Accurate ride comfort estimation combining accelerometer measurements, anthropometric data and neural networks

Maciej Piotr Cieslak, Stratis Kanarachos, Cyriel Diels, Mike Blundell, Anthony Baxendale, Mark Burnett

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Ride comfort can heavily influence user experience and therefore comprises one of the most important vehicle design targets. Although ride comfort has been heavily researched, there is still no definite solution to its accurate estimation. This can be attributed, to a large extent, to the subjective nature of the problem. Aim of this study was to explore the use of neural networks for the accurate estimation of ride comfort by combining anthropometric data and acceleration measurements. Different acceleration inputs, neural network architectures, training algorithms and objective functions were systematically investigated, and optimal parameters were derived. New insight into the influence of anthropometric data on ride comfort has been gained. The results indicate that the proposed method improves the accuracy of subjective ride comfort estimation compared to current standards. Neural networks were trained using data derived from a range of field trials involving ten participants, on public roads and controlled environment. A clustering and sensitivity analysis complements the study and identifies the most important factors influencing subjective ride comfort evaluation.

Original languageEnglish
Pages (from-to)(In-press)
Number of pages16
JournalNeural Computing and Applications
Volume(In-press)
Early online date30 Jul 2019
DOIs
Publication statusE-pub ahead of print - 30 Jul 2019

Fingerprint

Accelerometers
Neural networks
Acceleration measurement
Network architecture
Sensitivity analysis

Keywords

  • Comfort perception
  • Neural networks
  • Ride
  • Vibration

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Accurate ride comfort estimation combining accelerometer measurements, anthropometric data and neural networks. / Cieslak, Maciej Piotr; Kanarachos, Stratis; Diels, Cyriel; Blundell, Mike; Baxendale, Anthony ; Burnett, Mark.

In: Neural Computing and Applications, Vol. (In-press), 30.07.2019, p. (In-press).

Research output: Contribution to journalArticle

@article{be3c9ce34b3c45c1b6f5d5237df954bb,
title = "Accurate ride comfort estimation combining accelerometer measurements, anthropometric data and neural networks",
abstract = "Ride comfort can heavily influence user experience and therefore comprises one of the most important vehicle design targets. Although ride comfort has been heavily researched, there is still no definite solution to its accurate estimation. This can be attributed, to a large extent, to the subjective nature of the problem. Aim of this study was to explore the use of neural networks for the accurate estimation of ride comfort by combining anthropometric data and acceleration measurements. Different acceleration inputs, neural network architectures, training algorithms and objective functions were systematically investigated, and optimal parameters were derived. New insight into the influence of anthropometric data on ride comfort has been gained. The results indicate that the proposed method improves the accuracy of subjective ride comfort estimation compared to current standards. Neural networks were trained using data derived from a range of field trials involving ten participants, on public roads and controlled environment. A clustering and sensitivity analysis complements the study and identifies the most important factors influencing subjective ride comfort evaluation.",
keywords = "Comfort perception, Neural networks, Ride, Vibration",
author = "Cieslak, {Maciej Piotr} and Stratis Kanarachos and Cyriel Diels and Mike Blundell and Anthony Baxendale and Mark Burnett",
year = "2019",
month = "7",
day = "30",
doi = "10.1007/s00521-019-04351-1",
language = "English",
volume = "(In-press)",
pages = "(In--press)",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - Accurate ride comfort estimation combining accelerometer measurements, anthropometric data and neural networks

AU - Cieslak, Maciej Piotr

AU - Kanarachos, Stratis

AU - Diels, Cyriel

AU - Blundell, Mike

AU - Baxendale, Anthony

AU - Burnett, Mark

PY - 2019/7/30

Y1 - 2019/7/30

N2 - Ride comfort can heavily influence user experience and therefore comprises one of the most important vehicle design targets. Although ride comfort has been heavily researched, there is still no definite solution to its accurate estimation. This can be attributed, to a large extent, to the subjective nature of the problem. Aim of this study was to explore the use of neural networks for the accurate estimation of ride comfort by combining anthropometric data and acceleration measurements. Different acceleration inputs, neural network architectures, training algorithms and objective functions were systematically investigated, and optimal parameters were derived. New insight into the influence of anthropometric data on ride comfort has been gained. The results indicate that the proposed method improves the accuracy of subjective ride comfort estimation compared to current standards. Neural networks were trained using data derived from a range of field trials involving ten participants, on public roads and controlled environment. A clustering and sensitivity analysis complements the study and identifies the most important factors influencing subjective ride comfort evaluation.

AB - Ride comfort can heavily influence user experience and therefore comprises one of the most important vehicle design targets. Although ride comfort has been heavily researched, there is still no definite solution to its accurate estimation. This can be attributed, to a large extent, to the subjective nature of the problem. Aim of this study was to explore the use of neural networks for the accurate estimation of ride comfort by combining anthropometric data and acceleration measurements. Different acceleration inputs, neural network architectures, training algorithms and objective functions were systematically investigated, and optimal parameters were derived. New insight into the influence of anthropometric data on ride comfort has been gained. The results indicate that the proposed method improves the accuracy of subjective ride comfort estimation compared to current standards. Neural networks were trained using data derived from a range of field trials involving ten participants, on public roads and controlled environment. A clustering and sensitivity analysis complements the study and identifies the most important factors influencing subjective ride comfort evaluation.

KW - Comfort perception

KW - Neural networks

KW - Ride

KW - Vibration

UR - http://www.scopus.com/inward/record.url?scp=85069934171&partnerID=8YFLogxK

U2 - 10.1007/s00521-019-04351-1

DO - 10.1007/s00521-019-04351-1

M3 - Article

VL - (In-press)

SP - (In-press)

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

ER -