Estimating Knee Joint Angles During Cycling Using Deep Learning and Wearable Sensors

Ebru Fenney; Karl Morgan; Joshua Carter; Zak Sheehy; Crescent Jicol; Eamonn O'Neill

Estimating Knee Joint Angles During Cycling Using Deep Learning and Wearable Sensors

Ebru Fenney, Karl Morgan, Joshua Carter, Zak Sheehy, Crescent Jicol, Eamonn O'Neill

Research output: Contribution to conference › Paper › peer-review

25 Downloads (Pure)

Abstract

In this study, a long short-term memory (LSTM) neural
network was trained using inertial measurement unit (IMU)
data to predict knee joint angles during cycling. Even with a
small dataset, results produced are similar to other
methodologies which require a calibration stage and
expensive motion capture. Further training on a larger dataset
could produce better predictions and reduce model overfitting.

Original language	English
Number of pages	1
Publication status	Published - 27 Jul 2025
Event	Congress of the International Society of Biomechanics (ISB) - Stockholm, Sweden Duration: 27 Jul 2025 → 31 Jul 2025 Conference number: 30 https://isb2025.com/

Conference

Conference	Congress of the International Society of Biomechanics (ISB)
Country/Territory	Sweden
City	Stockholm
Period	27/07/25 → 31/07/25
Internet address	https://isb2025.com/

Keywords

Joint angle, cycling, wearable sensors

ASJC Scopus subject areas

Artificial Intelligence
Human-Computer Interaction
Computer Science Applications
Rehabilitation
Orthopedics and Sports Medicine

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

ISB2025_paperFinal published version, 113 KB

Cite this

@conference{9174b1c2be28484bbc3474e95c13502d,

title = "Estimating Knee Joint Angles During Cycling Using Deep Learning and Wearable Sensors",

abstract = "In this study, a long short-term memory (LSTM) neural network was trained using inertial measurement unit (IMU) data to predict knee joint angles during cycling. Even with a small dataset, results produced are similar to other methodologies which require a calibration stage and expensive motion capture. Further training on a larger dataset could produce better predictions and reduce model overfitting.",

keywords = "Joint angle, cycling, wearable sensors",

author = "Ebru Fenney and Karl Morgan and Joshua Carter and Zak Sheehy and Crescent Jicol and Eamonn O'Neill",

year = "2025",

month = jul,

day = "27",

language = "English",

note = "Congress of the International Society of Biomechanics (ISB) ; Conference date: 27-07-2025 Through 31-07-2025",

url = "https://isb2025.com/",

}

TY - CONF

T1 - Estimating Knee Joint Angles During Cycling Using Deep Learning and Wearable Sensors

AU - Fenney, Ebru

AU - Morgan, Karl

AU - Carter, Joshua

AU - Sheehy, Zak

AU - Jicol, Crescent

AU - O'Neill, Eamonn

N1 - Conference code: 30

PY - 2025/7/27

Y1 - 2025/7/27

N2 - In this study, a long short-term memory (LSTM) neural network was trained using inertial measurement unit (IMU) data to predict knee joint angles during cycling. Even with a small dataset, results produced are similar to other methodologies which require a calibration stage and expensive motion capture. Further training on a larger dataset could produce better predictions and reduce model overfitting.

AB - In this study, a long short-term memory (LSTM) neural network was trained using inertial measurement unit (IMU) data to predict knee joint angles during cycling. Even with a small dataset, results produced are similar to other methodologies which require a calibration stage and expensive motion capture. Further training on a larger dataset could produce better predictions and reduce model overfitting.

KW - Joint angle, cycling, wearable sensors

M3 - Paper

T2 - Congress of the International Society of Biomechanics (ISB)

Y2 - 27 July 2025 through 31 July 2025

ER -

Estimating Knee Joint Angles During Cycling Using Deep Learning and Wearable Sensors

Abstract

Conference

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Fingerprint

Cite this