Lift movement detection with a QDA classifier for an active hip exoskeleton

Baojun Chen, Lorenzo Grazi, Francesco Lanotte, Nicola Vitiello, Simona Crea

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

To provide assistance with an active exoskeleton, the control system of the device has to automatically detect the onset of the user’s movement and provide timely assistance, according to the recognized movement. In this paper, we present an algorithm designed to detect the lift movement with an active pelvis exoskeleton, based on a quadratic-discriminant-analysis classifier combined with a rule-based algorithm. The algorithm relies on sensory information acquired from the sensory apparatus of the exoskeleton, without needing additional sensors to be placed on the user’s body. The algorithm was validated in experiments with seven healthy subjects. Participants were requested to execute different actions, i.e. lift and lower a load, stand up, sit down and walk, while wearing the exoskeleton. On average, the algorithm showed an accuracy of 98.7 ± 0.6% in recognizing the lift task; such performance make it suitable for use in real application scenarios.

LanguageEnglish
Title of host publicationBiosystems and Biorobotics
PublisherSpringer International Publishing AG
Pages224-228
Number of pages5
DOIs
Publication statusPublished - Jan 1 2019

Publication series

NameBiosystems and Biorobotics
Volume22
ISSN (Print)2195-3562
ISSN (Electronic)2195-3570

Fingerprint

Classifiers
Discriminant analysis
Control systems
Sensors
Experiments

ASJC Scopus subject areas

  • Biomedical Engineering
  • Mechanical Engineering
  • Artificial Intelligence

Cite this

Chen, B., Grazi, L., Lanotte, F., Vitiello, N., & Crea, S. (2019). Lift movement detection with a QDA classifier for an active hip exoskeleton. In Biosystems and Biorobotics (pp. 224-228). (Biosystems and Biorobotics; Vol. 22). Springer International Publishing AG. https://doi.org/10.1007/978-3-030-01887-0_43

Lift movement detection with a QDA classifier for an active hip exoskeleton. / Chen, Baojun; Grazi, Lorenzo; Lanotte, Francesco; Vitiello, Nicola; Crea, Simona.

Biosystems and Biorobotics. Springer International Publishing AG, 2019. p. 224-228 (Biosystems and Biorobotics; Vol. 22).

Research output: Chapter in Book/Report/Conference proceedingChapter

Chen, B, Grazi, L, Lanotte, F, Vitiello, N & Crea, S 2019, Lift movement detection with a QDA classifier for an active hip exoskeleton. in Biosystems and Biorobotics. Biosystems and Biorobotics, vol. 22, Springer International Publishing AG, pp. 224-228. https://doi.org/10.1007/978-3-030-01887-0_43
Chen B, Grazi L, Lanotte F, Vitiello N, Crea S. Lift movement detection with a QDA classifier for an active hip exoskeleton. In Biosystems and Biorobotics. Springer International Publishing AG. 2019. p. 224-228. (Biosystems and Biorobotics). https://doi.org/10.1007/978-3-030-01887-0_43
Chen, Baojun ; Grazi, Lorenzo ; Lanotte, Francesco ; Vitiello, Nicola ; Crea, Simona. / Lift movement detection with a QDA classifier for an active hip exoskeleton. Biosystems and Biorobotics. Springer International Publishing AG, 2019. pp. 224-228 (Biosystems and Biorobotics).
@inbook{d78733bae8b14c0882d8e77059b94613,
title = "Lift movement detection with a QDA classifier for an active hip exoskeleton",
abstract = "To provide assistance with an active exoskeleton, the control system of the device has to automatically detect the onset of the user’s movement and provide timely assistance, according to the recognized movement. In this paper, we present an algorithm designed to detect the lift movement with an active pelvis exoskeleton, based on a quadratic-discriminant-analysis classifier combined with a rule-based algorithm. The algorithm relies on sensory information acquired from the sensory apparatus of the exoskeleton, without needing additional sensors to be placed on the user’s body. The algorithm was validated in experiments with seven healthy subjects. Participants were requested to execute different actions, i.e. lift and lower a load, stand up, sit down and walk, while wearing the exoskeleton. On average, the algorithm showed an accuracy of 98.7 ± 0.6{\%} in recognizing the lift task; such performance make it suitable for use in real application scenarios.",
author = "Baojun Chen and Lorenzo Grazi and Francesco Lanotte and Nicola Vitiello and Simona Crea",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-3-030-01887-0_43",
language = "English",
series = "Biosystems and Biorobotics",
publisher = "Springer International Publishing AG",
pages = "224--228",
booktitle = "Biosystems and Biorobotics",
address = "Switzerland",

}

TY - CHAP

T1 - Lift movement detection with a QDA classifier for an active hip exoskeleton

AU - Chen, Baojun

AU - Grazi, Lorenzo

AU - Lanotte, Francesco

AU - Vitiello, Nicola

AU - Crea, Simona

PY - 2019/1/1

Y1 - 2019/1/1

N2 - To provide assistance with an active exoskeleton, the control system of the device has to automatically detect the onset of the user’s movement and provide timely assistance, according to the recognized movement. In this paper, we present an algorithm designed to detect the lift movement with an active pelvis exoskeleton, based on a quadratic-discriminant-analysis classifier combined with a rule-based algorithm. The algorithm relies on sensory information acquired from the sensory apparatus of the exoskeleton, without needing additional sensors to be placed on the user’s body. The algorithm was validated in experiments with seven healthy subjects. Participants were requested to execute different actions, i.e. lift and lower a load, stand up, sit down and walk, while wearing the exoskeleton. On average, the algorithm showed an accuracy of 98.7 ± 0.6% in recognizing the lift task; such performance make it suitable for use in real application scenarios.

AB - To provide assistance with an active exoskeleton, the control system of the device has to automatically detect the onset of the user’s movement and provide timely assistance, according to the recognized movement. In this paper, we present an algorithm designed to detect the lift movement with an active pelvis exoskeleton, based on a quadratic-discriminant-analysis classifier combined with a rule-based algorithm. The algorithm relies on sensory information acquired from the sensory apparatus of the exoskeleton, without needing additional sensors to be placed on the user’s body. The algorithm was validated in experiments with seven healthy subjects. Participants were requested to execute different actions, i.e. lift and lower a load, stand up, sit down and walk, while wearing the exoskeleton. On average, the algorithm showed an accuracy of 98.7 ± 0.6% in recognizing the lift task; such performance make it suitable for use in real application scenarios.

UR - http://www.scopus.com/inward/record.url?scp=85055017060&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055017060&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-01887-0_43

DO - 10.1007/978-3-030-01887-0_43

M3 - Chapter

T3 - Biosystems and Biorobotics

SP - 224

EP - 228

BT - Biosystems and Biorobotics

PB - Springer International Publishing AG

ER -