Research on a Mixed Gas Classification Algorithm Based on Extreme Random Tree
Because of the low accuracy of the current machine olfactory algorithms in detecting two mixed gases, this study proposes a hybrid gas detection algorithm based on an extreme random tree to greatly improve the classification accuracy and time efficiency. The method mainly uses the dynamic time warpi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-04-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/9/9/1728 |
id |
doaj-6701c821bacc497f9894cd6adb2cf649 |
---|---|
record_format |
Article |
spelling |
doaj-6701c821bacc497f9894cd6adb2cf6492020-11-25T01:23:18ZengMDPI AGApplied Sciences2076-34172019-04-0199172810.3390/app9091728app9091728Research on a Mixed Gas Classification Algorithm Based on Extreme Random TreeYonghui Xu0Xi Zhao1Yinsheng Chen2Zixuan Yang3School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Measurement and Control Technology and Communication Engineering, Harbin University of Science and Technology, Harbin 150001, ChinaSchool of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin 150001, ChinaBecause of the low accuracy of the current machine olfactory algorithms in detecting two mixed gases, this study proposes a hybrid gas detection algorithm based on an extreme random tree to greatly improve the classification accuracy and time efficiency. The method mainly uses the dynamic time warping algorithm (DTW) to perform data pre-processing and then extracts the gas characteristics from gas signals at different concentrations by applying a principal component analysis (PCA). Finally, the model is established by using a new extreme random tree algorithm to achieve the target gas classification. The sample data collected by the experiment was verified by comparison experiments with the proposed algorithm. The analysis results show that the proposed DTW algorithm improves the gas classification accuracy by 26.87%. Compared with the random forest algorithm, extreme gradient boosting (XGBoost) algorithm and gradient boosting decision tree (GBDT) algorithm, the accuracy rate increased by 4.53%, 5.11% and 8.10%, respectively, reaching 99.28%. In terms of the time efficiency of the algorithms, the actual runtime of the extreme random tree algorithm is 66.85%, 90.27%, and 81.61% lower than that of the random forest algorithm, XGBoost algorithm, and GBDT algorithm, respectively, reaching 103.2568 s.https://www.mdpi.com/2076-3417/9/9/1728machine olfactiongas recognitionextreme random treedynamic time regulationrandom forestfeature engineering |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yonghui Xu Xi Zhao Yinsheng Chen Zixuan Yang |
spellingShingle |
Yonghui Xu Xi Zhao Yinsheng Chen Zixuan Yang Research on a Mixed Gas Classification Algorithm Based on Extreme Random Tree Applied Sciences machine olfaction gas recognition extreme random tree dynamic time regulation random forest feature engineering |
author_facet |
Yonghui Xu Xi Zhao Yinsheng Chen Zixuan Yang |
author_sort |
Yonghui Xu |
title |
Research on a Mixed Gas Classification Algorithm Based on Extreme Random Tree |
title_short |
Research on a Mixed Gas Classification Algorithm Based on Extreme Random Tree |
title_full |
Research on a Mixed Gas Classification Algorithm Based on Extreme Random Tree |
title_fullStr |
Research on a Mixed Gas Classification Algorithm Based on Extreme Random Tree |
title_full_unstemmed |
Research on a Mixed Gas Classification Algorithm Based on Extreme Random Tree |
title_sort |
research on a mixed gas classification algorithm based on extreme random tree |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2019-04-01 |
description |
Because of the low accuracy of the current machine olfactory algorithms in detecting two mixed gases, this study proposes a hybrid gas detection algorithm based on an extreme random tree to greatly improve the classification accuracy and time efficiency. The method mainly uses the dynamic time warping algorithm (DTW) to perform data pre-processing and then extracts the gas characteristics from gas signals at different concentrations by applying a principal component analysis (PCA). Finally, the model is established by using a new extreme random tree algorithm to achieve the target gas classification. The sample data collected by the experiment was verified by comparison experiments with the proposed algorithm. The analysis results show that the proposed DTW algorithm improves the gas classification accuracy by 26.87%. Compared with the random forest algorithm, extreme gradient boosting (XGBoost) algorithm and gradient boosting decision tree (GBDT) algorithm, the accuracy rate increased by 4.53%, 5.11% and 8.10%, respectively, reaching 99.28%. In terms of the time efficiency of the algorithms, the actual runtime of the extreme random tree algorithm is 66.85%, 90.27%, and 81.61% lower than that of the random forest algorithm, XGBoost algorithm, and GBDT algorithm, respectively, reaching 103.2568 s. |
topic |
machine olfaction gas recognition extreme random tree dynamic time regulation random forest feature engineering |
url |
https://www.mdpi.com/2076-3417/9/9/1728 |
work_keys_str_mv |
AT yonghuixu researchonamixedgasclassificationalgorithmbasedonextremerandomtree AT xizhao researchonamixedgasclassificationalgorithmbasedonextremerandomtree AT yinshengchen researchonamixedgasclassificationalgorithmbasedonextremerandomtree AT zixuanyang researchonamixedgasclassificationalgorithmbasedonextremerandomtree |
_version_ |
1725123081301655552 |