Improving Human Activity Recognition Performance by Data Fusion and Feature Engineering
Human activity recognition (HAR) is essential in many health-related fields. A variety of technologies based on different sensors have been developed for HAR. Among them, fusion from heterogeneous wearable sensors has been developed as it is portable, non-interventional and accurate for HAR. To be a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/3/692 |
| _version_ | 1797409254649364480 |
|---|---|
| author | Jingcheng Chen Yining Sun Shaoming Sun |
| author_facet | Jingcheng Chen Yining Sun Shaoming Sun |
| author_sort | Jingcheng Chen |
| collection | DOAJ |
| description | Human activity recognition (HAR) is essential in many health-related fields. A variety of technologies based on different sensors have been developed for HAR. Among them, fusion from heterogeneous wearable sensors has been developed as it is portable, non-interventional and accurate for HAR. To be applied in real-time use with limited resources, the activity recognition system must be compact and reliable. This requirement can be achieved by feature selection (FS). By eliminating irrelevant and redundant features, the system burden is reduced with good classification performance (CP). This manuscript proposes a two-stage genetic algorithm-based feature selection algorithm with a fixed activation number (GFSFAN), which is implemented on the datasets with a variety of time, frequency and time-frequency domain features extracted from the collected raw time series of nine activities of daily living (ADL). Six classifiers are used to evaluate the effects of selected feature subsets from different FS algorithms on HAR performance. The results indicate that GFSFAN can achieve good CP with a small size. A sensor-to-segment coordinate calibration algorithm and lower-limb joint angle estimation algorithm are introduced. Experiments on the effect of the calibration and the introduction of joint angle on HAR shows that both of them can improve the CP. |
| first_indexed | 2024-03-09T04:11:41Z |
| format | Article |
| id | doaj.art-66aca4fa1c0a41a4a7a3db33c9d4a68c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T04:11:41Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-66aca4fa1c0a41a4a7a3db33c9d4a68c2023-12-03T13:59:42ZengMDPI AGSensors1424-82202021-01-0121369210.3390/s21030692Improving Human Activity Recognition Performance by Data Fusion and Feature EngineeringJingcheng Chen0Yining Sun1Shaoming Sun2Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaInstitute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaInstitute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaHuman activity recognition (HAR) is essential in many health-related fields. A variety of technologies based on different sensors have been developed for HAR. Among them, fusion from heterogeneous wearable sensors has been developed as it is portable, non-interventional and accurate for HAR. To be applied in real-time use with limited resources, the activity recognition system must be compact and reliable. This requirement can be achieved by feature selection (FS). By eliminating irrelevant and redundant features, the system burden is reduced with good classification performance (CP). This manuscript proposes a two-stage genetic algorithm-based feature selection algorithm with a fixed activation number (GFSFAN), which is implemented on the datasets with a variety of time, frequency and time-frequency domain features extracted from the collected raw time series of nine activities of daily living (ADL). Six classifiers are used to evaluate the effects of selected feature subsets from different FS algorithms on HAR performance. The results indicate that GFSFAN can achieve good CP with a small size. A sensor-to-segment coordinate calibration algorithm and lower-limb joint angle estimation algorithm are introduced. Experiments on the effect of the calibration and the introduction of joint angle on HAR shows that both of them can improve the CP.https://www.mdpi.com/1424-8220/21/3/692feature selectionhuman activity recognitionactivity of daily livingsensor fusionwearable sensorsgenetic algorithm |
| spellingShingle | Jingcheng Chen Yining Sun Shaoming Sun Improving Human Activity Recognition Performance by Data Fusion and Feature Engineering Sensors feature selection human activity recognition activity of daily living sensor fusion wearable sensors genetic algorithm |
| title | Improving Human Activity Recognition Performance by Data Fusion and Feature Engineering |
| title_full | Improving Human Activity Recognition Performance by Data Fusion and Feature Engineering |
| title_fullStr | Improving Human Activity Recognition Performance by Data Fusion and Feature Engineering |
| title_full_unstemmed | Improving Human Activity Recognition Performance by Data Fusion and Feature Engineering |
| title_short | Improving Human Activity Recognition Performance by Data Fusion and Feature Engineering |
| title_sort | improving human activity recognition performance by data fusion and feature engineering |
| topic | feature selection human activity recognition activity of daily living sensor fusion wearable sensors genetic algorithm |
| url | https://www.mdpi.com/1424-8220/21/3/692 |
| work_keys_str_mv | AT jingchengchen improvinghumanactivityrecognitionperformancebydatafusionandfeatureengineering AT yiningsun improvinghumanactivityrecognitionperformancebydatafusionandfeatureengineering AT shaomingsun improvinghumanactivityrecognitionperformancebydatafusionandfeatureengineering |