基于单个三轴加速度计的人体行为识别研究  

Single triaxial accelerometer based human action recognition research

作　　者：张宇 郭达[1] 高志勇 周大海 Zhang Yu;Guo Da;Gao Zhiyong;Zhou Dahai(School of Electronic Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China;AIdong Super AI (Beijing) Co.,Ltd.,Beijing 100007,China)

机构地区：[1]北京邮电大学电子工程学院,北京100876 [2]爱动超越人工智能科技(北京)有限责任公司,北京100007

出　　处：《信息技术与网络安全》2019年第2期21-25,共5页Information Technology and Network Security

摘　　要：人工智能的发展和行业应用需求促进人体行为识别研究得到众多关注,主要研究方法或基于视频数据或基于传感器数据。得益于可穿戴传感器的发展,众多研究专注于在人体部署多个传感器以期取得良好效果。不同于以往研究,本文仅通过佩戴在手腕的单个三轴加速度计进行人体行为识别研究,以最大程度减小对个体的干扰并降低传感器部署成本。通过数据预处理和特征提取,并利用一种改进的子窗口的集成学习算法,实现对人体行为的准确识别。实验结果表明,相较于传统算法,识别准确率得以显著提升,证实了研究成果的有效性。The development of artificial intelligence and the demand of industry application promote the research on human action recognition(HAR).The main research methods are based on video data or sensor data.Thanks to the development of wearable sensors,many studies focus on deploying multiple sensors on human body to achieve good results.However,different from previous studies,this paper tries to study HAR by using a single triaxial accelerometer worn on the wrist to minimize the interference to individual and reduce the cost of sensor deployment.After data preprocessing and feature extraction,an improved subwindow-based ensemble learning algorithm is used for accurate recognition.The experimental results show that the recognition accuracy is improved significantly compared with traditional algorithms,and the validity of the research results is verified.

关 键 词：可穿戴物联网 人工智能 人体行为识别 三轴加速度计 集成学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]