Proximity Detection During Epidemics: Direct UWB TOA Versus Machine Learning Based RSSI.

IF 1.5 Q3 TELECOMMUNICATIONS International Journal of Wireless Information Networks Pub Date : 2022-01-01 Epub Date: 2022-10-14 DOI:10.1007/s10776-022-00577-4
Zhuoran Su, Kaveh Pahlavan, Emmanuel Agu, Haowen Wei
{"title":"Proximity Detection During Epidemics: Direct UWB TOA Versus Machine Learning Based RSSI.","authors":"Zhuoran Su,&nbsp;Kaveh Pahlavan,&nbsp;Emmanuel Agu,&nbsp;Haowen Wei","doi":"10.1007/s10776-022-00577-4","DOIUrl":null,"url":null,"abstract":"<p><p>In this paper, we compare the direct TOA-based UWB technology with the RSSI-based BLE technology using machine learning algorithms for proximity detection during epidemics in terms of complexity of implementation, availability in existing smart phones, and precision of the results. We establish the theoretical limits on the precision and confidence of proximity estimation for both technologies using the Cramer Rao Lower Bound (CRLB) and validate the theoretical foundations using empirical data gathered in diverse practical operating scenarios. We perform our empirical experiments at eight distances in three flat environments and one non-flat environment encompassing both Line of Sight (LOS) and Obstructed-LOS (OLOS) situations. We also analyze the effects of various postures (eight angles) of the person carrying the sensor, and four on-body locations of the sensor. To estimate the range with BLE RSSI, we use 14 features for training the Gradient Boosted Machines (GBM) learning algorithm and we compare the precision of results with those obtained from memoryless UWB TOA ranging algorithm. We show that the memoryless UWB TOA algorithm achieves 93.60% confidence, slightly outperforming the 92.85% confidence of the BLE RSSI with more complex GBM machine learning (ML) algorithm and the need for substantial training. The training process for the RSSI-based BLE social distance measurements involved 3000 measurements to create a training dataset for each scenario and post-processing of data to extract 14 features of RSSI, and the ML classification algorithm consumed 200 s of computational time. The memoryless UWB ranging algorithm achieves more robust results without any need for training in less than 0.5 s of computation time.</p><p><strong>Graphical abstract: </strong></p>","PeriodicalId":45393,"journal":{"name":"International Journal of Wireless Information Networks","volume":"29 4","pages":"480-490"},"PeriodicalIF":1.5000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9562079/pdf/","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Wireless Information Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s10776-022-00577-4","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2022/10/14 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"TELECOMMUNICATIONS","Score":null,"Total":0}
引用次数: 2

Abstract

In this paper, we compare the direct TOA-based UWB technology with the RSSI-based BLE technology using machine learning algorithms for proximity detection during epidemics in terms of complexity of implementation, availability in existing smart phones, and precision of the results. We establish the theoretical limits on the precision and confidence of proximity estimation for both technologies using the Cramer Rao Lower Bound (CRLB) and validate the theoretical foundations using empirical data gathered in diverse practical operating scenarios. We perform our empirical experiments at eight distances in three flat environments and one non-flat environment encompassing both Line of Sight (LOS) and Obstructed-LOS (OLOS) situations. We also analyze the effects of various postures (eight angles) of the person carrying the sensor, and four on-body locations of the sensor. To estimate the range with BLE RSSI, we use 14 features for training the Gradient Boosted Machines (GBM) learning algorithm and we compare the precision of results with those obtained from memoryless UWB TOA ranging algorithm. We show that the memoryless UWB TOA algorithm achieves 93.60% confidence, slightly outperforming the 92.85% confidence of the BLE RSSI with more complex GBM machine learning (ML) algorithm and the need for substantial training. The training process for the RSSI-based BLE social distance measurements involved 3000 measurements to create a training dataset for each scenario and post-processing of data to extract 14 features of RSSI, and the ML classification algorithm consumed 200 s of computational time. The memoryless UWB ranging algorithm achieves more robust results without any need for training in less than 0.5 s of computation time.

Graphical abstract:

Abstract Image

Abstract Image

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
流行病期间的接近检测:直接超宽带TOA与基于机器学习的RSSI。
在本文中,我们比较了直接基于tob的UWB技术和基于rsi的BLE技术,使用机器学习算法在流行病期间进行接近检测,包括实现的复杂性、现有智能手机的可用性和结果的精度。我们使用Cramer Rao下界(CRLB)建立了两种技术的接近估计精度和置信度的理论限制,并使用在不同实际操作场景中收集的经验数据验证了理论基础。我们在三种平坦环境和一种非平坦环境中进行了八种距离的实证实验,包括视线(LOS)和视线受阻(OLOS)情况。我们还分析了携带传感器的人的不同姿势(八个角度)和传感器在身体上的四个位置的影响。为了使用BLE RSSI估计距离,我们使用了14个特征来训练梯度提升机(GBM)学习算法,并将结果的精度与无记忆UWB TOA测距算法的结果进行了比较。我们发现无记忆UWB TOA算法达到了93.60%的置信度,在更复杂的GBM机器学习(ML)算法和需要大量训练的情况下,略优于BLE RSSI的92.85%置信度。基于RSSI的BLE社交距离测量的训练过程涉及3000个测量值为每个场景创建训练数据集,并对数据进行后处理以提取14个RSSI特征,ML分类算法消耗200 s的计算时间。无记忆超宽带测距算法在不需要训练的情况下,在不到0.5 s的计算时间内获得了更强的鲁棒性结果。图形化的简介:
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
6.60
自引率
8.00%
发文量
41
期刊介绍: International Journal of Wireless Information Networks is an international forum for the dissemination of knowledge related to wireless information networks for researchers in the telecommunications and computer industries. This outstanding quarterly publishes high-quality, peer-reviewed original papers on applications such as sensor and mobile ad-hoc networks, wireless personal area networks, wireless LANs, mobile data networks, location aware networks and services, and RF localization and RFID techniques. The journal also covers performance-predictions methodologies, radio propagation studies, modulation and coding, multiple access methods, security and privacy considerations, antenna and RF subsystems, VLSI and ASIC design, experimental trials, traffic and frequency management, and network signaling and architecture. Four categories of papers are published: invited openings (review current and future directions), overview reports (address the philosophy and technical details of the standards and field trials), technical papers (present specific technical contributions of archival value), and letters (present new enhancement of previously published works, statements of open problems, comments on published papers, and corrections). International Journal of Wireless Information Networks aims to fill the needs of academic researchers involved in basic research at universities or research laboratories; telecommunications and computer engineers involved in design, planning, operation, and maintenance of state-of-the-art wireless information networks; and the technical community in telecommunications and computers involved in applied research and standards activities. To view cumulative tables of contents, find details on the latest call for papers, or other information, please visit the http://www.cwins.wpi.edu/journal.html International Journal of Wireless Information Networks Web Site.
期刊最新文献
On the Analyses of Propagation Characteristics and User Association for Sub-6 GHz and mmWave Carriers in Intelligent Reflecting Surfaces-Assisted Multi-tier 6G Networks Federated Learning-Enabled Cooperative Localization in Multi-agent System Polar-Coded OFDM Signal Using Physical Layer Network Coding for New-Generation Networks An Adaptive Distributed Broadcast Protocol for Wireless Nanosensor Networks Characteristics of Mid-Bands Interference in Wireless Spectrum Sharing for Mobility Support in 6G, Wi-Fi 7, and Beyond
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1