Estimating running kinematics variability with an IMU sensor placed on the runner's thorax

Zignoli, Andrea; Fruet, Damiano; Mourot, Laurent

doi:10.1109/star53492.2022.9859775

Cited by 3 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once the estimated stride frequency was available, both DFA-α and HG-D were computed as specified in the ’Temporal variables values’ Section. More details about the structure of the CNN can be found in [ 28 ]. All the Python scripts are available at the project repository ( https://bitbucket.org/andrea_zignoli/prissiv/src/np/src/ ).…”

Section: Methodsmentioning

confidence: 99%

“…Both DFA-α and HG-D were computed considering the first 10 minutes after the start of the single running condition following best-practice guidelines [4]. Additional results including DFA and HG-D calculations at different times (2,4,6,8) are available in the Additional Material https://drive.google.com/file/d/ 1y32xqVDioUXlzbsaLkgIL1JEVwg1kTXA/view?usp=sharingand in [28].…”

Section: Temporal Variables Values (Optogait)mentioning

confidence: 99%

“…The former was used to train the machine learning algorithm (i.e., to adjust the parameters of the model), whilst the latter was used to assess the accuracy of the model estimations. The technical details of the machine learning algorithm have been recently discussed and presented in peer-reviewed conference paper [28]. Here, they are briefly presented and summarized in Fig 1 . A 2-sec rolling window was used to select an input with fixed size every second.…”

Section: Other Estimation Strategies (Imu On the Thorax + Machine Lea...mentioning

confidence: 99%

“…In a preparatory technical work, the authors of this manuscript designed a machine learning model to predict running variability indices from a single IMU placed at the runner’s thorax level [ 28 ]. The focus of the work was on the technical details and on the accuracy of the algorithm estimations.…”

Section: Introductionmentioning

confidence: 99%

“…The present manuscript, which constitutes a natural expansion of the previous work, has two goals: 1) to present the values for indoor running variability at different speeds and treadmill inclinations collected with a gold-standard optoelectronic device, and 2) to present the comparison between three different possible estimation strategies for running kinematics and variability. The estimations strategies considered were: 1) the gold-standard optoelectronic device, 2) two IMUs placed on each foot of the runners, and 3) a single IMU placed on the runner’s thorax used as input for a 2-second time window machine learning algorithm (already presented in [ 28 ]) or for a 120-second time window machine learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Indoor running temporal variability for different running speeds, treadmill inclinations, and three different estimation strategies

2023

Self Cite

View full text Add to dashboard Cite

Inertial measurement units (IMU) constitute a light and cost-effective alternative to gold-standard measurement systems in the assessment of running temporal variables. IMU data collected on 20 runners running at different speeds (80, 90, 100, 110 and 120% of preferred running speed) and treadmill inclination (±2, ±5, and ±8%) were used here to predict the following temporal variables: stride frequency, duty factor, and two indices of running variability such as the detrended fluctuation analysis alpha (DFA-α) and the Higuchi’s D (HG-D). Three different estimation methodologies were compared: 1) a gold-standard optoelectronic device (which provided the reference values), 2) IMU placed on the runner’s feet, 3) a single IMU on the runner’s thorax used in conjunction with a machine learning algorithm with a short 2-second or a long 120-second window as input. A two-way ANOVA was used to test the presence of significant (p<0.05) differences due to the running condition or to the estimation methodology. The findings of this study suggest that using both IMU configurations for estimating stride frequency can be effective and comparable to the gold-standard. Additionally, the results indicate that the use of a single IMU on the thorax with a machine learning algorithm can lead to more accurate estimates of duty factor than the strategy of the IMU on the feet. However, caution should be exercised when using these techniques to measure running variability indices. Estimating DFA-α from a short 2-second time window was possible only in level running but not in downhill running and it could not accurately estimate HG-D across all running conditions. By taking a long 120-second window a machine learning algorithm could improve the accuracy in the estimation of DFA-α in all running conditions. By taking these factors into account, researchers and practitioners can make informed decisions about the use of IMU technology in measuring running biomechanics.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Temporal Variables Values (Optogait)mentioning

confidence: 99%

Section: Other Estimation Strategies (Imu On the Thorax + Machine Lea...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Indoor running temporal variability for different running speeds, treadmill inclinations, and three different estimation strategies

2023

Self Cite

View full text Add to dashboard Cite

show abstract

An Open-Source Wearable Sensor System for Measuring the Duty Factor of Runners

Lee,

Wang,

Lin

2024

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Intelligent Wearable Systems: Opportunities and Challenges in Health and Sports

Yang,

Amin,

Shihada

2024

ACM Comput. Surv.

View full text Add to dashboard Cite

Wearable devices or wearables, designed to be attached to the human body, can gather personalized real-time data and continuously monitor an individual’s health status and physiological disposition in a non-invasive manner. Intelligent wearables integrate advanced machine learning (ML) algorithms to process complex data patterns and provide accurate insights. As a result, intelligent wearables have emerged as a groundbreaking innovation in the fields of sports and health, introducing a new paradigm in kinematic analysis and patient data evaluation. For example, virtual coaches offer feedback on athletes’ performance, while virtual physicians assist in customizing medication for patients. This article provides an overview of various types of intelligent wearables and their applications in health and sports, categorizes ML algorithms, and introduces the wireless body area sensor network (WBASN) used for communication in wearable sensors. Additionally, we discuss potential challenges and development directions that could shape the future of intelligent wearables and propose effective solutions for their continued enhancement. This article offers valuable insights into the exciting potential of intelligent wearables to transform healthcare and sports.

show abstract

Estimating running kinematics variability with an IMU sensor placed on the runner's thorax

Cited by 3 publications

References 20 publications

Indoor running temporal variability for different running speeds, treadmill inclinations, and three different estimation strategies

Indoor running temporal variability for different running speeds, treadmill inclinations, and three different estimation strategies

An Open-Source Wearable Sensor System for Measuring the Duty Factor of Runners

Intelligent Wearable Systems: Opportunities and Challenges in Health and Sports

Contact Info

Product

Resources

About