Using Genetic Algorithms for Optimal Change Point Detection in Activity Monitoring

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Activity Monitoring is a key feature of health and well-being assessment that has received increased consideration from the research community over the last few decades. Body worn sensors and smart devices are widely used in Activity Monitoring in order to capture and classify large amounts of data over short periods of time, in a relatively un-obtrusive manner. Change point detection is a technique at the core of the data processing of the sensory data recorded used to identify the transition from one underlying time series generation model to another. The sudden change in mean, variance or both may represent change point in time series data. Accurate and automatic change point detection in data is not only used to identify events (transition from one activity to another), however, can also be used for labelling activities to generate real world annotated datasets. This paper proposes a genetic algorithm (GA) that identifies the optimal set of parameters for a Multivariate Exponentially Weighted Moving Average (MEWMA) approach to change point detection. The proposed technique optimizes different parameters of the MEWMA in an effort to find the maximum F-measure, which subsequently identifies the exact location of the change point from an existing activity to a new one. Results have been evaluated based on real and synthetic datasets collected from accelerometer data during a set of 8 different activities for two users with a high degree of accuracy form 99.4% to 99.8% and F-measure to 66.7%.
LanguageEnglish
Title of host publication2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS)
Place of PublicationDublin, Ireland
Pages318-323
Number of pages6
Volume16248004
ISBN (Electronic)978-1-4673-9036-1
DOIs
Publication statusPublished - 18 Aug 2016

Fingerprint

genetic algorithm
monitoring
time series
accelerometer
detection
sensor
parameter

Cite this

Khan, N., McClean, S. I., Zhang, S., & Nugent, CD. (2016). Using Genetic Algorithms for Optimal Change Point Detection in Activity Monitoring. In 2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS) (Vol. 16248004, pp. 318-323). Dublin, Ireland. https://doi.org/10.1109/CBMS.2016.27
Khan, Naveed ; McClean, Sally I ; Zhang, Shuai ; Nugent, CD. / Using Genetic Algorithms for Optimal Change Point Detection in Activity Monitoring. 2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS). Vol. 16248004 Dublin, Ireland, 2016. pp. 318-323
@inproceedings{2fc20e1ca6b94d3e8f8d5795aa945aa7,
title = "Using Genetic Algorithms for Optimal Change Point Detection in Activity Monitoring",
abstract = "Activity Monitoring is a key feature of health and well-being assessment that has received increased consideration from the research community over the last few decades. Body worn sensors and smart devices are widely used in Activity Monitoring in order to capture and classify large amounts of data over short periods of time, in a relatively un-obtrusive manner. Change point detection is a technique at the core of the data processing of the sensory data recorded used to identify the transition from one underlying time series generation model to another. The sudden change in mean, variance or both may represent change point in time series data. Accurate and automatic change point detection in data is not only used to identify events (transition from one activity to another), however, can also be used for labelling activities to generate real world annotated datasets. This paper proposes a genetic algorithm (GA) that identifies the optimal set of parameters for a Multivariate Exponentially Weighted Moving Average (MEWMA) approach to change point detection. The proposed technique optimizes different parameters of the MEWMA in an effort to find the maximum F-measure, which subsequently identifies the exact location of the change point from an existing activity to a new one. Results have been evaluated based on real and synthetic datasets collected from accelerometer data during a set of 8 different activities for two users with a high degree of accuracy form 99.4{\%} to 99.8{\%} and F-measure to 66.7{\%}.",
author = "Naveed Khan and McClean, {Sally I} and Shuai Zhang and CD Nugent",
year = "2016",
month = "8",
day = "18",
doi = "10.1109/CBMS.2016.27",
language = "English",
isbn = "978-1-4673-9037-8",
volume = "16248004",
pages = "318--323",
booktitle = "2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS)",

}

Khan, N, McClean, SI, Zhang, S & Nugent, CD 2016, Using Genetic Algorithms for Optimal Change Point Detection in Activity Monitoring. in 2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS). vol. 16248004, Dublin, Ireland, pp. 318-323. https://doi.org/10.1109/CBMS.2016.27

Using Genetic Algorithms for Optimal Change Point Detection in Activity Monitoring. / Khan, Naveed; McClean, Sally I; Zhang, Shuai; Nugent, CD.

2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS). Vol. 16248004 Dublin, Ireland, 2016. p. 318-323.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

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

AU - Khan, Naveed

AU - McClean, Sally I

AU - Zhang, Shuai

AU - Nugent, CD

PY - 2016/8/18

Y1 - 2016/8/18

N2 - Activity Monitoring is a key feature of health and well-being assessment that has received increased consideration from the research community over the last few decades. Body worn sensors and smart devices are widely used in Activity Monitoring in order to capture and classify large amounts of data over short periods of time, in a relatively un-obtrusive manner. Change point detection is a technique at the core of the data processing of the sensory data recorded used to identify the transition from one underlying time series generation model to another. The sudden change in mean, variance or both may represent change point in time series data. Accurate and automatic change point detection in data is not only used to identify events (transition from one activity to another), however, can also be used for labelling activities to generate real world annotated datasets. This paper proposes a genetic algorithm (GA) that identifies the optimal set of parameters for a Multivariate Exponentially Weighted Moving Average (MEWMA) approach to change point detection. The proposed technique optimizes different parameters of the MEWMA in an effort to find the maximum F-measure, which subsequently identifies the exact location of the change point from an existing activity to a new one. Results have been evaluated based on real and synthetic datasets collected from accelerometer data during a set of 8 different activities for two users with a high degree of accuracy form 99.4% to 99.8% and F-measure to 66.7%.

AB - Activity Monitoring is a key feature of health and well-being assessment that has received increased consideration from the research community over the last few decades. Body worn sensors and smart devices are widely used in Activity Monitoring in order to capture and classify large amounts of data over short periods of time, in a relatively un-obtrusive manner. Change point detection is a technique at the core of the data processing of the sensory data recorded used to identify the transition from one underlying time series generation model to another. The sudden change in mean, variance or both may represent change point in time series data. Accurate and automatic change point detection in data is not only used to identify events (transition from one activity to another), however, can also be used for labelling activities to generate real world annotated datasets. This paper proposes a genetic algorithm (GA) that identifies the optimal set of parameters for a Multivariate Exponentially Weighted Moving Average (MEWMA) approach to change point detection. The proposed technique optimizes different parameters of the MEWMA in an effort to find the maximum F-measure, which subsequently identifies the exact location of the change point from an existing activity to a new one. Results have been evaluated based on real and synthetic datasets collected from accelerometer data during a set of 8 different activities for two users with a high degree of accuracy form 99.4% to 99.8% and F-measure to 66.7%.

U2 - 10.1109/CBMS.2016.27

DO - 10.1109/CBMS.2016.27

M3 - Conference contribution

SN - 978-1-4673-9037-8

VL - 16248004

SP - 318

EP - 323

BT - 2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS)

CY - Dublin, Ireland

ER -

Khan N, McClean SI, Zhang S, Nugent CD. Using Genetic Algorithms for Optimal Change Point Detection in Activity Monitoring. In 2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS). Vol. 16248004. Dublin, Ireland. 2016. p. 318-323 https://doi.org/10.1109/CBMS.2016.27