CoChat

Prediction of gait trajectories based on the Long Short Term Memory neural networks

Open access

The DOI matches its Crossref record; 103 of the 103 references it cites were found in a registry or an index.

Abstract

The forecasting of lower limb trajectories can improve the operation of assistive devices and minimise the risk of tripping and balance loss. The aim of this work was to examine four Long Short Term Memory (LSTM) neural network architectures (Vanilla, Stacked, Bidirectional and Autoencoders) in predicting the future trajectories of lower limb kinematics, i.e. Angular Velocity (AV) and Linear Acceleration (LA). Kinematics data of foot, shank and thigh (LA and AV) were collected from 13 male and 3 female participants (28 ± 4 years old, 1.72 ± 0.07 m in height, 66 ± 10 kg in mass) who walked for 10 minutes at preferred walking speed (4.34 ± 0.43 km.h -1 ) and at an imposed speed (5km.h -1 , 15.4% ± 7.6% faster) on a 0% gradient treadmill. The sliding window technique was adopted for training and testing the LSTM models with total kinematics time-series data of 10,500 strides. Results based on leave-one-out cross validation, suggested that the LSTM autoencoders is the top predictor of the lower limb kinematics trajectories (i.e. up to 0.1s). The normalised mean squared error was evaluated on trajectory predictions at each time-step and it obtained 2.82–5.31% for the LSTM autoencoders. The ability to predict future lower limb motions may have a wide range of applications including the design and control of bionics allowing improved human-machine interface and mitigating the risk of falls and balance loss.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0255597

Cites

103 of 103 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig 1 Definition of sagittal plane movements as well as the (X,Y) coordinates. Sagittal plane movements included the rotation around the X-axis (i.e., AV) and the translation along the Y-axis (i.e., LA).
Fig 1 Definition of sagittal plane movements as well as the (X,Y) coordinates. Sagittal plane movements included the rotation around the X-axis (i.e., AV) and the translation along the Y-axis (i.e., LA).CC BY · PubMed Central
Fig 2 Foot, shank and thigh sagittal plane AV and LA. Those were selected as the model’s independent variables predominantly because primary motions of the human movement are flexion and extension in the sagittal plane (6). (a) Foot (X1), shank (X2) and thigh (X3) AV. (b) Foot (Y1), shank (Y2) and thigh (Y3) LA.
Fig 2 Foot, shank and thigh sagittal plane AV and LA. Those were selected as the model’s independent variables predominantly because primary motions of the human movement are flexion and extension in the sagittal plane (6). (a) Foot (X1), shank (X2) and thigh (X3) AV. (b) Foot (Y1), shank (Y2) and thigh (Y3) LA.CC BY · PubMed Central
Fig 3 Sliding window demonstration on 1 feature. The graph shows the sliding window operation on the foot angular velocity (X1). In this paper, the input/output window comprises of 6 features.
Fig 3 Sliding window demonstration on 1 feature. The graph shows the sliding window operation on the foot angular velocity (X1). In this paper, the input/output window comprises of 6 features.CC BY · PubMed Central
Fig 4 LSTM models prediction performance based on the inter-subject test for each feature vector at PWS only. Models were tested with 75 time-steps and the same participant was tested across LSTM models. Black is the actual trajectory. Brown is the Vanilla LSTM predicted trajectory. Red is the Stacked LSTM predicted trajectory. Green is the Bi-LSTM predicted trajectory. Blue is the ED-LSTM predicted trajectory. (a) Foot AV (X1). (b) Foot LA (Y4). (c) Shank AV (X2). (d) Shank LA (Y5). (e) Thigh AV (X3). (f) Thigh LA (Y6).
Fig 4 LSTM models prediction performance based on the inter-subject test for each feature vector at PWS only. Models were tested with 75 time-steps and the same participant was tested across LSTM models. Black is the actual trajectory. Brown is the Vanilla LSTM predicted trajectory. Red is the Stacked LSTM predicted trajectory. Green is the Bi-LSTM predicted trajectory. Blue is the ED-LSTM predicted trajectory. (a) Foot AV (X1). (b) Foot LA (Y4). (c) Shank AV (X2). (d) Shank LA (Y5). (e) Thigh AV (X3). (f) Thigh LA (Y6).CC BY · PubMed Central
Fig 5 Performance comparison between LSTM models based on leave-one-out cross validation at PWS and 5km.h-1 for each feature vector. Red is the RMSE (Left Y-axis). Black is the CC (Right Y-axis). Wider gaps between the two error lines (CC and RMSE) means better prediction quality for the related feature vector. The Stacked and ED LSTM maintained the gap for all feature vectors. (a) Foot AV (X1). (b) Foot LA (Y4). (c) Shank AV (X2). (d) Shank LA (Y5). (e) Thigh AV (X3). (f) Thigh LA (Y6).
Fig 5 Performance comparison between LSTM models based on leave-one-out cross validation at PWS and 5km.h-1 for each feature vector. Red is the RMSE (Left Y-axis). Black is the CC (Right Y-axis). Wider gaps between the two error lines (CC and RMSE) means better prediction quality for the related feature vector. The Stacked and ED LSTM maintained the gap for all feature vectors. (a) Foot AV (X1). (b) Foot LA (Y4). (c) Shank AV (X2). (d) Shank LA (Y5). (e) Thigh AV (X3). (f) Thigh LA (Y6).CC BY · PubMed Central
Fig 6 Performance comparison between LSTM models based on leave-one-out cross validation at PWS and 5km.h-1 for each feature vector. Green is the RMSE (Left Y-axis). Blue is the NRMSE (Right Y-axis). Lower error points for the MAE and NRMSE means a better predictive model for the related feature vector. (a) Foot AV (X1). (b) Foot LA (Y4). (c) Shank AV (X2). (d) Shank LA (Y5). (e) Thigh AV (X3). (f) Thigh LA (Y6).
Fig 6 Performance comparison between LSTM models based on leave-one-out cross validation at PWS and 5km.h-1 for each feature vector. Green is the RMSE (Left Y-axis). Blue is the NRMSE (Right Y-axis). Lower error points for the MAE and NRMSE means a better predictive model for the related feature vector. (a) Foot AV (X1). (b) Foot LA (Y4). (c) Shank AV (X2). (d) Shank LA (Y5). (e) Thigh AV (X3). (f) Thigh LA (Y6).CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 103 references

Research works printed but not linked: 5

  1. TM Mitchell, 1997, Machine learning
  2. Graves A. Generating sequences with recurrent neural networks. arXiv preprint arXiv:13080850. 2013.
  3. S Butterworth, 1930, On the theory of filter amplifiers, Wireless Engineer, 7, 536
  4. RW Soutas-Little, 1998, Motion analysis and biomechanics, J Rehabil Res Dev, 49
  5. L Bottou, 2010, Proceedings of COMPSTAT’2010, 177

Cited by

See all 54

Metadata

Authors
Zaroug, A., Garofolini, A., Lai, D. T. H., Mudie, K., & Begg, R.
Affiliations
  • Victoria University (AU)
  • Defence Science and Technology Group (AU)
Corresponding author
  • Zaroug, Abdelrahman
  • Garofolini, Alessandro
  • Lai, Daniel T. H.
  • Mudie, Kurt
  • Begg, Rezaul
Venue
PLOS ONE
Published
2021-08-05
Volume
16
Issue
8
Pages
e0255597
ISSN
1932-6203 (ISSN-L)
OpenAlex
W3187228760
Cited by
48
References
103
Citations by year
2026: 6 · 2025: 15 · 2024: 10 · 2023: 7 · 2022: 9 · 2021: 1
FWCI
2.05
Type
journal article
Language
en
Open access
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Victoria University Research Repository (Victoria University) (submittedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Figshare (submittedVersion, cc-by)
Funders
  • Victoria University
  • Defence Science and Technology Group
Topics
  • Physical Sciences › Engineering › Biomedical Engineering › Prosthetics and Rehabilitation Robotics
  • Health Sciences › Health Professions › Physical Therapy, Sports Therapy and Rehabilitation › Balance, Gait, and Falls Prevention
  • Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
Keywords
lower limb kinematics, long short-term memory, LSTM autoencoder, angular velocity, linear acceleration, walking speed, treadmill walking, assistive devices, fall prevention, bionic prosthetics, human-machine interaction
MeSH terms
Adult, Algorithms, Biomechanical Phenomena, Female, Gait, Humans, Male, Memory, Short-Term, Walking, Neural Networks, Computer

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Prediction of gait trajectories based on the Long Short Term Memory neural networks. https://app.cochat.ai/papers/10.1371/journal.pone.0255597
The paper
Zaroug, A., Garofolini, A., Lai, D. T. H., Mudie, K., & Begg, R. (2021). Prediction of gait trajectories based on the Long Short Term Memory neural networks. PLOS ONE. https://doi.org/10.1371/journal.pone.0255597

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.