Wi-Fi CSI-based Human Presence Detection Using DTW Features and Machine Learning

Julio C.H. Soto; Iandra Galdino; Brenda G. Gouveia; Egberto Caballero; Vinicius Ferreira; Debora Muchaluat-Saade; Celio Albuquerque

doi:10.1109/LATINCOM56090.2022.10000702

Wi-Fi CSI-based Human Presence Detection Using DTW Features and Machine Learning

Julio C.H. Soto
, Iandra Galdino
, Brenda G. Gouveia
, Egberto Caballero
, Vinicius Ferreira
, Debora Muchaluat-Saade
, Celio Albuquerque

Research output: Chapter in Book/Report/Conference proceeding › Paper (Conference contribution) › peer-review

13 Scopus citations

Abstract

With the development of smart devices, human detection and localization became important tasks for several applications including security, healthcare monitoring, entertainment, and so on. Existing signal-based detection systems, mostly focus on detecting human activities and classifying them by Machine Learning (ML) methods, like Support Vector Machine (SVM) and Random Forest (RF). This paper focuses on device-free presence detection. We propose a specific setup for collecting Wi-Fi based Channel State Information (CSI) data for detecting human presence. The proposal includes the application of Dynamic Time Warping (DTW) algorithm features to compare the differences between empty rooms and filled rooms. The proposed architecture and approach achieves competitive accuracy when compared to the existing technologies.

Original language	English
Title of host publication	2022 IEEE Latin-American Conference on Communications, LATINCOM 2022
Editors	Igor M. Moraes, Miguel Elias M. Campista, Yacine Ghamri-Doudane, Costa Luis Henrique M. K. Costa, Marcelo G. Rubinstein
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665482257
DOIs	https://doi.org/10.1109/LATINCOM56090.2022.10000702
State	Published - 2022
Externally published	Yes
Event	14th IEEE Latin-American Conference on Communications, LATINCOM 2022 - Rio de Janeiro, Brazil Duration: 30 Nov 2022 → 2 Dec 2022

Publication series

Name	2022 IEEE Latin-American Conference on Communications, LATINCOM 2022

Conference

Conference	14th IEEE Latin-American Conference on Communications, LATINCOM 2022
Country/Territory	Brazil
City	Rio de Janeiro
Period	30/11/22 → 2/12/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

channel state information
DTW
Human presence detection
Machine Learning
Wi-Fi

Access to Document

10.1109/LATINCOM56090.2022.10000702

Cite this

Soto, J. C. H., Galdino, I., Gouveia, B. G., Caballero, E., Ferreira, V., Muchaluat-Saade, D., & Albuquerque, C. (2022). Wi-Fi CSI-based Human Presence Detection Using DTW Features and Machine Learning. In I. M. Moraes, M. E. M. Campista, Y. Ghamri-Doudane, C. Luis Henrique M. K. Costa, & M. G. Rubinstein (Eds.), 2022 IEEE Latin-American Conference on Communications, LATINCOM 2022 (2022 IEEE Latin-American Conference on Communications, LATINCOM 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/LATINCOM56090.2022.10000702

Soto, Julio C.H. ; Galdino, Iandra ; Gouveia, Brenda G. et al. / Wi-Fi CSI-based Human Presence Detection Using DTW Features and Machine Learning. 2022 IEEE Latin-American Conference on Communications, LATINCOM 2022. editor / Igor M. Moraes ; Miguel Elias M. Campista ; Yacine Ghamri-Doudane ; Costa Luis Henrique M. K. Costa ; Marcelo G. Rubinstein. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE Latin-American Conference on Communications, LATINCOM 2022).

@inproceedings{6b839430238c46d385f980e31ce346ce,

title = "Wi-Fi CSI-based Human Presence Detection Using DTW Features and Machine Learning",

abstract = "With the development of smart devices, human detection and localization became important tasks for several applications including security, healthcare monitoring, entertainment, and so on. Existing signal-based detection systems, mostly focus on detecting human activities and classifying them by Machine Learning (ML) methods, like Support Vector Machine (SVM) and Random Forest (RF). This paper focuses on device-free presence detection. We propose a specific setup for collecting Wi-Fi based Channel State Information (CSI) data for detecting human presence. The proposal includes the application of Dynamic Time Warping (DTW) algorithm features to compare the differences between empty rooms and filled rooms. The proposed architecture and approach achieves competitive accuracy when compared to the existing technologies.",

keywords = "channel state information, DTW, Human presence detection, Machine Learning, Wi-Fi",

author = "Soto, \{Julio C.H.\} and Iandra Galdino and Gouveia, \{Brenda G.\} and Egberto Caballero and Vinicius Ferreira and Debora Muchaluat-Saade and Celio Albuquerque",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 14th IEEE Latin-American Conference on Communications, LATINCOM 2022 ; Conference date: 30-11-2022 Through 02-12-2022",

year = "2022",

doi = "10.1109/LATINCOM56090.2022.10000702",

language = "Ingl{\'e}s",

series = "2022 IEEE Latin-American Conference on Communications, LATINCOM 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Moraes, \{Igor M.\} and Campista, \{Miguel Elias M.\} and Yacine Ghamri-Doudane and \{Luis Henrique M. K. Costa\}, Costa and Rubinstein, \{Marcelo G.\}",

booktitle = "2022 IEEE Latin-American Conference on Communications, LATINCOM 2022",

}

Soto, JCH, Galdino, I, Gouveia, BG, Caballero, E, Ferreira, V, Muchaluat-Saade, D & Albuquerque, C 2022, Wi-Fi CSI-based Human Presence Detection Using DTW Features and Machine Learning. in IM Moraes, MEM Campista, Y Ghamri-Doudane, C Luis Henrique M. K. Costa & MG Rubinstein (eds), 2022 IEEE Latin-American Conference on Communications, LATINCOM 2022. 2022 IEEE Latin-American Conference on Communications, LATINCOM 2022, Institute of Electrical and Electronics Engineers Inc., 14th IEEE Latin-American Conference on Communications, LATINCOM 2022, Rio de Janeiro, Brazil, 30/11/22. https://doi.org/10.1109/LATINCOM56090.2022.10000702

Wi-Fi CSI-based Human Presence Detection Using DTW Features and Machine Learning. / Soto, Julio C.H.; Galdino, Iandra; Gouveia, Brenda G. et al.
2022 IEEE Latin-American Conference on Communications, LATINCOM 2022. ed. / Igor M. Moraes; Miguel Elias M. Campista; Yacine Ghamri-Doudane; Costa Luis Henrique M. K. Costa; Marcelo G. Rubinstein. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE Latin-American Conference on Communications, LATINCOM 2022).

Research output: Chapter in Book/Report/Conference proceeding › Paper (Conference contribution) › peer-review

TY - GEN

T1 - Wi-Fi CSI-based Human Presence Detection Using DTW Features and Machine Learning

AU - Soto, Julio C.H.

AU - Galdino, Iandra

AU - Gouveia, Brenda G.

AU - Caballero, Egberto

AU - Ferreira, Vinicius

AU - Muchaluat-Saade, Debora

AU - Albuquerque, Celio

PY - 2022

Y1 - 2022

N2 - With the development of smart devices, human detection and localization became important tasks for several applications including security, healthcare monitoring, entertainment, and so on. Existing signal-based detection systems, mostly focus on detecting human activities and classifying them by Machine Learning (ML) methods, like Support Vector Machine (SVM) and Random Forest (RF). This paper focuses on device-free presence detection. We propose a specific setup for collecting Wi-Fi based Channel State Information (CSI) data for detecting human presence. The proposal includes the application of Dynamic Time Warping (DTW) algorithm features to compare the differences between empty rooms and filled rooms. The proposed architecture and approach achieves competitive accuracy when compared to the existing technologies.

AB - With the development of smart devices, human detection and localization became important tasks for several applications including security, healthcare monitoring, entertainment, and so on. Existing signal-based detection systems, mostly focus on detecting human activities and classifying them by Machine Learning (ML) methods, like Support Vector Machine (SVM) and Random Forest (RF). This paper focuses on device-free presence detection. We propose a specific setup for collecting Wi-Fi based Channel State Information (CSI) data for detecting human presence. The proposal includes the application of Dynamic Time Warping (DTW) algorithm features to compare the differences between empty rooms and filled rooms. The proposed architecture and approach achieves competitive accuracy when compared to the existing technologies.

KW - channel state information

KW - DTW

KW - Human presence detection

KW - Machine Learning

KW - Wi-Fi

UR - https://www.scopus.com/pages/publications/85146662980

U2 - 10.1109/LATINCOM56090.2022.10000702

DO - 10.1109/LATINCOM56090.2022.10000702

M3 - Articulo (Contribución a conferencia)

AN - SCOPUS:85146662980

T3 - 2022 IEEE Latin-American Conference on Communications, LATINCOM 2022

BT - 2022 IEEE Latin-American Conference on Communications, LATINCOM 2022

A2 - Moraes, Igor M.

A2 - Campista, Miguel Elias M.

A2 - Ghamri-Doudane, Yacine

A2 - Luis Henrique M. K. Costa, Costa

A2 - Rubinstein, Marcelo G.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th IEEE Latin-American Conference on Communications, LATINCOM 2022

Y2 - 30 November 2022 through 2 December 2022

ER -

Soto JCH, Galdino I, Gouveia BG, Caballero E, Ferreira V, Muchaluat-Saade D et al. Wi-Fi CSI-based Human Presence Detection Using DTW Features and Machine Learning. In Moraes IM, Campista MEM, Ghamri-Doudane Y, Luis Henrique M. K. Costa C, Rubinstein MG, editors, 2022 IEEE Latin-American Conference on Communications, LATINCOM 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (2022 IEEE Latin-American Conference on Communications, LATINCOM 2022). doi: 10.1109/LATINCOM56090.2022.10000702

Wi-Fi CSI-based Human Presence Detection Using DTW Features and Machine Learning

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this