An event-triggered machine learning approach for accelerometer-based fall detection

I Putu Edy Suardiyana Putra, James Brusey, Elena Gaura, Rein Vesilo

Research output: Contribution to journalArticle

15 Citations (Scopus)
36 Downloads (Pure)

Abstract

The fixed-size non-overlapping sliding window (FNSW)
and fixed-size overlapping sliding window (FOSW)
approaches are the most commonly used
data-segmentation techniques in machine
learning-based fall detection using accelerometer
sensors. However, these techniques do not segment by
fall stages (pre-impact, impact, and post-impact)
and thus useful information is lost, which may
reduce the detection rate of the
classifier. Aligning the segment with the fall stage
is difficult, as the segment size varies. We propose
an event-triggered machine learning (EvenT-ML)
approach that aligns each fall stage so that the
characteristic features of the fall stages are more
easily recognized. To evaluate our approach, two
publicly accessible datasets were
used. Classification and regression tree (CART),
k-nearest neighbor (k-NN), logistic regression (LR),
and the support vector machine (SVM) were used to
train the classifiers. EvenT-ML gives classifier
F-scores of 98% for a chest-worn sensor and
92% for a waist-worn sensor, and significantly
reduces the computational cost compared with the
FNSW- and FOSW-based approaches, with reductions of
up to 8-fold and 78-fold, respectively. EvenT-ML
achieves a significantly better F-score than
existing fall detection approaches. These results
indicate that aligning feature segments with fall
stages significantly increases the detection rate
and reduces the computational cost.
Original languageEnglish
Pages (from-to)20
JournalSensors
Volume18
Issue number1
Early online date22 Dec 2017
DOIs
Publication statusPublished - 1 Jan 2018

Fingerprint

machine learning
accelerometers
Accelerometers
Learning systems
Classifiers
sliding
Costs and Cost Analysis
classifiers
Sensors
Thorax
Logistic Models
regression analysis
sensors
Support vector machines
Logistics
Costs
costs
chest
logistics
Machine Learning

Keywords

  • fall detection
  • segmentation technique
  • fall stages
  • machine learning
  • computational cost

Cite this

An event-triggered machine learning approach for accelerometer-based fall detection. / Putra, I Putu Edy Suardiyana; Brusey, James; Gaura, Elena; Vesilo, Rein.

In: Sensors, Vol. 18, No. 1, 01.01.2018, p. 20.

Research output: Contribution to journalArticle

Putra, I Putu Edy Suardiyana ; Brusey, James ; Gaura, Elena ; Vesilo, Rein. / An event-triggered machine learning approach for accelerometer-based fall detection. In: Sensors. 2018 ; Vol. 18, No. 1. pp. 20.
@article{add94e6d908242548a9969cae0676479,
title = "An event-triggered machine learning approach for accelerometer-based fall detection",
abstract = "The fixed-size non-overlapping sliding window (FNSW) and fixed-size overlapping sliding window (FOSW) approaches are the most commonly used data-segmentation techniques in machine learning-based fall detection using accelerometer sensors. However, these techniques do not segment by fall stages (pre-impact, impact, and post-impact) and thus useful information is lost, which may reduce the detection rate of the classifier. Aligning the segment with the fall stage is difficult, as the segment size varies. We propose an event-triggered machine learning (EvenT-ML) approach that aligns each fall stage so that the characteristic features of the fall stages are more easily recognized. To evaluate our approach, two publicly accessible datasets were used. Classification and regression tree (CART), k-nearest neighbor (k-NN), logistic regression (LR), and the support vector machine (SVM) were used to train the classifiers. EvenT-ML gives classifier F-scores of 98{\%} for a chest-worn sensor and 92{\%} for a waist-worn sensor, and significantly reduces the computational cost compared with the FNSW- and FOSW-based approaches, with reductions of up to 8-fold and 78-fold, respectively. EvenT-ML achieves a significantly better F-score than existing fall detection approaches. These results indicate that aligning feature segments with fall stages significantly increases the detection rate and reduces the computational cost.",
keywords = "fall detection, segmentation technique, fall stages, machine learning, computational cost",
author = "Putra, {I Putu Edy Suardiyana} and James Brusey and Elena Gaura and Rein Vesilo",
year = "2018",
month = "1",
day = "1",
doi = "10.3390/s18010020",
language = "English",
volume = "18",
pages = "20",
journal = "Sensors",
issn = "1424-3210",
publisher = "MDPI",
number = "1",

}

TY - JOUR

T1 - An event-triggered machine learning approach for accelerometer-based fall detection

AU - Putra, I Putu Edy Suardiyana

AU - Brusey, James

AU - Gaura, Elena

AU - Vesilo, Rein

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The fixed-size non-overlapping sliding window (FNSW) and fixed-size overlapping sliding window (FOSW) approaches are the most commonly used data-segmentation techniques in machine learning-based fall detection using accelerometer sensors. However, these techniques do not segment by fall stages (pre-impact, impact, and post-impact) and thus useful information is lost, which may reduce the detection rate of the classifier. Aligning the segment with the fall stage is difficult, as the segment size varies. We propose an event-triggered machine learning (EvenT-ML) approach that aligns each fall stage so that the characteristic features of the fall stages are more easily recognized. To evaluate our approach, two publicly accessible datasets were used. Classification and regression tree (CART), k-nearest neighbor (k-NN), logistic regression (LR), and the support vector machine (SVM) were used to train the classifiers. EvenT-ML gives classifier F-scores of 98% for a chest-worn sensor and 92% for a waist-worn sensor, and significantly reduces the computational cost compared with the FNSW- and FOSW-based approaches, with reductions of up to 8-fold and 78-fold, respectively. EvenT-ML achieves a significantly better F-score than existing fall detection approaches. These results indicate that aligning feature segments with fall stages significantly increases the detection rate and reduces the computational cost.

AB - The fixed-size non-overlapping sliding window (FNSW) and fixed-size overlapping sliding window (FOSW) approaches are the most commonly used data-segmentation techniques in machine learning-based fall detection using accelerometer sensors. However, these techniques do not segment by fall stages (pre-impact, impact, and post-impact) and thus useful information is lost, which may reduce the detection rate of the classifier. Aligning the segment with the fall stage is difficult, as the segment size varies. We propose an event-triggered machine learning (EvenT-ML) approach that aligns each fall stage so that the characteristic features of the fall stages are more easily recognized. To evaluate our approach, two publicly accessible datasets were used. Classification and regression tree (CART), k-nearest neighbor (k-NN), logistic regression (LR), and the support vector machine (SVM) were used to train the classifiers. EvenT-ML gives classifier F-scores of 98% for a chest-worn sensor and 92% for a waist-worn sensor, and significantly reduces the computational cost compared with the FNSW- and FOSW-based approaches, with reductions of up to 8-fold and 78-fold, respectively. EvenT-ML achieves a significantly better F-score than existing fall detection approaches. These results indicate that aligning feature segments with fall stages significantly increases the detection rate and reduces the computational cost.

KW - fall detection

KW - segmentation technique

KW - fall stages

KW - machine learning

KW - computational cost

U2 - 10.3390/s18010020

DO - 10.3390/s18010020

M3 - Article

VL - 18

SP - 20

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 1

ER -