An Ensemble Learning Method for Robot Electronic Nose with Active Perception
The electronic nose is the olfactory organ of the robot, which is composed of a large number of sensors to perceive the smell of objects through free diffusion. Traditionally, it is difficult to realize the active perception function, and it is difficult to meet the requirements of small size, low c...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/11/3941 |
| _version_ | 1827690389431123968 |
|---|---|
| author | Shengming Li Lin Feng Yunfei Ge Li Zhu Liang Zhao |
| author_facet | Shengming Li Lin Feng Yunfei Ge Li Zhu Liang Zhao |
| author_sort | Shengming Li |
| collection | DOAJ |
| description | The electronic nose is the olfactory organ of the robot, which is composed of a large number of sensors to perceive the smell of objects through free diffusion. Traditionally, it is difficult to realize the active perception function, and it is difficult to meet the requirements of small size, low cost, and quick response that robots require. In order to address these issues, a novel electronic nose with active perception was designed and an ensemble learning method was proposed to distinguish the smell of different objects. An array of three MQ303 semiconductor gas sensors and an electrochemical sensor DART-2-Fe5 were used to construct the novel electronic nose, and the proposed ensemble learning method with four algorithms realized the active odor perception function. The experiment results verified that the accuracy of the active odor perception can reach more than 90%, even though it used 30% training data. The novel electronic nose with active perception based on the ensemble learning method can improve the efficiency and accuracy of odor data collection and olfactory perception. |
| first_indexed | 2024-03-10T10:38:31Z |
| format | Article |
| id | doaj.art-e4c5bd8bdac5467c8c39cf3b20660bd0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T10:38:31Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e4c5bd8bdac5467c8c39cf3b20660bd02023-11-21T23:10:14ZengMDPI AGSensors1424-82202021-06-012111394110.3390/s21113941An Ensemble Learning Method for Robot Electronic Nose with Active PerceptionShengming Li0Lin Feng1Yunfei Ge2Li Zhu3Liang Zhao4School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, ChinaSchool of Computer Science and Technology, Dalian University of Technology, Dalian 116024, ChinaSchool of Computer Science and Technology, Dalian University of Technology, Dalian 116024, ChinaKey Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian 116024, ChinaKey Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian 116024, ChinaThe electronic nose is the olfactory organ of the robot, which is composed of a large number of sensors to perceive the smell of objects through free diffusion. Traditionally, it is difficult to realize the active perception function, and it is difficult to meet the requirements of small size, low cost, and quick response that robots require. In order to address these issues, a novel electronic nose with active perception was designed and an ensemble learning method was proposed to distinguish the smell of different objects. An array of three MQ303 semiconductor gas sensors and an electrochemical sensor DART-2-Fe5 were used to construct the novel electronic nose, and the proposed ensemble learning method with four algorithms realized the active odor perception function. The experiment results verified that the accuracy of the active odor perception can reach more than 90%, even though it used 30% training data. The novel electronic nose with active perception based on the ensemble learning method can improve the efficiency and accuracy of odor data collection and olfactory perception.https://www.mdpi.com/1424-8220/21/11/3941electronic noseensemble learningactive perception |
| spellingShingle | Shengming Li Lin Feng Yunfei Ge Li Zhu Liang Zhao An Ensemble Learning Method for Robot Electronic Nose with Active Perception Sensors electronic nose ensemble learning active perception |
| title | An Ensemble Learning Method for Robot Electronic Nose with Active Perception |
| title_full | An Ensemble Learning Method for Robot Electronic Nose with Active Perception |
| title_fullStr | An Ensemble Learning Method for Robot Electronic Nose with Active Perception |
| title_full_unstemmed | An Ensemble Learning Method for Robot Electronic Nose with Active Perception |
| title_short | An Ensemble Learning Method for Robot Electronic Nose with Active Perception |
| title_sort | ensemble learning method for robot electronic nose with active perception |
| topic | electronic nose ensemble learning active perception |
| url | https://www.mdpi.com/1424-8220/21/11/3941 |
| work_keys_str_mv | AT shengmingli anensemblelearningmethodforrobotelectronicnosewithactiveperception AT linfeng anensemblelearningmethodforrobotelectronicnosewithactiveperception AT yunfeige anensemblelearningmethodforrobotelectronicnosewithactiveperception AT lizhu anensemblelearningmethodforrobotelectronicnosewithactiveperception AT liangzhao anensemblelearningmethodforrobotelectronicnosewithactiveperception AT shengmingli ensemblelearningmethodforrobotelectronicnosewithactiveperception AT linfeng ensemblelearningmethodforrobotelectronicnosewithactiveperception AT yunfeige ensemblelearningmethodforrobotelectronicnosewithactiveperception AT lizhu ensemblelearningmethodforrobotelectronicnosewithactiveperception AT liangzhao ensemblelearningmethodforrobotelectronicnosewithactiveperception |