Hidden Markov Model-Based Fall Detection with Motion Sensor Orientation Calibration: A Case for Real-Life Home Monitoring

Shuo Yu, Hsinchun Chen, Randall A. Brown

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Falls are a major threat for senior citizens’ independent living. Motion sensor technologies and automatic fall detection systems have emerged as a reliable low-cost solution to this challenge. We develop a hidden Markov model (HMM)-based fall detection system to detect falls automatically using a single motion sensor for real-life home monitoring scenarios. We propose a new representation for acceleration signals in HMMs to avoid feature engineering and developed a sensor orientation calibration algorithm to resolve sensor misplacement issues (misplaced sensor location and misaligned sensor orientation) in real-world scenarios. HMM classifiers are trained to detect falls based on acceleration signal data collected from motion sensors. We collect a dataset from experiments of simulated falls and normal activities and acquired a dataset from a real-world fall repository (FARSEEING) to evaluate our system. Our system achieves positive predictive value of 0.981 and sensitivity of 0.992 on the experiment dataset with 200 fall events and 385 normal activities, and positive predictive value of 0.786 and sensitivity of 1.000 on the real-world fall dataset with 22 fall events and 2,618 normal activities. Our system’s results significantly outperform benchmark systems, which shows the advantage of our HMM-based fall detection system with sensor orientation calibration. Our fall detection system is able to precisely detect falls in real-life home scenarios with a reasonably low false alarm rate.

Original languageEnglish (US)
JournalIEEE Journal of Biomedical and Health Informatics
DOIs
StateAccepted/In press - Dec 8 2017

Fingerprint

Hidden Markov models
Calibration
Monitoring
Sensors
Independent Living
Benchmarking
Technology
Costs and Cost Analysis
Datasets
Classifiers
Experiments
Costs

Keywords

  • Acceleration
  • activity recognition
  • Calibration
  • fall detection
  • Feature extraction
  • Floors
  • Hidden Markov models
  • hidden Markov models
  • Injuries
  • Senior citizens
  • signal detection
  • wearable sensors

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Health Information Management

Cite this

@article{d86cb6223b67496cbb8b5745428f14d7,
title = "Hidden Markov Model-Based Fall Detection with Motion Sensor Orientation Calibration: A Case for Real-Life Home Monitoring",
abstract = "Falls are a major threat for senior citizens’ independent living. Motion sensor technologies and automatic fall detection systems have emerged as a reliable low-cost solution to this challenge. We develop a hidden Markov model (HMM)-based fall detection system to detect falls automatically using a single motion sensor for real-life home monitoring scenarios. We propose a new representation for acceleration signals in HMMs to avoid feature engineering and developed a sensor orientation calibration algorithm to resolve sensor misplacement issues (misplaced sensor location and misaligned sensor orientation) in real-world scenarios. HMM classifiers are trained to detect falls based on acceleration signal data collected from motion sensors. We collect a dataset from experiments of simulated falls and normal activities and acquired a dataset from a real-world fall repository (FARSEEING) to evaluate our system. Our system achieves positive predictive value of 0.981 and sensitivity of 0.992 on the experiment dataset with 200 fall events and 385 normal activities, and positive predictive value of 0.786 and sensitivity of 1.000 on the real-world fall dataset with 22 fall events and 2,618 normal activities. Our system’s results significantly outperform benchmark systems, which shows the advantage of our HMM-based fall detection system with sensor orientation calibration. Our fall detection system is able to precisely detect falls in real-life home scenarios with a reasonably low false alarm rate.",
keywords = "Acceleration, activity recognition, Calibration, fall detection, Feature extraction, Floors, Hidden Markov models, hidden Markov models, Injuries, Senior citizens, signal detection, wearable sensors",
author = "Shuo Yu and Hsinchun Chen and Brown, {Randall A.}",
year = "2017",
month = "12",
day = "8",
doi = "10.1109/JBHI.2017.2782079",
language = "English (US)",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Hidden Markov Model-Based Fall Detection with Motion Sensor Orientation Calibration

T2 - A Case for Real-Life Home Monitoring

AU - Yu, Shuo

AU - Chen, Hsinchun

AU - Brown, Randall A.

PY - 2017/12/8

Y1 - 2017/12/8

N2 - Falls are a major threat for senior citizens’ independent living. Motion sensor technologies and automatic fall detection systems have emerged as a reliable low-cost solution to this challenge. We develop a hidden Markov model (HMM)-based fall detection system to detect falls automatically using a single motion sensor for real-life home monitoring scenarios. We propose a new representation for acceleration signals in HMMs to avoid feature engineering and developed a sensor orientation calibration algorithm to resolve sensor misplacement issues (misplaced sensor location and misaligned sensor orientation) in real-world scenarios. HMM classifiers are trained to detect falls based on acceleration signal data collected from motion sensors. We collect a dataset from experiments of simulated falls and normal activities and acquired a dataset from a real-world fall repository (FARSEEING) to evaluate our system. Our system achieves positive predictive value of 0.981 and sensitivity of 0.992 on the experiment dataset with 200 fall events and 385 normal activities, and positive predictive value of 0.786 and sensitivity of 1.000 on the real-world fall dataset with 22 fall events and 2,618 normal activities. Our system’s results significantly outperform benchmark systems, which shows the advantage of our HMM-based fall detection system with sensor orientation calibration. Our fall detection system is able to precisely detect falls in real-life home scenarios with a reasonably low false alarm rate.

AB - Falls are a major threat for senior citizens’ independent living. Motion sensor technologies and automatic fall detection systems have emerged as a reliable low-cost solution to this challenge. We develop a hidden Markov model (HMM)-based fall detection system to detect falls automatically using a single motion sensor for real-life home monitoring scenarios. We propose a new representation for acceleration signals in HMMs to avoid feature engineering and developed a sensor orientation calibration algorithm to resolve sensor misplacement issues (misplaced sensor location and misaligned sensor orientation) in real-world scenarios. HMM classifiers are trained to detect falls based on acceleration signal data collected from motion sensors. We collect a dataset from experiments of simulated falls and normal activities and acquired a dataset from a real-world fall repository (FARSEEING) to evaluate our system. Our system achieves positive predictive value of 0.981 and sensitivity of 0.992 on the experiment dataset with 200 fall events and 385 normal activities, and positive predictive value of 0.786 and sensitivity of 1.000 on the real-world fall dataset with 22 fall events and 2,618 normal activities. Our system’s results significantly outperform benchmark systems, which shows the advantage of our HMM-based fall detection system with sensor orientation calibration. Our fall detection system is able to precisely detect falls in real-life home scenarios with a reasonably low false alarm rate.

KW - Acceleration

KW - activity recognition

KW - Calibration

KW - fall detection

KW - Feature extraction

KW - Floors

KW - Hidden Markov models

KW - hidden Markov models

KW - Injuries

KW - Senior citizens

KW - signal detection

KW - wearable sensors

UR - http://www.scopus.com/inward/record.url?scp=85038816171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038816171&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2017.2782079

DO - 10.1109/JBHI.2017.2782079

M3 - Article

C2 - 29990227

AN - SCOPUS:85038816171

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

ER -