Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot
This study introduces a novel convolutional neural network (CNN) architecture, encompassing both single and multi-head designs, developed to identify a user’s locomotion activity while using a wearable lower limb robot. Our research involved 500 healthy adult participants in an activities of daily l...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/10/9/1082 |
| _version_ | 1797581217317519360 |
|---|---|
| author | Chang-Sik Son Won-Seok Kang |
| author_facet | Chang-Sik Son Won-Seok Kang |
| author_sort | Chang-Sik Son |
| collection | DOAJ |
| description | This study introduces a novel convolutional neural network (CNN) architecture, encompassing both single and multi-head designs, developed to identify a user’s locomotion activity while using a wearable lower limb robot. Our research involved 500 healthy adult participants in an activities of daily living (ADL) space, conducted from 1 September to 30 November 2022. We collected prospective data to identify five locomotion activities (level ground walking, stair ascent/descent, and ramp ascent/descent) across three terrains: flat ground, staircase, and ramp. To evaluate the predictive capabilities of the proposed CNN architectures, we compared its performance with three other models: one CNN and two hybrid models (CNN-LSTM and LSTM-CNN). Experiments were conducted using multivariate signals of various types obtained from electromyograms (EMGs) and the wearable robot. Our results reveal that the deeper CNN architecture significantly surpasses the performance of the three competing models. The proposed model, leveraging encoder data such as hip angles and velocities, along with postural signals such as roll, pitch, and yaw from the wearable lower limb robot, achieved superior performance with an inference speed of 1.14 s. Specifically, the F-measure performance of the proposed model reached 96.17%, compared to 90.68% for DDLMI, 94.41% for DeepConvLSTM, and 95.57% for LSTM-CNN, respectively. |
| first_indexed | 2024-03-10T23:01:10Z |
| format | Article |
| id | doaj.art-2e052d6c04e1472fa2e40f05f7e04421 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-10T23:01:10Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-2e052d6c04e1472fa2e40f05f7e044212023-11-19T09:37:24ZengMDPI AGBioengineering2306-53542023-09-01109108210.3390/bioengineering10091082Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton RobotChang-Sik Son0Won-Seok Kang1Division of Intelligent Robot, Daegu Gyeongbuk Institute of Science & Technology (DGIST), Daegu 42988, Republic of KoreaDivision of Intelligent Robot, Daegu Gyeongbuk Institute of Science & Technology (DGIST), Daegu 42988, Republic of KoreaThis study introduces a novel convolutional neural network (CNN) architecture, encompassing both single and multi-head designs, developed to identify a user’s locomotion activity while using a wearable lower limb robot. Our research involved 500 healthy adult participants in an activities of daily living (ADL) space, conducted from 1 September to 30 November 2022. We collected prospective data to identify five locomotion activities (level ground walking, stair ascent/descent, and ramp ascent/descent) across three terrains: flat ground, staircase, and ramp. To evaluate the predictive capabilities of the proposed CNN architectures, we compared its performance with three other models: one CNN and two hybrid models (CNN-LSTM and LSTM-CNN). Experiments were conducted using multivariate signals of various types obtained from electromyograms (EMGs) and the wearable robot. Our results reveal that the deeper CNN architecture significantly surpasses the performance of the three competing models. The proposed model, leveraging encoder data such as hip angles and velocities, along with postural signals such as roll, pitch, and yaw from the wearable lower limb robot, achieved superior performance with an inference speed of 1.14 s. Specifically, the F-measure performance of the proposed model reached 96.17%, compared to 90.68% for DDLMI, 94.41% for DeepConvLSTM, and 95.57% for LSTM-CNN, respectively.https://www.mdpi.com/2306-5354/10/9/1082human activity recognitionwearable robotsingle-head CNNmulti-head CNNhyperparameter optimizationtime series classification |
| spellingShingle | Chang-Sik Son Won-Seok Kang Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot Bioengineering human activity recognition wearable robot single-head CNN multi-head CNN hyperparameter optimization time series classification |
| title | Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot |
| title_full | Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot |
| title_fullStr | Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot |
| title_full_unstemmed | Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot |
| title_short | Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot |
| title_sort | multivariate cnn model for human locomotion activity recognition with a wearable exoskeleton robot |
| topic | human activity recognition wearable robot single-head CNN multi-head CNN hyperparameter optimization time series classification |
| url | https://www.mdpi.com/2306-5354/10/9/1082 |
| work_keys_str_mv | AT changsikson multivariatecnnmodelforhumanlocomotionactivityrecognitionwithawearableexoskeletonrobot AT wonseokkang multivariatecnnmodelforhumanlocomotionactivityrecognitionwithawearableexoskeletonrobot |