Component-level tuning of kinematic features from composite therapist impressions of movement quality

Vinay Venkataraman, Pavan Turaga, Michael Baran, Nicole Lehrer, Tingfang Du, Long Cheng, Thanassis Rikakis, Steven L. Wolf

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this paper, we propose a general framework for tuning component-level kinematic features using therapists overall impressions ofmovement quality, in the context of a home-based adaptive mixed reality rehabilitation (HAMRR) system. We propose a linear combination of nonlinear kinematic features to model wrist movement, and propose an approach to learn feature thresholds and weights using high-level labels of overallmovement quality provided by a therapist. The kinematic features are chosen such that they correlate with the quality of wrist movements to clinical assessment scores. Further, the proposed features are designed to be reliably extracted from an inexpensive and portable motion capture system using a single reflective marker on the wrist. Using a dataset collected from ten stroke survivors, we demonstrate that the framework can be reliably used for movement quality assessment in HAMRR systems. The system is currently being deployed for large-scale evaluations, and will represent an increasingly important application area of motion capture and activity analysis.

Original languageEnglish (US)
Article number6967759
Pages (from-to)143-152
Number of pages10
JournalIEEE Journal of Biomedical and Health Informatics
Volume20
Issue number1
DOIs
StatePublished - Jan 1 2016

Fingerprint

Wrist
Biomechanical Phenomena
Kinematics
Tuning
Patient rehabilitation
Composite materials
Rehabilitation
Labels
Stroke
Weights and Measures

Keywords

  • Kinematic features
  • Movement quality assessment
  • Stroke rehabilitation

ASJC Scopus subject areas

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Health Information Management

Cite this

Component-level tuning of kinematic features from composite therapist impressions of movement quality. / Venkataraman, Vinay; Turaga, Pavan; Baran, Michael; Lehrer, Nicole; Du, Tingfang; Cheng, Long; Rikakis, Thanassis; Wolf, Steven L.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 20, No. 1, 6967759, 01.01.2016, p. 143-152.

Research output: Contribution to journalArticle

Venkataraman, Vinay ; Turaga, Pavan ; Baran, Michael ; Lehrer, Nicole ; Du, Tingfang ; Cheng, Long ; Rikakis, Thanassis ; Wolf, Steven L. / Component-level tuning of kinematic features from composite therapist impressions of movement quality. In: IEEE Journal of Biomedical and Health Informatics. 2016 ; Vol. 20, No. 1. pp. 143-152.
@article{d36aca4f050e41ce8a8a297520269126,
title = "Component-level tuning of kinematic features from composite therapist impressions of movement quality",
abstract = "In this paper, we propose a general framework for tuning component-level kinematic features using therapists overall impressions ofmovement quality, in the context of a home-based adaptive mixed reality rehabilitation (HAMRR) system. We propose a linear combination of nonlinear kinematic features to model wrist movement, and propose an approach to learn feature thresholds and weights using high-level labels of overallmovement quality provided by a therapist. The kinematic features are chosen such that they correlate with the quality of wrist movements to clinical assessment scores. Further, the proposed features are designed to be reliably extracted from an inexpensive and portable motion capture system using a single reflective marker on the wrist. Using a dataset collected from ten stroke survivors, we demonstrate that the framework can be reliably used for movement quality assessment in HAMRR systems. The system is currently being deployed for large-scale evaluations, and will represent an increasingly important application area of motion capture and activity analysis.",
keywords = "Kinematic features, Movement quality assessment, Stroke rehabilitation",
author = "Vinay Venkataraman and Pavan Turaga and Michael Baran and Nicole Lehrer and Tingfang Du and Long Cheng and Thanassis Rikakis and Wolf, {Steven L.}",
year = "2016",
month = "1",
day = "1",
doi = "10.1109/JBHI.2014.2375206",
language = "English (US)",
volume = "20",
pages = "143--152",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Component-level tuning of kinematic features from composite therapist impressions of movement quality

AU - Venkataraman, Vinay

AU - Turaga, Pavan

AU - Baran, Michael

AU - Lehrer, Nicole

AU - Du, Tingfang

AU - Cheng, Long

AU - Rikakis, Thanassis

AU - Wolf, Steven L.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - In this paper, we propose a general framework for tuning component-level kinematic features using therapists overall impressions ofmovement quality, in the context of a home-based adaptive mixed reality rehabilitation (HAMRR) system. We propose a linear combination of nonlinear kinematic features to model wrist movement, and propose an approach to learn feature thresholds and weights using high-level labels of overallmovement quality provided by a therapist. The kinematic features are chosen such that they correlate with the quality of wrist movements to clinical assessment scores. Further, the proposed features are designed to be reliably extracted from an inexpensive and portable motion capture system using a single reflective marker on the wrist. Using a dataset collected from ten stroke survivors, we demonstrate that the framework can be reliably used for movement quality assessment in HAMRR systems. The system is currently being deployed for large-scale evaluations, and will represent an increasingly important application area of motion capture and activity analysis.

AB - In this paper, we propose a general framework for tuning component-level kinematic features using therapists overall impressions ofmovement quality, in the context of a home-based adaptive mixed reality rehabilitation (HAMRR) system. We propose a linear combination of nonlinear kinematic features to model wrist movement, and propose an approach to learn feature thresholds and weights using high-level labels of overallmovement quality provided by a therapist. The kinematic features are chosen such that they correlate with the quality of wrist movements to clinical assessment scores. Further, the proposed features are designed to be reliably extracted from an inexpensive and portable motion capture system using a single reflective marker on the wrist. Using a dataset collected from ten stroke survivors, we demonstrate that the framework can be reliably used for movement quality assessment in HAMRR systems. The system is currently being deployed for large-scale evaluations, and will represent an increasingly important application area of motion capture and activity analysis.

KW - Kinematic features

KW - Movement quality assessment

KW - Stroke rehabilitation

UR - http://www.scopus.com/inward/record.url?scp=84971623048&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84971623048&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2014.2375206

DO - 10.1109/JBHI.2014.2375206

M3 - Article

VL - 20

SP - 143

EP - 152

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 1

M1 - 6967759

ER -