Daily Locomotion Recognition and Prediction: A Kinematic Data-Based Machine Learning Approach
More versatile, user-independent tools for recognizing and predicting locomotion modes (LMs) and LM transitions (LMTs) in natural gaits are still needed. This study tackles these challenges by proposing an automatic, user-independent recognition and prediction tool using easily wearable kinematic mo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8982003/ |
| _version_ | 1818875429635751936 |
|---|---|
| author | Joana Figueiredo Simao P. Carvalho Diogo Goncalve Juan C. Moreno Cristina P. Santos |
| author_facet | Joana Figueiredo Simao P. Carvalho Diogo Goncalve Juan C. Moreno Cristina P. Santos |
| author_sort | Joana Figueiredo |
| collection | DOAJ |
| description | More versatile, user-independent tools for recognizing and predicting locomotion modes (LMs) and LM transitions (LMTs) in natural gaits are still needed. This study tackles these challenges by proposing an automatic, user-independent recognition and prediction tool using easily wearable kinematic motion sensors for innovatively classifying several LMs (walking direction, level-ground walking, ascend and descend stairs, and ascend and descend ramps) and respective LMTs. We compared diverse state-of-the-art feature processing and dimensionality reduction methods and machine-learning classifiers to find an effective tool for recognition and prediction of LMs and LMTs. The comparison included kinematic patterns from 10 able-bodied subjects. The more accurate tools were achieved using min-max scaling [-1; 1] interval and “mRMR plus forward selection” algorithm for feature normalization and dimensionality reduction, respectively, and Gaussian support vector machine classifier. The developed tool was accurate in the recognition (accuracy >99% and >96%) and prediction (accuracy >99% and >93%) of daily LMs and LMTs, respectively, using exclusively kinematic data. The use of kinematic data yielded an effective recognition and prediction tool, predicting the LMs and LMTs one-step-ahead. This timely prediction is relevant for assistive devices providing personalized assistance in daily scenarios. The kinematic data-based machine learning tool innovatively addresses several LMs and LMTs while allowing the user to self-select the leading limb to perform LMTs, ensuring a natural gait. |
| first_indexed | 2024-12-19T13:26:21Z |
| format | Article |
| id | doaj.art-d94b90a373194812b05cdab71fccb11a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-19T13:26:21Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-d94b90a373194812b05cdab71fccb11a2022-12-21T20:19:32ZengIEEEIEEE Access2169-35362020-01-018332503326210.1109/ACCESS.2020.29715528982003Daily Locomotion Recognition and Prediction: A Kinematic Data-Based Machine Learning ApproachJoana Figueiredo0https://orcid.org/0000-0001-9547-3051Simao P. Carvalho1Diogo Goncalve2Juan C. Moreno3Cristina P. Santos4Industrial Electronics Department, Center for MicroElectroMechanical Systems (CMEMS), University of Minho, Guimarães, PortugalIndustrial Electronics Department, Center for MicroElectroMechanical Systems (CMEMS), University of Minho, Guimarães, PortugalIndustrial Electronics Department, Center for MicroElectroMechanical Systems (CMEMS), University of Minho, Guimarães, PortugalNeural Rehabilitation Group, Cajal Institute, Spanish National Research Council, Madrid, SpainIndustrial Electronics Department, Center for MicroElectroMechanical Systems (CMEMS), University of Minho, Guimarães, PortugalMore versatile, user-independent tools for recognizing and predicting locomotion modes (LMs) and LM transitions (LMTs) in natural gaits are still needed. This study tackles these challenges by proposing an automatic, user-independent recognition and prediction tool using easily wearable kinematic motion sensors for innovatively classifying several LMs (walking direction, level-ground walking, ascend and descend stairs, and ascend and descend ramps) and respective LMTs. We compared diverse state-of-the-art feature processing and dimensionality reduction methods and machine-learning classifiers to find an effective tool for recognition and prediction of LMs and LMTs. The comparison included kinematic patterns from 10 able-bodied subjects. The more accurate tools were achieved using min-max scaling [-1; 1] interval and “mRMR plus forward selection” algorithm for feature normalization and dimensionality reduction, respectively, and Gaussian support vector machine classifier. The developed tool was accurate in the recognition (accuracy >99% and >96%) and prediction (accuracy >99% and >93%) of daily LMs and LMTs, respectively, using exclusively kinematic data. The use of kinematic data yielded an effective recognition and prediction tool, predicting the LMs and LMTs one-step-ahead. This timely prediction is relevant for assistive devices providing personalized assistance in daily scenarios. The kinematic data-based machine learning tool innovatively addresses several LMs and LMTs while allowing the user to self-select the leading limb to perform LMTs, ensuring a natural gait.https://ieeexplore.ieee.org/document/8982003/Kinematic datamachine learningmotion intention recognitionmotion transition prediction |
| spellingShingle | Joana Figueiredo Simao P. Carvalho Diogo Goncalve Juan C. Moreno Cristina P. Santos Daily Locomotion Recognition and Prediction: A Kinematic Data-Based Machine Learning Approach IEEE Access Kinematic data machine learning motion intention recognition motion transition prediction |
| title | Daily Locomotion Recognition and Prediction: A Kinematic Data-Based Machine Learning Approach |
| title_full | Daily Locomotion Recognition and Prediction: A Kinematic Data-Based Machine Learning Approach |
| title_fullStr | Daily Locomotion Recognition and Prediction: A Kinematic Data-Based Machine Learning Approach |
| title_full_unstemmed | Daily Locomotion Recognition and Prediction: A Kinematic Data-Based Machine Learning Approach |
| title_short | Daily Locomotion Recognition and Prediction: A Kinematic Data-Based Machine Learning Approach |
| title_sort | daily locomotion recognition and prediction a kinematic data based machine learning approach |
| topic | Kinematic data machine learning motion intention recognition motion transition prediction |
| url | https://ieeexplore.ieee.org/document/8982003/ |
| work_keys_str_mv | AT joanafigueiredo dailylocomotionrecognitionandpredictionakinematicdatabasedmachinelearningapproach AT simaopcarvalho dailylocomotionrecognitionandpredictionakinematicdatabasedmachinelearningapproach AT diogogoncalve dailylocomotionrecognitionandpredictionakinematicdatabasedmachinelearningapproach AT juancmoreno dailylocomotionrecognitionandpredictionakinematicdatabasedmachinelearningapproach AT cristinapsantos dailylocomotionrecognitionandpredictionakinematicdatabasedmachinelearningapproach |