CoChat

A Locomotion Intent Prediction System Based on Multi-Sensor Fusion

Open access

The DOI matches its Crossref record; 48 of the 49 references it cites were found in a registry or an index.

Abstract

Locomotion intent prediction is essential for the control of powered lower-limb prostheses to realize smooth locomotion transitions. In this research, we develop a multi-sensor fusion based locomotion intent prediction system, which can recognize current locomotion mode and detect locomotion transitions in advance. Seven able-bodied subjects were recruited for this research. Signals from two foot pressure insoles and three inertial measurement units (one on the thigh, one on the shank and the other on the foot) are measured. A two-level recognition strategy is used for the recognition with linear discriminate classifier. Six kinds of locomotion modes and ten kinds of locomotion transitions are tested in this study. Recognition accuracy during steady locomotion periods (i.e., no locomotion transitions) is 99.71% ± 0.05% for seven able-bodied subjects. During locomotion transition periods, all the transitions are correctly detected and most of them can be detected before transiting to new locomotion modes. No significant deterioration in recognition performance is observed in the following five hours after the system is trained, and small number of experiment trials are required to train reliable classifiers.

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 · 10.3390/s140712349

Cites

48 of 48 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1. The placement of the sensors on human body. Foot pressure insoles are placed in shoes of both feet and the signals are sampled by circuits embedded in FP module1 and FP module2. IMUs used for recording the movement data of the thigh, the shank and the foot are embedded in IMU module1, IMU module2 and FP module1, respectively.
Figure 1. The placement of the sensors on human body. Foot pressure insoles are placed in shoes of both feet and the signals are sampled by circuits embedded in FP module1 and FP module2. IMUs used for recording the movement data of the thigh, the shank and the foot are embedded in IMU module1, IMU module2 and FP module1, respectively.CC BY · PubMed Central
Figure 2. (a) The structure of data transmission in the designed system using RS-485 bus. In each sensor module, the data stream is controlled by MCU; (b) The custom made foot pressure insoles used in this study. Positions of pressure sensors are marked as 1, 2, 3 and 4, respectively; (c) The IMU board embedded with an accelerometer (ACCEL), a gyroscope (GYRO) and a magnetometer (MAG); (d) The foot pressure sampling circuit.
Figure 2. (a) The structure of data transmission in the designed system using RS-485 bus. In each sensor module, the data stream is controlled by MCU; (b) The custom made foot pressure insoles used in this study. Positions of pressure sensors are marked as 1, 2, 3 and 4, respectively; (c) The IMU board embedded with an accelerometer (ACCEL), a gyroscope (GYRO) and a magnetometer (MAG); (d) The foot pressure sampling circuit.CC BY · PubMed Central
Figure 3. Block diagram of the locomotion intent prediction system.
Figure 3. Block diagram of the locomotion intent prediction system.CC BY · PubMed Central
Figure 4. Average recognition accuracy (a) and adjusted prediction time (b) over seven able-bodied subjects with window size ranging from 100 ms to 200 ms. Color shades denote SEMs across subjects.
Figure 4. Average recognition accuracy (a) and adjusted prediction time (b) over seven able-bodied subjects with window size ranging from 100 ms to 200 ms. Color shades denote SEMs across subjects.CC BY · PubMed Central
Figure 5. Average recognition error (a) and adjusted prediction time (b) over seven able-bodied subjects with the original majority voting and the modified post-processing approach. Error bars denote SEMs across subjects.
Figure 5. Average recognition error (a) and adjusted prediction time (b) over seven able-bodied subjects with the original majority voting and the modified post-processing approach. Error bars denote SEMs across subjects.CC BY · PubMed Central
Figure 6. Average recognition accuracy (a) and adjusted prediction time (b) over seven able-bodied subjects with some time ranging from 15 min to 300 min after training. Color shades denote SEMs across subjects.
Figure 6. Average recognition accuracy (a) and adjusted prediction time (b) over seven able-bodied subjects with some time ranging from 15 min to 300 min after training. Color shades denote SEMs across subjects.CC BY · PubMed Central
Figure 7. Average recognition accuracy (a) and adjusted prediction time (b) over seven able-bodied subjects with the number of training pairs ranging from 1 to 20. Color shades denote SEMs across subjects.
Figure 7. Average recognition accuracy (a) and adjusted prediction time (b) over seven able-bodied subjects with the number of training pairs ranging from 1 to 20. Color shades denote SEMs across subjects.CC BY · PubMed Central
Figure 8. Recognition performances of online test experiments for Set-A experiment trial (a) and Set-B experiment trial (b). Data of 6 experiment pairs were used to train the system. The solid line denotes decision stream made by the locomotion intent recognition system. The dash line denotes the critical moment for each locomotion transition. Color shades denote locomotion transition periods of each trial.
Figure 8. Recognition performances of online test experiments for Set-A experiment trial (a) and Set-B experiment trial (b). Data of 6 experiment pairs were used to train the system. The solid line denotes decision stream made by the locomotion intent recognition system. The dash line denotes the critical moment for each locomotion transition. Color shades denote locomotion transition periods of each trial.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 48 references

Cited by

See all 70

Metadata

Authors
Chen, B., Zheng, E., & Wang, Q.
Affiliations
Peking University (CN)
Corresponding author
Wang, Qining
Venue
Sensors
Publisher
MDPI AG
Published
2014-07-10
Volume
14
Issue
7
Pages
12349-12369
ISSN
1424-8220 (ISSN-L)
OpenAlex
W2090283616
Cited by
69
References
49
Citations by year
2026: 3 · 2025: 8 · 2024: 7 · 2023: 3 · 2022: 5 · 2021: 11 · 2020: 9 · 2019: 7 · 2018: 9 · 2017: 5 · 2016: 1 · 2014: 1
FWCI
1.21
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Natural Science Foundation of China (61005082, 61020106005)
  • Peking University (3J0865600)
  • Beijing Nova Program (Z141101001814001)
Topics
  • Physical Sciences › Engineering › Biomedical Engineering › Prosthetics and Rehabilitation Robotics
  • Physical Sciences › Engineering › Biomedical Engineering › Muscle activation and electromyography studies
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
Keywords
multi-sensor fusion, lower limb prosthesis, powered prostheses, locomotion mode recognition, inertial measurement unit, linear discriminant analysis, gait control
MeSH terms
Algorithms, Artificial Limbs, Electromyography, Humans, Leg, Locomotion, Prosthesis Design, Signal Processing, Computer-Assisted, Walking

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

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.