basel). 2019 Feb 1;19(3):621. doi: 10.3390/s19030621.
9
Human Physical Activity Recognition Using Smartphone Sensors.使用智能手机传感器进行人体活动识别。
Sensors (Basel). 2019 Jan 23;19(3):458. doi: 10.3390/s19030458.
10
Empirical Study and Improvement on Deep Transfer Learning for Human Activity Recognition.基于深度学习的人体活动识别的实证研究与改进。
Sensors (Basel). 2018 Dec 24;19(1):57. doi: 10.3390/s19010057.
Zotero 插件