Sensor selection scheme in activity recognition based on hierarchical feature reduction
To better understand the activity state of human, we might need multiple sensors on different parts of the body. According to different types of activities, the number and slot of required sensors would also be different. Therefore, how to determine the number and slot of necessary sensors regarding...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-08-01
|
| Series: | International Journal of Distributed Sensor Networks |
| Online Access: | https://doi.org/10.1177/1550147718793801 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832545216189431808 |
|---|---|
| author | Yu Wei Libin Jiao Jie Sha Jixin Ma Anton Umek Anton Kos |
| author_facet | Yu Wei Libin Jiao Jie Sha Jixin Ma Anton Umek Anton Kos |
| author_sort | Yu Wei |
| collection | DOAJ |
| description | To better understand the activity state of human, we might need multiple sensors on different parts of the body. According to different types of activities, the number and slot of required sensors would also be different. Therefore, how to determine the number and slot of necessary sensors regarding to wearers’ experience and processing efficiency is a meaningful study in actual practice. In this work, we propose a novel sensor selection scheme that is based on the improvement of the feature reduction process of the recognition. This scheme applies a hierarchical feature reduction method based on mutual information with max relevance and low-dimensional embedding strategy. It divides the process of feature reduction into two stages: first, redundant sensors are removed with one-order sequential forward selection based on mutual information; second, feature selection strategy that maximizing class-relevance is integrated with low-dimensional mapping so that the set of features will be further compressed. To verify the feasibility and superiority of the scheme, we design a complete solution for real practice of human activity recognition. According to the results of the experiments, we are able to recognize human activities accurately and efficiently with as few sensors as possible. |
| format | Article |
| id | doaj-art-18fe2e4e6e464145b5c6517e6ea73560 |
| institution | Kabale University |
| issn | 1550-1477 |
| language | English |
| publishDate | 2018-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Distributed Sensor Networks |
| spelling | doaj-art-18fe2e4e6e464145b5c6517e6ea735602025-02-03T07:26:22ZengWileyInternational Journal of Distributed Sensor Networks1550-14772018-08-011410.1177/1550147718793801Sensor selection scheme in activity recognition based on hierarchical feature reductionYu Wei0Libin Jiao1Jie Sha2Jixin Ma3Anton Umek4Anton Kos5Computer Teaching and Research Section, Capital University of Physical Education and Sports, Beijing, ChinaCollege of Information Science and Technology, Beijing Normal University, Beijing, ChinaComputer Teaching and Research Section, Capital University of Physical Education and Sports, Beijing, ChinaFaculty of Architecture, Computing and Humanities, University of Greenwich, London, UKFaculty of Electrical Engineering, University of Ljubljana, Ljubljana, SloveniaFaculty of Electrical Engineering, University of Ljubljana, Ljubljana, SloveniaTo better understand the activity state of human, we might need multiple sensors on different parts of the body. According to different types of activities, the number and slot of required sensors would also be different. Therefore, how to determine the number and slot of necessary sensors regarding to wearers’ experience and processing efficiency is a meaningful study in actual practice. In this work, we propose a novel sensor selection scheme that is based on the improvement of the feature reduction process of the recognition. This scheme applies a hierarchical feature reduction method based on mutual information with max relevance and low-dimensional embedding strategy. It divides the process of feature reduction into two stages: first, redundant sensors are removed with one-order sequential forward selection based on mutual information; second, feature selection strategy that maximizing class-relevance is integrated with low-dimensional mapping so that the set of features will be further compressed. To verify the feasibility and superiority of the scheme, we design a complete solution for real practice of human activity recognition. According to the results of the experiments, we are able to recognize human activities accurately and efficiently with as few sensors as possible.https://doi.org/10.1177/1550147718793801 |
| spellingShingle | Yu Wei Libin Jiao Jie Sha Jixin Ma Anton Umek Anton Kos Sensor selection scheme in activity recognition based on hierarchical feature reduction International Journal of Distributed Sensor Networks |
| title | Sensor selection scheme in activity recognition based on hierarchical feature reduction |
| title_full | Sensor selection scheme in activity recognition based on hierarchical feature reduction |
| title_fullStr | Sensor selection scheme in activity recognition based on hierarchical feature reduction |
| title_full_unstemmed | Sensor selection scheme in activity recognition based on hierarchical feature reduction |
| title_short | Sensor selection scheme in activity recognition based on hierarchical feature reduction |
| title_sort | sensor selection scheme in activity recognition based on hierarchical feature reduction |
| url | https://doi.org/10.1177/1550147718793801 |
| work_keys_str_mv | AT yuwei sensorselectionschemeinactivityrecognitionbasedonhierarchicalfeaturereduction AT libinjiao sensorselectionschemeinactivityrecognitionbasedonhierarchicalfeaturereduction AT jiesha sensorselectionschemeinactivityrecognitionbasedonhierarchicalfeaturereduction AT jixinma sensorselectionschemeinactivityrecognitionbasedonhierarchicalfeaturereduction AT antonumek sensorselectionschemeinactivityrecognitionbasedonhierarchicalfeaturereduction AT antonkos sensorselectionschemeinactivityrecognitionbasedonhierarchicalfeaturereduction |