Optimal Parameter Exploration for Online Change-Point Detection in Activity Monitoring Using Genetic Algorithms

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In recent years, smart phones with inbuilt sensors have become popular devices to facilitate activity recognition. The sensors capture a large amount of data, containing meaningful events, in a short period of time. The change points in this data are used to specify transitions to distinct events and can be used in various scenarios such as identifying change in a patient’s vital signs in the medical domain or requesting activity labels for generating real-world labeled activity datasets. Our work focuses on change-point detection to identify a transition from one activity to another. Within this paper, we extend our previous work on multivariate exponentially weighted moving average (MEWMA) algorithm by using a genetic algorithm (GA) to identify the optimal set of parameters for online change-point detection. The proposed technique finds the maximum accuracy and F_measure by optimizing the different parameters of the MEWMA, which subsequently identifies the exact location of the change point from an existing activity to a new one. Optimal parameter selection facilitates an algorithm to detect accurate change points and minimize false alarms. Results have been evaluated based on two real datasets of accelerometer data collected from a set of different activities from two users, with a high degree of accuracy from 99.4% to 99.8% and F_measure of up to 66.7%.
LanguageEnglish
JournalSensors
Volume16
Issue number11
DOIs
Publication statusPublished - 26 Oct 2016

Fingerprint

genetic algorithms
Genetic algorithms
Monitoring
Sensors
Accelerometers
Labels
Vital Signs
Equipment and Supplies
sensors
false alarms
accelerometers
Datasets
Smartphone

Keywords

  • multivariate change detection
  • activity monitoring
  • multivariate exponentially weighted moving average
  • accelerometer
  • Genetic Algorithm
  • change-point detection

Cite this

@article{cb6675b0f3374be5bb27b3440ca11007,
title = "Optimal Parameter Exploration for Online Change-Point Detection in Activity Monitoring Using Genetic Algorithms",
abstract = "In recent years, smart phones with inbuilt sensors have become popular devices to facilitate activity recognition. The sensors capture a large amount of data, containing meaningful events, in a short period of time. The change points in this data are used to specify transitions to distinct events and can be used in various scenarios such as identifying change in a patient’s vital signs in the medical domain or requesting activity labels for generating real-world labeled activity datasets. Our work focuses on change-point detection to identify a transition from one activity to another. Within this paper, we extend our previous work on multivariate exponentially weighted moving average (MEWMA) algorithm by using a genetic algorithm (GA) to identify the optimal set of parameters for online change-point detection. The proposed technique finds the maximum accuracy and F_measure by optimizing the different parameters of the MEWMA, which subsequently identifies the exact location of the change point from an existing activity to a new one. Optimal parameter selection facilitates an algorithm to detect accurate change points and minimize false alarms. Results have been evaluated based on two real datasets of accelerometer data collected from a set of different activities from two users, with a high degree of accuracy from 99.4{\%} to 99.8{\%} and F_measure of up to 66.7{\%}.",
keywords = "multivariate change detection, activity monitoring, multivariate exponentially weighted moving average, accelerometer, Genetic Algorithm, change-point detection",
author = "Naveed Khan and McClean, {Sally I} and Shuai Zhang and Nugent, {Chris D.}",
year = "2016",
month = "10",
day = "26",
doi = "10.3390/s16111784",
language = "English",
volume = "16",
journal = "Sensors",
issn = "1424-8220",
publisher = "MDPI",
number = "11",

}

TY - JOUR

T1 - Optimal Parameter Exploration for Online Change-Point Detection in Activity Monitoring Using Genetic Algorithms

AU - Khan, Naveed

AU - McClean, Sally I

AU - Zhang, Shuai

AU - Nugent, Chris D.

PY - 2016/10/26

Y1 - 2016/10/26

N2 - In recent years, smart phones with inbuilt sensors have become popular devices to facilitate activity recognition. The sensors capture a large amount of data, containing meaningful events, in a short period of time. The change points in this data are used to specify transitions to distinct events and can be used in various scenarios such as identifying change in a patient’s vital signs in the medical domain or requesting activity labels for generating real-world labeled activity datasets. Our work focuses on change-point detection to identify a transition from one activity to another. Within this paper, we extend our previous work on multivariate exponentially weighted moving average (MEWMA) algorithm by using a genetic algorithm (GA) to identify the optimal set of parameters for online change-point detection. The proposed technique finds the maximum accuracy and F_measure by optimizing the different parameters of the MEWMA, which subsequently identifies the exact location of the change point from an existing activity to a new one. Optimal parameter selection facilitates an algorithm to detect accurate change points and minimize false alarms. Results have been evaluated based on two real datasets of accelerometer data collected from a set of different activities from two users, with a high degree of accuracy from 99.4% to 99.8% and F_measure of up to 66.7%.

AB - In recent years, smart phones with inbuilt sensors have become popular devices to facilitate activity recognition. The sensors capture a large amount of data, containing meaningful events, in a short period of time. The change points in this data are used to specify transitions to distinct events and can be used in various scenarios such as identifying change in a patient’s vital signs in the medical domain or requesting activity labels for generating real-world labeled activity datasets. Our work focuses on change-point detection to identify a transition from one activity to another. Within this paper, we extend our previous work on multivariate exponentially weighted moving average (MEWMA) algorithm by using a genetic algorithm (GA) to identify the optimal set of parameters for online change-point detection. The proposed technique finds the maximum accuracy and F_measure by optimizing the different parameters of the MEWMA, which subsequently identifies the exact location of the change point from an existing activity to a new one. Optimal parameter selection facilitates an algorithm to detect accurate change points and minimize false alarms. Results have been evaluated based on two real datasets of accelerometer data collected from a set of different activities from two users, with a high degree of accuracy from 99.4% to 99.8% and F_measure of up to 66.7%.

KW - multivariate change detection

KW - activity monitoring

KW - multivariate exponentially weighted moving average

KW - accelerometer

KW - Genetic Algorithm

KW - change-point detection

U2 - 10.3390/s16111784

DO - 10.3390/s16111784

M3 - Article

VL - 16

JO - Sensors

T2 - Sensors

JF - Sensors

SN - 1424-8220

IS - 11

ER -