Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction
This paper proposes a novel approach to tackle the human activity recognition (HAR) problem. Four classes of body movement datasets, namely stand-up, sit-down, run, and walk, are applied to perform HAR. Instead of using vision-based solutions, we address the HAR challenge by implementing a real-time...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/18/7802 |
| _version_ | 1797577035488428032 |
|---|---|
| author | Yu-Hsuan Tseng Chih-Yu Wen |
| author_facet | Yu-Hsuan Tseng Chih-Yu Wen |
| author_sort | Yu-Hsuan Tseng |
| collection | DOAJ |
| description | This paper proposes a novel approach to tackle the human activity recognition (HAR) problem. Four classes of body movement datasets, namely stand-up, sit-down, run, and walk, are applied to perform HAR. Instead of using vision-based solutions, we address the HAR challenge by implementing a real-time HAR system architecture with a wearable inertial measurement unit (IMU) sensor, which aims to achieve networked sensing and data sampling of human activity, data pre-processing and feature analysis, data generation and correction, and activity classification using hybrid learning models. Referring to the experimental results, the proposed system selects the pre-trained eXtreme Gradient Boosting (XGBoost) model and the Convolutional Variational Autoencoder (CVAE) model as the classifier and generator, respectively, with 96.03% classification accuracy. |
| first_indexed | 2024-03-10T22:02:13Z |
| format | Article |
| id | doaj.art-4a0aad6f7b344a4f95f60d46cb508785 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T22:02:13Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-4a0aad6f7b344a4f95f60d46cb5087852023-11-19T12:54:29ZengMDPI AGSensors1424-82202023-09-012318780210.3390/s23187802Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data CorrectionYu-Hsuan Tseng0Chih-Yu Wen1Department of Computer Science and Engineering, National Chung Hsing University, Taichung 40227, TaiwanDepartment of Electrical Engineering, National Chung Hsing University, Taichung 40227, TaiwanThis paper proposes a novel approach to tackle the human activity recognition (HAR) problem. Four classes of body movement datasets, namely stand-up, sit-down, run, and walk, are applied to perform HAR. Instead of using vision-based solutions, we address the HAR challenge by implementing a real-time HAR system architecture with a wearable inertial measurement unit (IMU) sensor, which aims to achieve networked sensing and data sampling of human activity, data pre-processing and feature analysis, data generation and correction, and activity classification using hybrid learning models. Referring to the experimental results, the proposed system selects the pre-trained eXtreme Gradient Boosting (XGBoost) model and the Convolutional Variational Autoencoder (CVAE) model as the classifier and generator, respectively, with 96.03% classification accuracy.https://www.mdpi.com/1424-8220/23/18/7802human activity recognitionvariational autoencodergenerative adversarial networks |
| spellingShingle | Yu-Hsuan Tseng Chih-Yu Wen Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction Sensors human activity recognition variational autoencoder generative adversarial networks |
| title | Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction |
| title_full | Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction |
| title_fullStr | Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction |
| title_full_unstemmed | Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction |
| title_short | Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction |
| title_sort | hybrid learning models for imu based har with feature analysis and data correction |
| topic | human activity recognition variational autoencoder generative adversarial networks |
| url | https://www.mdpi.com/1424-8220/23/18/7802 |
| work_keys_str_mv | AT yuhsuantseng hybridlearningmodelsforimubasedharwithfeatureanalysisanddatacorrection AT chihyuwen hybridlearningmodelsforimubasedharwithfeatureanalysisanddatacorrection |