Embedded-machine learning and soft, flexible sensors for wearable devices - viewing from an AI engineer

可穿戴计算机 材料科学 软机器人 可穿戴技术 人机交互 纳米技术 人工智能 计算机科学 嵌入式系统 机器人
作者
Chi Cuong Vu
出处
期刊:Materials Today Physics [Elsevier BV]
卷期号:42: 101376-101376 被引量:47
标识
DOI:10.1016/j.mtphys.2024.101376
摘要

Sensor technology, whose primary function is to represent the interaction between humans and the surrounding world, has become a core feature of many electronic products in the past decades. Among them, flexible sensors are attracting many studies because of their superior properties compared to traditional sensors, such as thinness, lightness, or ease of integration on different surfaces. However, the instability of the received signal is always a big challenge, making it difficult to read valuable information. Using traditional signal processing methods becomes ineffective in practical tasks. Therefore, many researchers have combined data production and analysis processes to overcome the risks encountered gradually. The most anticipated combination in this field is between soft sensors and embedded artificial intelligence models. More specifically, based on the sensing mechanisms and wearable application cases, the researchers propose different machine learning models to observe the signal patterns. This direction of development not only ensures the versatility of wearable devices but also ensures accuracy when drawing valuable conclusions. To achieve this goal, we must consider an overall system with flexible sensors that different working mechanisms will yield different signal types. From there, we choose an embedded machine-learning model that is appropriate for the amount of data and available hardware resources. Following the above approach, this review outlines the research on how machine learning models and soft sensors have impacted human lives over the past few years. After that, we draw conclusions and predictions about the challenges, solutions, and development trends. The review is expected to become a key reference point for works related to smart wearable devices using soft sensors.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
111完成签到,获得积分10
刚刚
晴天完成签到 ,获得积分10
刚刚
冯亦帆帆发布了新的文献求助10
1秒前
Juvenilesy的应助被自然醒采纳,获得10
3秒前
菘蓝完成签到 ,获得积分10
3秒前
现代宛丝发布了新的文献求助10
3秒前
4秒前
ry关闭了ry的文献求助
5秒前
马赛克完成签到,获得积分10
5秒前
七听的应助被hhhhh采纳,获得150
6秒前
myfmmmm完成签到,获得积分20
6秒前
ferrumNjr完成签到,获得积分10
6秒前
Yee完成签到 ,获得积分10
6秒前
bkagyin的应助被jgz1215采纳,获得10
6秒前
微7完成签到,获得积分10
7秒前
7秒前
田様的应助被vamcello采纳,获得10
8秒前
满意的妙海完成签到 ,获得积分10
8秒前
简qw发布了新的文献求助10
8秒前
孙栗吱完成签到 ,获得积分10
9秒前
9秒前
薄荷完成签到 ,获得积分10
9秒前
哈哈完成签到 ,获得积分10
10秒前
jq完成签到 ,获得积分10
10秒前
syvshc的应助被pp采纳,获得10
10秒前
朱雀发布了新的文献求助10
10秒前
徐睿发布了新的文献求助10
11秒前
wanci的应助被开朗紫采纳,获得10
11秒前
何睦完成签到 ,获得积分10
12秒前
Zzzvir发布了新的文献求助10
13秒前
banana的应助被多加辣采纳,获得10
13秒前
鼻毛好胜发布了新的文献求助10
14秒前
14秒前
韩小炜完成签到,获得积分10
15秒前
灏蝻完成签到,获得积分10
16秒前
大时钟的应助被hhh采纳,获得10
17秒前
棠棠完成签到 ,获得积分10
17秒前
王赟赟发布了新的文献求助10
18秒前
科研通AI6.3的应助被简qw采纳,获得10
18秒前
18秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Boundaries and Bodhisattvas 500
高分子基功能界面水蒸发材料与应用研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8181498
求助须知:如何正确求助?哪些是违规求助? 9571421
关于积分的说明 21817968
捐赠科研通 7777967
什么是DOI,文献DOI怎么找? 3433508
关于科研通互助平台的介绍 2557696
邀请新用户注册赠送积分活动 2479552