A novel adaptive, real-time algorithm to detect gait events from wearable sensors

Noelia Chia Bejarano, Emilia Ambrosini, Alessandra Pedrocchi, Giancarlo Ferrigno, Marco Monticone, Simona Ferrante

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

A real-time, adaptive algorithm based on two inertial and magnetic sensors placed on the shanks was developed for gait-event detection. For each leg, the algorithm detected the Initial Contact (IC), as the minimum of the flexion/extension angle, and the End Contact (EC) and the Mid-Swing (MS), as minimum and maximum of the angular velocity, respectively. The algorithm consisted of calibration, real-time detection, and step-by-step update. Data collected from 22 healthy subjects (21 to 85 years) walking at three self-selected speeds were used to validate the algorithm against the GaitRite system. Comparable levels of accuracy and significantly lower detection delays were achieved with respect to other published methods. The algorithm robustness was tested on ten healthy subjects performing sudden speed changes and on ten stroke subjects (43 to 89 years). For healthy subjects, F1-scores of 1 and mean detection delays lower than 14 ms were obtained. For stroke subjects, F1-scores of 0.998 and 0.944 were obtained for IC and EC, respectively, with mean detection delays always below 31 ms. The algorithm accurately detected gait events in real time from a heterogeneous dataset of gait patterns and paves the way for the design of closed-loop controllers for customized gait trainings and/or assistive devices.

Original languageEnglish
Article number6862063
Pages (from-to)413-422
Number of pages10
JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume23
Issue number3
DOIs
Publication statusPublished - May 1 2015

Fingerprint

Gait
Healthy Volunteers
Magnetic sensors
Stroke
Self-Help Devices
Angular velocity
Adaptive algorithms
Calibration
Walking
Wearable sensors
Leg
Controllers

Keywords

  • Ambulatory gait system
  • Hemiparetic gait
  • Inertial and magnetic sensors
  • Real-time signal processing
  • Temporal gait parameters

ASJC Scopus subject areas

  • Neuroscience(all)
  • Computer Science Applications
  • Biomedical Engineering
  • Medicine(all)

Cite this

Bejarano, N. C., Ambrosini, E., Pedrocchi, A., Ferrigno, G., Monticone, M., & Ferrante, S. (2015). A novel adaptive, real-time algorithm to detect gait events from wearable sensors. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 23(3), 413-422. [6862063]. https://doi.org/10.1109/TNSRE.2014.2337914

A novel adaptive, real-time algorithm to detect gait events from wearable sensors. / Bejarano, Noelia Chia; Ambrosini, Emilia; Pedrocchi, Alessandra; Ferrigno, Giancarlo; Monticone, Marco; Ferrante, Simona.

In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 23, No. 3, 6862063, 01.05.2015, p. 413-422.

Research output: Contribution to journalArticle

Bejarano, NC, Ambrosini, E, Pedrocchi, A, Ferrigno, G, Monticone, M & Ferrante, S 2015, 'A novel adaptive, real-time algorithm to detect gait events from wearable sensors', IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 23, no. 3, 6862063, pp. 413-422. https://doi.org/10.1109/TNSRE.2014.2337914
Bejarano, Noelia Chia ; Ambrosini, Emilia ; Pedrocchi, Alessandra ; Ferrigno, Giancarlo ; Monticone, Marco ; Ferrante, Simona. / A novel adaptive, real-time algorithm to detect gait events from wearable sensors. In: IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2015 ; Vol. 23, No. 3. pp. 413-422.
@article{7ba3651df479428583be961c0c604b67,
title = "A novel adaptive, real-time algorithm to detect gait events from wearable sensors",
abstract = "A real-time, adaptive algorithm based on two inertial and magnetic sensors placed on the shanks was developed for gait-event detection. For each leg, the algorithm detected the Initial Contact (IC), as the minimum of the flexion/extension angle, and the End Contact (EC) and the Mid-Swing (MS), as minimum and maximum of the angular velocity, respectively. The algorithm consisted of calibration, real-time detection, and step-by-step update. Data collected from 22 healthy subjects (21 to 85 years) walking at three self-selected speeds were used to validate the algorithm against the GaitRite system. Comparable levels of accuracy and significantly lower detection delays were achieved with respect to other published methods. The algorithm robustness was tested on ten healthy subjects performing sudden speed changes and on ten stroke subjects (43 to 89 years). For healthy subjects, F1-scores of 1 and mean detection delays lower than 14 ms were obtained. For stroke subjects, F1-scores of 0.998 and 0.944 were obtained for IC and EC, respectively, with mean detection delays always below 31 ms. The algorithm accurately detected gait events in real time from a heterogeneous dataset of gait patterns and paves the way for the design of closed-loop controllers for customized gait trainings and/or assistive devices.",
keywords = "Ambulatory gait system, Hemiparetic gait, Inertial and magnetic sensors, Real-time signal processing, Temporal gait parameters",
author = "Bejarano, {Noelia Chia} and Emilia Ambrosini and Alessandra Pedrocchi and Giancarlo Ferrigno and Marco Monticone and Simona Ferrante",
year = "2015",
month = "5",
day = "1",
doi = "10.1109/TNSRE.2014.2337914",
language = "English",
volume = "23",
pages = "413--422",
journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",
issn = "1534-4320",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - A novel adaptive, real-time algorithm to detect gait events from wearable sensors

AU - Bejarano, Noelia Chia

AU - Ambrosini, Emilia

AU - Pedrocchi, Alessandra

AU - Ferrigno, Giancarlo

AU - Monticone, Marco

AU - Ferrante, Simona

PY - 2015/5/1

Y1 - 2015/5/1

N2 - A real-time, adaptive algorithm based on two inertial and magnetic sensors placed on the shanks was developed for gait-event detection. For each leg, the algorithm detected the Initial Contact (IC), as the minimum of the flexion/extension angle, and the End Contact (EC) and the Mid-Swing (MS), as minimum and maximum of the angular velocity, respectively. The algorithm consisted of calibration, real-time detection, and step-by-step update. Data collected from 22 healthy subjects (21 to 85 years) walking at three self-selected speeds were used to validate the algorithm against the GaitRite system. Comparable levels of accuracy and significantly lower detection delays were achieved with respect to other published methods. The algorithm robustness was tested on ten healthy subjects performing sudden speed changes and on ten stroke subjects (43 to 89 years). For healthy subjects, F1-scores of 1 and mean detection delays lower than 14 ms were obtained. For stroke subjects, F1-scores of 0.998 and 0.944 were obtained for IC and EC, respectively, with mean detection delays always below 31 ms. The algorithm accurately detected gait events in real time from a heterogeneous dataset of gait patterns and paves the way for the design of closed-loop controllers for customized gait trainings and/or assistive devices.

AB - A real-time, adaptive algorithm based on two inertial and magnetic sensors placed on the shanks was developed for gait-event detection. For each leg, the algorithm detected the Initial Contact (IC), as the minimum of the flexion/extension angle, and the End Contact (EC) and the Mid-Swing (MS), as minimum and maximum of the angular velocity, respectively. The algorithm consisted of calibration, real-time detection, and step-by-step update. Data collected from 22 healthy subjects (21 to 85 years) walking at three self-selected speeds were used to validate the algorithm against the GaitRite system. Comparable levels of accuracy and significantly lower detection delays were achieved with respect to other published methods. The algorithm robustness was tested on ten healthy subjects performing sudden speed changes and on ten stroke subjects (43 to 89 years). For healthy subjects, F1-scores of 1 and mean detection delays lower than 14 ms were obtained. For stroke subjects, F1-scores of 0.998 and 0.944 were obtained for IC and EC, respectively, with mean detection delays always below 31 ms. The algorithm accurately detected gait events in real time from a heterogeneous dataset of gait patterns and paves the way for the design of closed-loop controllers for customized gait trainings and/or assistive devices.

KW - Ambulatory gait system

KW - Hemiparetic gait

KW - Inertial and magnetic sensors

KW - Real-time signal processing

KW - Temporal gait parameters

UR - http://www.scopus.com/inward/record.url?scp=84929299073&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929299073&partnerID=8YFLogxK

U2 - 10.1109/TNSRE.2014.2337914

DO - 10.1109/TNSRE.2014.2337914

M3 - Article

VL - 23

SP - 413

EP - 422

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

SN - 1534-4320

IS - 3

M1 - 6862063

ER -