Automated gait event detection for a variety of locomotion tasks using a novel gyroscope-based algorithm

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

doi:10.1016/j.gaitpost.2020.06.019

Cited by 24 publications

(34 citation statements)

References 35 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a first step, mid-swing phases were determined. It was shown that positive peaks of the angular velocity around the frontal axis denote the mid-swing phases of every step ( 29 – 31 ). Therefore, positive peak detection was used to determine the mid-swing phases of every gait cycle in the smoothed angular velocities around the participant's frontal axis.…”

Section: Methodsmentioning

confidence: 99%

Heading Direction Is Significantly Biased by Preceding Whole-Body Roll-Orientation While Lying

et al. 2022

View full text Add to dashboard Cite

BackgroundAfter a prolonged static whole-body roll-tilt, a significant bias of the internal estimates of the direction of gravity has been observed when assessing the subjective visual vertical.ObjectiveWe hypothesized that this post-tilt bias represents a more general phenomenon, broadly affecting spatial orientation and navigation. Specifically, we predicted that after the prolonged roll-tilt to either side perceived straight-ahead would also be biased.MethodsTwenty-five healthy participants were asked to rest in three different lying positions (supine, right-ear-down, and left-ear-down) for 5 min (“adaptation period”) prior to walking straight-ahead blindfolded for 2 min. Walking was recorded with the inertial measurement unit sensors attached to different body locations and with sensor shoe insoles. The raw data was segmented with a gait–event detection method. The Heading direction was determined and linear mixed-effects models were used for statistical analyses.ResultsA significant bias in heading into the direction of the previous roll-tilt position was observed in the post-adaptation trials. This bias was identified in both measurement systems and decreased again over the 2-min walking period.ConclusionsThe bias observed further confirms the influence of prior knowledge on spatial orientation and navigation. Specifically, it underlines the broad impact of a shifting internal estimate of direction of gravity over a range of distinct paradigms, illustrating similar decay time constants. In the broader context, the observed bias in perceived straight-ahead emphasizes that getting up in the morning after a good night's sleep is a vulnerable period, with an increased risk of falls and fall-related injuries due to non-availability of optimally tuned internal estimates of the direction of gravity and the direction of straight-ahead.

show abstract

Section: Methodsmentioning

confidence: 99%

Heading Direction Is Significantly Biased by Preceding Whole-Body Roll-Orientation While Lying

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Data in other studies has been segmented in a variety of ways including continuous walking [22], three gait cycles [21], or single gait cycles [26,27]. The higher-order data segmentation in those studies may prove to be clinically useful for use in a human activity recognition model that includes other activities (e.g., going up stairs or sit-to-stand), and integration with a gait event detection algorithm [55].…”

Section: Reducing the Burden For Cliniciansmentioning

confidence: 99%

Predicting Knee Joint Kinematics from Wearable Sensor Data in People with Knee Osteoarthritis and Clinical Considerations for Future Machine Learning Models

Tan

Tippaya

Binnie

et al. 2022

Sensors

View full text Add to dashboard Cite

Deep learning models developed to predict knee joint kinematics are usually trained on inertial measurement unit (IMU) data from healthy people and only for the activity of walking. Yet, people with knee osteoarthritis have difficulties with other activities and there are a lack of studies using IMU training data from this population. Our objective was to conduct a proof-of-concept study to determine the feasibility of using IMU training data from people with knee osteoarthritis performing multiple clinically important activities to predict knee joint sagittal plane kinematics using a deep learning approach. We trained a bidirectional long short-term memory model on IMU data from 17 participants with knee osteoarthritis to estimate knee joint flexion kinematics for phases of walking, transitioning to and from a chair, and negotiating stairs. We tested two models, a double-leg model (four IMUs) and a single-leg model (two IMUs). The single-leg model demonstrated less prediction error compared to the double-leg model. Across the different activity phases, RMSE (SD) ranged from 7.04° (2.6) to 11.78° (6.04), MAE (SD) from 5.99° (2.34) to 10.37° (5.44), and Pearson’s R from 0.85 to 0.99 using leave-one-subject-out cross-validation. This study demonstrates the feasibility of using IMU training data from people who have knee osteoarthritis for the prediction of kinematics for multiple clinically relevant activities.

show abstract

“…Sarshar et al [26] who also used RNN to train two IMU sensors attached to the shanks, reported an accuracy of 0.9977 for both HS and TO events, however, they did not compute the error in prediction delays. Utilizing rule-based algorithms, Fadillioglu et al [27] presented an automated gait event detection method using a gyroscope attached to the right shank and reported an MAE of 7ms and 19ms for the HS and TO events respectively. More recently, Yu et al [28] also used a single sensor on the right foot with an LSTM-HMM hybrid model for gait event detection, reporting the accuracy only without mentioning the delays.…”

Section: Discussionmentioning

confidence: 99%

Gait Events Prediction using Hybrid CNN-RNN-based Deep Learning models through a Single Waist-worn Wearable Sensor

Arshad¹,

Jamsrandorj²,

Kim³

et al. 2022

Preprint

View full text Add to dashboard Cite

Elderly gait is a source of rich information about their physical and mental health condition. As an alternative to the multiple sensors on the lower body parts, a single sensor on the pelvis has a positional advantage and an abundance of information acquirable. This study aimed to explore a way of improving the accuracy of gait event detection in the elderly using a single sensor on the waist and deep learning models. Data was gathered from elderly subjects equipped with three IMU sensors while they walked. The input was taken only from the waist sensor was used to train 16 deep-learning models including CNN, RNN, and CNN-RNN hybrid with or without the Bidirectional and Attention mechanism. The groundtruth was extracted from foot IMU sensors. Fairly high accuracy of 99.73% and 93.89% was achieved by the CNN-BiGRU-Att model at the tolerance window of ±6TS (±6ms) and ±1TS (±1ms) respectively. Advancing from the previous studies exploring gait event detection, the model showed a great improvement in terms of its prediction error having an MAE of 6.239ms and 5.24ms for HS and TO events respectively at the tolerance window of ±1TS. The results showed that the use of CNN-RNN hybrid models with Attention and Bidirectional mechanisms is promising for accurate gait event detection using a single waist sensor. The study can contribute to reducing the burden of gait detection and increase its applicability in future wearable devices that can be used for remote health monitoring (RHM) or diagnosis based thereon.

show abstract

Automated gait event detection for a variety of locomotion tasks using a novel gyroscope-based algorithm

Cited by 24 publications

References 35 publications

Heading Direction Is Significantly Biased by Preceding Whole-Body Roll-Orientation While Lying

Heading Direction Is Significantly Biased by Preceding Whole-Body Roll-Orientation While Lying

Predicting Knee Joint Kinematics from Wearable Sensor Data in People with Knee Osteoarthritis and Clinical Considerations for Future Machine Learning Models

Gait Events Prediction using Hybrid CNN-RNN-based Deep Learning models through a Single Waist-worn Wearable Sensor

Contact Info

Product

Resources

About