CHARM-Deep: Continuous Human Activity Recognition Model Based on Deep Neural Network Using IMU Sensors of Smartwatch

计算机科学 智能手表 人工智能 惯性测量装置 深度学习 活动识别 人工神经网络 模式识别(心理学) 实时计算 嵌入式系统 可穿戴计算机
作者
Sara Ashry,Tetsuji Ogawa,Walid Gomaa
出处
期刊:IEEE Sensors Journal [IEEE Sensors Council]
卷期号:20 (15): 8757-8770 被引量:27
标识
DOI:10.1109/jsen.2020.2985374
摘要

In the present paper, an attempt was made to achieve high-performance continuous human activity recognition (CHAR) using deep neural networks. The present study focuses on recognizing different activities in a continuous stream, which means `back-to-back' consecutive set of activities, from only inertial measurement unit (IMU) sensors mounted on smartwatches. For that purpose, a new dataset called `CHAR-SW', which includes numerous streams of daily activities, was collected using smartwatches, and feature representations and network architectures were designed. Experimental comparisons using our own dataset and public datasets (Aruba and Tulum) have been performed. They demonstrated that cascading bidirectional long short-term memory (Bi-LSTM) with featured data performed well in offline mode from the viewpoints of accuracy, computational time, and storage space required. The input to the Bi-LSTM is a descriptor which composed of a stream of the following features: autocorrelation, median, entropy, and instantaneous frequency. Additionally, a novel technique to operate the CHAR system online was introduced and shown to be effective. Experimental results can be summarized as: the offline CHARM-Deep enhanced the accuracy compared with using raw data or the existing approaches, and it reduced the processing time by 86% at least relative to the time consumed in executing the Bi-LSTM classifier directly on the raw data. It also reduced storage space by approximately 97.77% compared with using raw data. The online evaluation shows that it can recognize activities in real-time with an accuracy of 91%.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
秋雨完成签到,获得积分10
刚刚
刚刚
1秒前
别忘了吃胶囊完成签到,获得积分10
1秒前
lin完成签到,获得积分20
2秒前
4秒前
小爽完成签到,获得积分0
5秒前
lin发布了新的文献求助10
5秒前
5秒前
123发布了新的文献求助10
6秒前
7秒前
xmdcobra完成签到,获得积分10
10秒前
10秒前
小二郎应助初初采纳,获得10
13秒前
英俊的铭应助调皮的天真采纳,获得10
13秒前
14秒前
jeitt完成签到,获得积分10
15秒前
Zhaobin发布了新的文献求助10
16秒前
量子星尘发布了新的文献求助10
19秒前
深情安青应助哈哈哈哈采纳,获得10
20秒前
21秒前
淙淙柔水完成签到,获得积分0
22秒前
随意完成签到,获得积分10
26秒前
RBT发布了新的文献求助10
26秒前
烟花应助魔道祖师采纳,获得10
26秒前
skywalker完成签到,获得积分10
26秒前
27秒前
28秒前
开心的火龙果完成签到,获得积分10
29秒前
Zhaobin完成签到,获得积分10
29秒前
ss13l完成签到,获得积分10
29秒前
初初完成签到,获得积分10
30秒前
ymy完成签到,获得积分20
33秒前
Chloe发布了新的文献求助10
34秒前
负责丹亦完成签到,获得积分10
36秒前
汉堡包应助RBT采纳,获得10
36秒前
Imcarie完成签到 ,获得积分10
37秒前
41秒前
桐桐应助Penny采纳,获得10
43秒前
47秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Comparison analysis of Apple face ID in iPad Pro 13” with first use of metasurfaces for diffraction vs. iPhone 16 Pro 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4039683
求助须知:如何正确求助?哪些是违规求助? 3577312
关于积分的说明 11377241
捐赠科研通 3306735
什么是DOI,文献DOI怎么找? 1819586
邀请新用户注册赠送积分活动 892935
科研通“疑难数据库(出版商)”最低求助积分说明 815165