Fast Wearable Sensor–Based Foot–Ground Contact Phase Classification Using a Convolutional Neural Network with Sliding-Window Label Overlapping
Classification of foot–ground contact phases, as well as the swing phase is essential in biomechanics domains where lower-limb motion analysis is required; this analysis is used for lower-limb rehabilitation, walking gait analysis and improvement, and exoskeleton motion capture. In this study, slidi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/17/4996 |
| _version_ | 1827706921384148992 |
|---|---|
| author | Haneul Jeon Sang Lae Kim Soyeon Kim Donghun Lee |
| author_facet | Haneul Jeon Sang Lae Kim Soyeon Kim Donghun Lee |
| author_sort | Haneul Jeon |
| collection | DOAJ |
| description | Classification of foot–ground contact phases, as well as the swing phase is essential in biomechanics domains where lower-limb motion analysis is required; this analysis is used for lower-limb rehabilitation, walking gait analysis and improvement, and exoskeleton motion capture. In this study, sliding-window label overlapping of time-series wearable motion data in training dataset acquisition is proposed to accurately detect foot–ground contact phases, which are composed of 3 sub-phases as well as the swing phase, at a frequency of 100 Hz with a convolutional neural network (CNN) architecture. We not only succeeded in developing a real-time CNN model for learning and obtaining a test accuracy of 99.8% or higher, but also confirmed that its validation accuracy was close to 85%. |
| first_indexed | 2024-03-10T16:35:28Z |
| format | Article |
| id | doaj.art-04677d14b95341af9388680b5c83d357 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T16:35:28Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-04677d14b95341af9388680b5c83d3572023-11-20T12:26:29ZengMDPI AGSensors1424-82202020-09-012017499610.3390/s20174996Fast Wearable Sensor–Based Foot–Ground Contact Phase Classification Using a Convolutional Neural Network with Sliding-Window Label OverlappingHaneul Jeon0Sang Lae Kim1Soyeon Kim2Donghun Lee3School of Mechanical Engineering, Soongsil University, Seoul 06978, KoreaSchool of Mechanical Engineering, Soongsil University, Seoul 06978, KoreaSchool of Mechanical Engineering, Soongsil University, Seoul 06978, KoreaSchool of Mechanical Engineering, Soongsil University, Seoul 06978, KoreaClassification of foot–ground contact phases, as well as the swing phase is essential in biomechanics domains where lower-limb motion analysis is required; this analysis is used for lower-limb rehabilitation, walking gait analysis and improvement, and exoskeleton motion capture. In this study, sliding-window label overlapping of time-series wearable motion data in training dataset acquisition is proposed to accurately detect foot–ground contact phases, which are composed of 3 sub-phases as well as the swing phase, at a frequency of 100 Hz with a convolutional neural network (CNN) architecture. We not only succeeded in developing a real-time CNN model for learning and obtaining a test accuracy of 99.8% or higher, but also confirmed that its validation accuracy was close to 85%.https://www.mdpi.com/1424-8220/20/17/4996time-series databiomechanicswalking gaitCNNsliding windowwearable sensor |
| spellingShingle | Haneul Jeon Sang Lae Kim Soyeon Kim Donghun Lee Fast Wearable Sensor–Based Foot–Ground Contact Phase Classification Using a Convolutional Neural Network with Sliding-Window Label Overlapping Sensors time-series data biomechanics walking gait CNN sliding window wearable sensor |
| title | Fast Wearable Sensor–Based Foot–Ground Contact Phase Classification Using a Convolutional Neural Network with Sliding-Window Label Overlapping |
| title_full | Fast Wearable Sensor–Based Foot–Ground Contact Phase Classification Using a Convolutional Neural Network with Sliding-Window Label Overlapping |
| title_fullStr | Fast Wearable Sensor–Based Foot–Ground Contact Phase Classification Using a Convolutional Neural Network with Sliding-Window Label Overlapping |
| title_full_unstemmed | Fast Wearable Sensor–Based Foot–Ground Contact Phase Classification Using a Convolutional Neural Network with Sliding-Window Label Overlapping |
| title_short | Fast Wearable Sensor–Based Foot–Ground Contact Phase Classification Using a Convolutional Neural Network with Sliding-Window Label Overlapping |
| title_sort | fast wearable sensor based foot ground contact phase classification using a convolutional neural network with sliding window label overlapping |
| topic | time-series data biomechanics walking gait CNN sliding window wearable sensor |
| url | https://www.mdpi.com/1424-8220/20/17/4996 |
| work_keys_str_mv | AT haneuljeon fastwearablesensorbasedfootgroundcontactphaseclassificationusingaconvolutionalneuralnetworkwithslidingwindowlabeloverlapping AT sanglaekim fastwearablesensorbasedfootgroundcontactphaseclassificationusingaconvolutionalneuralnetworkwithslidingwindowlabeloverlapping AT soyeonkim fastwearablesensorbasedfootgroundcontactphaseclassificationusingaconvolutionalneuralnetworkwithslidingwindowlabeloverlapping AT donghunlee fastwearablesensorbasedfootgroundcontactphaseclassificationusingaconvolutionalneuralnetworkwithslidingwindowlabeloverlapping |