Effects of Data Augmentation on the Nine-Axis IMU-Based Orientation Estimation Accuracy of a Recurrent Neural Network
The nine-axis inertial and measurement unit (IMU)-based three-dimensional (3D) orientation estimation is a fundamental part of inertial motion capture. Recently, owing to the successful utilization of deep learning in various applications, orientation estimation neural networks (NNs) trained on larg...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/17/7458 |
| _version_ | 1797581859377381376 |
|---|---|
| author | Ji Seok Choi Jung Keun Lee |
| author_facet | Ji Seok Choi Jung Keun Lee |
| author_sort | Ji Seok Choi |
| collection | DOAJ |
| description | The nine-axis inertial and measurement unit (IMU)-based three-dimensional (3D) orientation estimation is a fundamental part of inertial motion capture. Recently, owing to the successful utilization of deep learning in various applications, orientation estimation neural networks (NNs) trained on large datasets, including nine-axis IMU signals and reference orientation data, have been developed. During the training process, the limited amount of training data is a critical issue in the development of powerful networks. Data augmentation, which increases the amount of training data, is a key approach for addressing the data shortage problem and thus for improving the estimation performance. However, to the best of our knowledge, no studies have been conducted to analyze the effects of data augmentation techniques on estimation performance in orientation estimation networks using IMU sensors. This paper selects three data augmentation techniques for IMU-based orientation estimation NNs, i.e., augmentation by virtual rotation, bias addition, and noise addition (which are hereafter referred to as <i>rotation</i>, <i>bias</i>, and <i>noise</i>, respectively). Then, this paper analyzes the effects of these augmentation techniques on estimation accuracy in recurrent neural networks, for a total of seven combinations (i.e., rotation only, bias only, noise only, rotation and bias, rotation and noise, and rotation and bias and noise). The evaluation results show that, among a total of seven augmentation cases, four cases including ‘rotation’ (i.e., rotation only, rotation and bias, rotation and noise, and rotation and bias and noise) occupy the top four. Therefore, it may be concluded that the augmentation effect of rotation is overwhelming compared to those of bias and noise. By applying rotation augmentation, the performance of the NN can be significantly improved. The analysis of the effect of the data augmentation techniques presented in this paper may provide insights for developing robust IMU-based orientation estimation networks. |
| first_indexed | 2024-03-10T23:13:34Z |
| format | Article |
| id | doaj.art-9850f3ecebbd4617b3a8c9dcec06f2cf |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T23:13:34Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9850f3ecebbd4617b3a8c9dcec06f2cf2023-11-19T08:50:10ZengMDPI AGSensors1424-82202023-08-012317745810.3390/s23177458Effects of Data Augmentation on the Nine-Axis IMU-Based Orientation Estimation Accuracy of a Recurrent Neural NetworkJi Seok Choi0Jung Keun Lee1Inertial Motion Capture Lab, School of ICT, Robotics & Mechanical Engineering, Hankyong National University, Anseong 17579, Republic of KoreaInertial Motion Capture Lab, School of ICT, Robotics & Mechanical Engineering, Hankyong National University, Anseong 17579, Republic of KoreaThe nine-axis inertial and measurement unit (IMU)-based three-dimensional (3D) orientation estimation is a fundamental part of inertial motion capture. Recently, owing to the successful utilization of deep learning in various applications, orientation estimation neural networks (NNs) trained on large datasets, including nine-axis IMU signals and reference orientation data, have been developed. During the training process, the limited amount of training data is a critical issue in the development of powerful networks. Data augmentation, which increases the amount of training data, is a key approach for addressing the data shortage problem and thus for improving the estimation performance. However, to the best of our knowledge, no studies have been conducted to analyze the effects of data augmentation techniques on estimation performance in orientation estimation networks using IMU sensors. This paper selects three data augmentation techniques for IMU-based orientation estimation NNs, i.e., augmentation by virtual rotation, bias addition, and noise addition (which are hereafter referred to as <i>rotation</i>, <i>bias</i>, and <i>noise</i>, respectively). Then, this paper analyzes the effects of these augmentation techniques on estimation accuracy in recurrent neural networks, for a total of seven combinations (i.e., rotation only, bias only, noise only, rotation and bias, rotation and noise, and rotation and bias and noise). The evaluation results show that, among a total of seven augmentation cases, four cases including ‘rotation’ (i.e., rotation only, rotation and bias, rotation and noise, and rotation and bias and noise) occupy the top four. Therefore, it may be concluded that the augmentation effect of rotation is overwhelming compared to those of bias and noise. By applying rotation augmentation, the performance of the NN can be significantly improved. The analysis of the effect of the data augmentation techniques presented in this paper may provide insights for developing robust IMU-based orientation estimation networks.https://www.mdpi.com/1424-8220/23/17/7458data augmentationorientation estimationinertial measurement unitdeep learningrecurrent neural network |
| spellingShingle | Ji Seok Choi Jung Keun Lee Effects of Data Augmentation on the Nine-Axis IMU-Based Orientation Estimation Accuracy of a Recurrent Neural Network Sensors data augmentation orientation estimation inertial measurement unit deep learning recurrent neural network |
| title | Effects of Data Augmentation on the Nine-Axis IMU-Based Orientation Estimation Accuracy of a Recurrent Neural Network |
| title_full | Effects of Data Augmentation on the Nine-Axis IMU-Based Orientation Estimation Accuracy of a Recurrent Neural Network |
| title_fullStr | Effects of Data Augmentation on the Nine-Axis IMU-Based Orientation Estimation Accuracy of a Recurrent Neural Network |
| title_full_unstemmed | Effects of Data Augmentation on the Nine-Axis IMU-Based Orientation Estimation Accuracy of a Recurrent Neural Network |
| title_short | Effects of Data Augmentation on the Nine-Axis IMU-Based Orientation Estimation Accuracy of a Recurrent Neural Network |
| title_sort | effects of data augmentation on the nine axis imu based orientation estimation accuracy of a recurrent neural network |
| topic | data augmentation orientation estimation inertial measurement unit deep learning recurrent neural network |
| url | https://www.mdpi.com/1424-8220/23/17/7458 |
| work_keys_str_mv | AT jiseokchoi effectsofdataaugmentationonthenineaxisimubasedorientationestimationaccuracyofarecurrentneuralnetwork AT jungkeunlee effectsofdataaugmentationonthenineaxisimubasedorientationestimationaccuracyofarecurrentneuralnetwork |