Zhao, Yuxuan (2022) A Study of Machine Learning based on Physical Load Classification. Masters thesis, University of Wales Trinity Saint David.
![[img]](https://repository.uwtsd.ac.uk/style/images/fileicons/text.png) |
Text
Zhao, Yuxuan (2022) MSc A study of machine learning based on physical load classification.pdf - Accepted Version Restricted to Repository staff only Available under License CC-BY-NC-ND Creative Commons Attribution Non-commercial No Derivatives. Download (1MB) | Request a copy |
Abstract
A whole system of gait data acquisition based on IMU sensors was completed in this study and an in-depth study was carried out based on the data collected by this system. The IMU data of human lower limb movements were experimentally verified to be usable for physical load recognition and classification work. As a result, the processed data used for machine learning is divided into three main categories: no-load, light-load and heavy-load. The traditional LSTM was able to achieve 71.1% accuracy for the multi-classification problem, and the Bi-LSTM was able to achieve a 74.5% correct classification rate. The excellent performance of multiple Bi-LSTMs for binary classification problems was exploited by changing the discriminative approach of the network, and a correct recognition rate of 94.1% was achieved for 3 classifications using 3 binary Bi-LSTM networks. This method can be used to provide a reference of the drive torque size and drive mode for the drive assist unit of an exoskeleton robot or a sports rehabilitation machine to achieve automatic determination of the torque size of the assist. It can reduce the energy consumption of the wearer during walking, reduce the fatigue during weight-bearing, increase the power-assist efficiency of the system and improve the performance of the system, which is of good reference value.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Theses and Dissertations > Masters Dissertations |
| Depositing User: | Yuxuan Zhao |
| Date Deposited: | 24 Apr 2023 11:56 |
| Last Modified: | 07 Aug 2024 13:29 |
| URI: | https://repository.uwtsd.ac.uk/id/eprint/2363 |
Administrator Actions (login required)
 |
Edit Item - Repository Staff Only |