Estimation of Knee Joint Forces in Sport Movements Using Wearable Sensors and Machine Learning

Stetter, Bernd; Ringhof, Steffen; Krafft, Frieder C.; Sell, Stefan; Stein, Thorsten

doi:10.3390/s19173690

Cited by 87 publications

(116 citation statements)

References 45 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…Combining single IMU data from the sacrum with a convolutional neural network, Johnson et al estimated 3D GRF with the error of 4-9% during running and side-stepping [14]. A leg-mounted IMU combined with a feed forward neural network predicted knee joint forces with an error rate of 17% during running, changing direction, and jumping [49]. Issues to be addressed for sports wearables include reducing the number of sensors and enhancing prediction accuracy.…”

Section: Discussionmentioning

confidence: 99%

Prediction of Lower Limb Kinetics and Kinematics during Walking by a Single IMU on the Lower Back Using Machine Learning

Lim

Kim

Park

2019

Sensors

View full text Add to dashboard Cite

Recent studies have reported the application of artificial neural network (ANN) techniques on data of inertial measurement units (IMUs) to predict ground reaction forces (GRFs), which could serve as quantitative indicators of sports performance or rehabilitation. The number of IMUs and their measurement locations are often determined heuristically, and the rationale underlying the selection of these parameter values is not discussed. Using the dynamic relationship between the center of mass (CoM), the GRFs and joint kinetics, we propose the CoM as a single measurement location with which to predict the dynamic data of the lower limbs, using an ANN. Data from seven subjects walking on a treadmill at various speeds were collected from a single IMU worn near the sacrum. The data was segmented by step and numerically processed for integration. Six segment angles of the stance and swing leg, three joint torques, and two GRFs were estimated from the kinematics of the CoM measured from a single IMU sensor, with fair accuracy. These results indicate the importance of the CoM as a dynamic determinant of multi-segment kinetics during walking. The tradeoff between data quantity and wearable convenience can be solved by utilizing a machine learning algorithm based on the dynamic characteristics of human walking.

show abstract

Section: Discussionmentioning

confidence: 99%

Prediction of Lower Limb Kinetics and Kinematics during Walking by a Single IMU on the Lower Back Using Machine Learning

Lim

Kim

Park

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…A big difference is observed between the upper and lower steps in S3 and S10, whereas the change of resistance is similar in S5 and S9. Although fabric sensors have shown excellent performance in human motion recognition and other fields, most sensors are single or integrated as additive parts in the test [5,40]. In this work, conductive yarns were directly positioned and knitted into elastic leggings to test different area sensors and determine the best sensor area.…”

Section: Suitable Areas For Sensingmentioning

confidence: 99%

Human Motion Recognition of Knitted Flexible Sensor in Walking Cycle

Miao

Niu

et al. 2019

Sensors

View full text Add to dashboard Cite

Knitted fabric sensors have been widely used as strain sensors in the sports health field and its large strain performance and structure are suitable for human body movements. When a knitted structure is worn, different human body movements are reflected through the large strain deformation of fabric structure and consequently change the electrical signal. Here, the mechanical and electrical properties of highly elastic knitted sweatpants were tested under large strain. This sensor has good sensitivity and stability during movement. Compared with traditional motion monitoring, this technique divides the walking cycle into two stages, namely, stance and swing phases, which can be further subdivided into six stages. The corresponding resistance characteristic values can accurately distinguish the gait cycle. Analysis on hysteresis and repeatability revealed that the sensor exhibits a constant electrical performance. Four kinds of motion postures were predicted and judged by comparing the resistance characteristic range value, peak value calculation function and time axis. The measured sensor outputs were transferred to a computer via 4.0 Bluetooth. Matlab language was used to detect the status through a rule-based algorithm and the sensor outputs.

show abstract

“…Hence, this has the same drawbacks as the lab sensors for calculating joint contact forces as it is challenging to measure GRF data in the wild. Stetter et al (2019) proposed a model for predicting knee joint loading using two IMU sensors, one on the upper leg and one on the lower leg. However, similar to de Vries et al (2012) and Wesseling et al (2018), they evaluated the model on data from healthy subjects only.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Approach to Estimate Hip and Knee Joint Loading Using a Mobile Phone-Embedded IMU

Brabandere

Emmerzaal

Timmermans

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Hip osteoarthritis patients exhibit changes in kinematics and kinetics that affect joint loading. Monitoring this load can provide valuable information to clinicians. For example, a patient's joint loading measured across different activities can be used to determine the amount of exercise that the patient needs to complete each day. Unfortunately, current methods for measuring joint loading require a lab environment which most clinicians do not have access to. This study explores employing machine learning to construct a model that can estimate joint loading based on sensor data obtained solely from a mobile phone. In order to learn such a model, we collected a dataset from 10 patients with hip osteoarthritis who performed multiple repetitions of nine different exercises. During each repetition, we simultaneously recorded 3D motion capture data, ground reaction force data, and the inertial measurement unit data from a mobile phone attached to the patient's hip. The 3D motion and ground reaction force data were used to compute the ground truth joint loading using musculoskeletal modeling. Our goal is to estimate the ground truth loading value using only the data captured by the sensors of the mobile phone. We propose a machine learning pipeline for learning such a model based on the recordings of a phone's accelerometer and gyroscope. When evaluated for an unseen patient, the proposed pipeline achieves a mean absolute error of 29% for the left hip and 36% for the right hip. While our approach is a step in the direction of using a minimal number of sensors to estimate joint loading outside the lab, developing a tool that is accurate enough to be applicable in a clinical context still remains an open challenge. It may be necessary to use sensors at more than one location in order to obtain better estimates.

show abstract

Estimation of Knee Joint Forces in Sport Movements Using Wearable Sensors and Machine Learning

Cited by 87 publications

References 45 publications

Prediction of Lower Limb Kinetics and Kinematics during Walking by a Single IMU on the Lower Back Using Machine Learning

Prediction of Lower Limb Kinetics and Kinematics during Walking by a Single IMU on the Lower Back Using Machine Learning

Human Motion Recognition of Knitted Flexible Sensor in Walking Cycle

A Machine Learning Approach to Estimate Hip and Knee Joint Loading Using a Mobile Phone-Embedded IMU

Contact Info

Product

Resources

About