Danger-pose detection system using commodity wi-fi for bathroom monitoring

Zizheng Zhang, Shigemi Ishida, Shigeaki Tagashira, Akira Fukuda

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A bathroom has higher probability of accidents than other rooms due to a slippery floor and temperature change. Because of high privacy and humidity, we face difficulties in monitoring inside a bathroom using traditional healthcare methods based on cameras and wearable sensors. In this paper, we present a danger-pose detection system using commodity Wi-Fi devices, which can be applied to bathroom monitoring, preserving privacy. A machine learning-based detection method usually requires data collected in target situations, which is difficult in detection-of-danger situations. We therefore employ a machine learning-based anomaly-detection method that requires a small amount of data in anomaly conditions, minimizing the required training data collected in dangerous conditions. We first derive the amplitude and phase shift from Wi-Fi channel state information (CSI) to extract low-frequency components that are related to human activities. We then separately extract static and dynamic features from the CSI changes in time. Finally, the static and dynamic features are fed into a one-class support vector machine (SVM), which is used as an anomaly-detection method, to classify whether a user is not in bathtub, bathing safely, or in dangerous conditions. We conducted experimental evaluations and demonstrated that our danger-pose detection system achieved a high detection performance in a non-line-of-sight (NLOS) scenario.

Original languageEnglish
Article number884
JournalSensors (Switzerland)
Volume19
Issue number4
DOIs
Publication statusPublished - Feb 2 2019

Fingerprint

Toilet Facilities
commodities
Wi-Fi
Channel state information
hazards
Learning systems
Monitoring
Privacy
Phase shift
Support vector machines
Atmospheric humidity
Accidents
Cameras
privacy
machine learning
anomalies
Humidity
Human Activities
bathing
Delivery of Health Care

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Danger-pose detection system using commodity wi-fi for bathroom monitoring. / Zhang, Zizheng; Ishida, Shigemi; Tagashira, Shigeaki; Fukuda, Akira.

In: Sensors (Switzerland), Vol. 19, No. 4, 884, 02.02.2019.

Research output: Contribution to journalArticle

@article{06e3e6739afe44399efc7a9d7bf3c335,
title = "Danger-pose detection system using commodity wi-fi for bathroom monitoring",
abstract = "A bathroom has higher probability of accidents than other rooms due to a slippery floor and temperature change. Because of high privacy and humidity, we face difficulties in monitoring inside a bathroom using traditional healthcare methods based on cameras and wearable sensors. In this paper, we present a danger-pose detection system using commodity Wi-Fi devices, which can be applied to bathroom monitoring, preserving privacy. A machine learning-based detection method usually requires data collected in target situations, which is difficult in detection-of-danger situations. We therefore employ a machine learning-based anomaly-detection method that requires a small amount of data in anomaly conditions, minimizing the required training data collected in dangerous conditions. We first derive the amplitude and phase shift from Wi-Fi channel state information (CSI) to extract low-frequency components that are related to human activities. We then separately extract static and dynamic features from the CSI changes in time. Finally, the static and dynamic features are fed into a one-class support vector machine (SVM), which is used as an anomaly-detection method, to classify whether a user is not in bathtub, bathing safely, or in dangerous conditions. We conducted experimental evaluations and demonstrated that our danger-pose detection system achieved a high detection performance in a non-line-of-sight (NLOS) scenario.",
author = "Zizheng Zhang and Shigemi Ishida and Shigeaki Tagashira and Akira Fukuda",
year = "2019",
month = "2",
day = "2",
doi = "10.3390/s19040884",
language = "English",
volume = "19",
journal = "Sensors",
issn = "1424-3210",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "4",

}

TY - JOUR

T1 - Danger-pose detection system using commodity wi-fi for bathroom monitoring

AU - Zhang, Zizheng

AU - Ishida, Shigemi

AU - Tagashira, Shigeaki

AU - Fukuda, Akira

PY - 2019/2/2

Y1 - 2019/2/2

N2 - A bathroom has higher probability of accidents than other rooms due to a slippery floor and temperature change. Because of high privacy and humidity, we face difficulties in monitoring inside a bathroom using traditional healthcare methods based on cameras and wearable sensors. In this paper, we present a danger-pose detection system using commodity Wi-Fi devices, which can be applied to bathroom monitoring, preserving privacy. A machine learning-based detection method usually requires data collected in target situations, which is difficult in detection-of-danger situations. We therefore employ a machine learning-based anomaly-detection method that requires a small amount of data in anomaly conditions, minimizing the required training data collected in dangerous conditions. We first derive the amplitude and phase shift from Wi-Fi channel state information (CSI) to extract low-frequency components that are related to human activities. We then separately extract static and dynamic features from the CSI changes in time. Finally, the static and dynamic features are fed into a one-class support vector machine (SVM), which is used as an anomaly-detection method, to classify whether a user is not in bathtub, bathing safely, or in dangerous conditions. We conducted experimental evaluations and demonstrated that our danger-pose detection system achieved a high detection performance in a non-line-of-sight (NLOS) scenario.

AB - A bathroom has higher probability of accidents than other rooms due to a slippery floor and temperature change. Because of high privacy and humidity, we face difficulties in monitoring inside a bathroom using traditional healthcare methods based on cameras and wearable sensors. In this paper, we present a danger-pose detection system using commodity Wi-Fi devices, which can be applied to bathroom monitoring, preserving privacy. A machine learning-based detection method usually requires data collected in target situations, which is difficult in detection-of-danger situations. We therefore employ a machine learning-based anomaly-detection method that requires a small amount of data in anomaly conditions, minimizing the required training data collected in dangerous conditions. We first derive the amplitude and phase shift from Wi-Fi channel state information (CSI) to extract low-frequency components that are related to human activities. We then separately extract static and dynamic features from the CSI changes in time. Finally, the static and dynamic features are fed into a one-class support vector machine (SVM), which is used as an anomaly-detection method, to classify whether a user is not in bathtub, bathing safely, or in dangerous conditions. We conducted experimental evaluations and demonstrated that our danger-pose detection system achieved a high detection performance in a non-line-of-sight (NLOS) scenario.

UR - http://www.scopus.com/inward/record.url?scp=85061997489&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061997489&partnerID=8YFLogxK

U2 - 10.3390/s19040884

DO - 10.3390/s19040884

M3 - Article

C2 - 30791629

AN - SCOPUS:85061997489

VL - 19

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 4

M1 - 884

ER -