SOM clustering and modelling of Australian railway drivers’ sleep, wake, duty profiles

Irene L. Hudson, Shalem Y. Leemaqz, Susan Kim, David Darwent, Greg Roach, Drew Dawson

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Two SOM ANN approaches were used in a study of Australian railway drivers (RDs) to classify RDs’ sleep/wake states and their sleep duration time series profiles over 14 days follow-up. The first approach was a feature-based SOM approach that clustered the most frequently occurring patterns of sleep. The second created RD networks of sleep/wake/duty/break feature parameter vectors of between-states transition probabilities via a multivariate extension of the mixture transition distribution (MTD) model, accommodating covariate interactions. SOM/ANN found 4 clusters of RDs whose sleep profiles differed significantly. Generalised Additive Models for Location, Scale and Shape of the 2 sleep outcomes confirmed that break and sleep onset times, break duration and hours to next duty are significant effects which operate differentially across the groups. Generally sleep increases for next duty onset between 10 am and 4 pm, and when hours since break onset exceeds 1 day. These 2 factors were significant factors determining current sleep, which have differential impacts across the clusters. Some drivers groups catch up sleep after the night shift, while others do so before the night shift. Sleep is governed by the RD’s anticipatory behaviour of next scheduled duty onset and hours since break onset, and driver experience, age and domestic scenario. This has clear health and safety implications for the rail industry.

LanguageEnglish
Title of host publicationStudies in Computational Intelligence
PublisherSpringer Verlag
Pages235-279
Number of pages45
DOIs
Publication statusPublished - 1 Feb 2016

Publication series

NameStudies in Computational Intelligence
Volume628
ISSN (Print)1860-949X

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Hudson, I. L., Leemaqz, S. Y., Kim, S., Darwent, D., Roach, G., & Dawson, D. (2016). SOM clustering and modelling of Australian railway drivers’ sleep, wake, duty profiles. In Studies in Computational Intelligence (pp. 235-279). (Studies in Computational Intelligence; Vol. 628). Springer Verlag. https://doi.org/10.1007/978-3-319-28495-8_11
Hudson, Irene L. ; Leemaqz, Shalem Y. ; Kim, Susan ; Darwent, David ; Roach, Greg ; Dawson, Drew. / SOM clustering and modelling of Australian railway drivers’ sleep, wake, duty profiles. Studies in Computational Intelligence. Springer Verlag, 2016. pp. 235-279 (Studies in Computational Intelligence).
@inbook{9ed75e1b548541ec8b6f7a6be3103342,
title = "SOM clustering and modelling of Australian railway drivers’ sleep, wake, duty profiles",
abstract = "Two SOM ANN approaches were used in a study of Australian railway drivers (RDs) to classify RDs’ sleep/wake states and their sleep duration time series profiles over 14 days follow-up. The first approach was a feature-based SOM approach that clustered the most frequently occurring patterns of sleep. The second created RD networks of sleep/wake/duty/break feature parameter vectors of between-states transition probabilities via a multivariate extension of the mixture transition distribution (MTD) model, accommodating covariate interactions. SOM/ANN found 4 clusters of RDs whose sleep profiles differed significantly. Generalised Additive Models for Location, Scale and Shape of the 2 sleep outcomes confirmed that break and sleep onset times, break duration and hours to next duty are significant effects which operate differentially across the groups. Generally sleep increases for next duty onset between 10 am and 4 pm, and when hours since break onset exceeds 1 day. These 2 factors were significant factors determining current sleep, which have differential impacts across the clusters. Some drivers groups catch up sleep after the night shift, while others do so before the night shift. Sleep is governed by the RD’s anticipatory behaviour of next scheduled duty onset and hours since break onset, and driver experience, age and domestic scenario. This has clear health and safety implications for the rail industry.",
author = "Hudson, {Irene L.} and Leemaqz, {Shalem Y.} and Susan Kim and David Darwent and Greg Roach and Drew Dawson",
year = "2016",
month = "2",
day = "1",
doi = "10.1007/978-3-319-28495-8_11",
language = "English",
series = "Studies in Computational Intelligence",
publisher = "Springer Verlag",
pages = "235--279",
booktitle = "Studies in Computational Intelligence",

}

Hudson, IL, Leemaqz, SY, Kim, S, Darwent, D, Roach, G & Dawson, D 2016, SOM clustering and modelling of Australian railway drivers’ sleep, wake, duty profiles. in Studies in Computational Intelligence. Studies in Computational Intelligence, vol. 628, Springer Verlag, pp. 235-279. https://doi.org/10.1007/978-3-319-28495-8_11

SOM clustering and modelling of Australian railway drivers’ sleep, wake, duty profiles. / Hudson, Irene L.; Leemaqz, Shalem Y.; Kim, Susan; Darwent, David; Roach, Greg; Dawson, Drew.

Studies in Computational Intelligence. Springer Verlag, 2016. p. 235-279 (Studies in Computational Intelligence; Vol. 628).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - SOM clustering and modelling of Australian railway drivers’ sleep, wake, duty profiles

AU - Hudson, Irene L.

AU - Leemaqz, Shalem Y.

AU - Kim, Susan

AU - Darwent, David

AU - Roach, Greg

AU - Dawson, Drew

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Two SOM ANN approaches were used in a study of Australian railway drivers (RDs) to classify RDs’ sleep/wake states and their sleep duration time series profiles over 14 days follow-up. The first approach was a feature-based SOM approach that clustered the most frequently occurring patterns of sleep. The second created RD networks of sleep/wake/duty/break feature parameter vectors of between-states transition probabilities via a multivariate extension of the mixture transition distribution (MTD) model, accommodating covariate interactions. SOM/ANN found 4 clusters of RDs whose sleep profiles differed significantly. Generalised Additive Models for Location, Scale and Shape of the 2 sleep outcomes confirmed that break and sleep onset times, break duration and hours to next duty are significant effects which operate differentially across the groups. Generally sleep increases for next duty onset between 10 am and 4 pm, and when hours since break onset exceeds 1 day. These 2 factors were significant factors determining current sleep, which have differential impacts across the clusters. Some drivers groups catch up sleep after the night shift, while others do so before the night shift. Sleep is governed by the RD’s anticipatory behaviour of next scheduled duty onset and hours since break onset, and driver experience, age and domestic scenario. This has clear health and safety implications for the rail industry.

AB - Two SOM ANN approaches were used in a study of Australian railway drivers (RDs) to classify RDs’ sleep/wake states and their sleep duration time series profiles over 14 days follow-up. The first approach was a feature-based SOM approach that clustered the most frequently occurring patterns of sleep. The second created RD networks of sleep/wake/duty/break feature parameter vectors of between-states transition probabilities via a multivariate extension of the mixture transition distribution (MTD) model, accommodating covariate interactions. SOM/ANN found 4 clusters of RDs whose sleep profiles differed significantly. Generalised Additive Models for Location, Scale and Shape of the 2 sleep outcomes confirmed that break and sleep onset times, break duration and hours to next duty are significant effects which operate differentially across the groups. Generally sleep increases for next duty onset between 10 am and 4 pm, and when hours since break onset exceeds 1 day. These 2 factors were significant factors determining current sleep, which have differential impacts across the clusters. Some drivers groups catch up sleep after the night shift, while others do so before the night shift. Sleep is governed by the RD’s anticipatory behaviour of next scheduled duty onset and hours since break onset, and driver experience, age and domestic scenario. This has clear health and safety implications for the rail industry.

UR - http://www.scopus.com/inward/record.url?scp=84957561803&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-28495-8_11

DO - 10.1007/978-3-319-28495-8_11

M3 - Chapter

T3 - Studies in Computational Intelligence

SP - 235

EP - 279

BT - Studies in Computational Intelligence

PB - Springer Verlag

ER -

Hudson IL, Leemaqz SY, Kim S, Darwent D, Roach G, Dawson D. SOM clustering and modelling of Australian railway drivers’ sleep, wake, duty profiles. In Studies in Computational Intelligence. Springer Verlag. 2016. p. 235-279. (Studies in Computational Intelligence). https://doi.org/10.1007/978-3-319-28495-8_11