A New Mixed-Gas-Detection Method Based on a Support Vector Machine Optimized by a Sparrow Search Algorithm

To solve the problem of the low recognition rate of mixed gases and consider the phenomenon of low prediction accuracy when traditional gas-concentration-prediction methods deal with nonlinear data, this paper proposes a mixed-gas identification and gas-concentration-prediction method based on a sup...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Vol. 22; no. 22; p. 8977
Main Authors: Zhang, Haitao, Han, Yaozhen
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 20.11.2022
MDPI
Subjects:
Accuracy
Agricultural production
Algorithms
Artificial intelligence
Carbon monoxide
Classification
Datasets
Gases
Interdisciplinary subjects
Machine learning
Methods
mixed-gas detection
Neural networks
Neural Networks, Computer
Optimization algorithms
Pattern recognition
prediction
Principal Component Analysis
Sensors
sparrow search algorithm
Support Vector Machine
Support vector machines
Unmanned aerial vehicles
Water quality
prediction
sparrow search algorithm
support vector machine
classification
mixed-gas detection
ISSN:1424-8220, 1424-8220
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To solve the problem of the low recognition rate of mixed gases and consider the phenomenon of low prediction accuracy when traditional gas-concentration-prediction methods deal with nonlinear data, this paper proposes a mixed-gas identification and gas-concentration-prediction method based on a support vector machine (SVM) optimized by a sparrow search algorithm (SSA). Principal component analysis (PCA) is applied to perform data dimensionality reduction on the input data, and SSA is adopted to optimize the SVM hyperparameters to improve the recognition rate and gas-concentration-prediction accuracy of mixed gases. For the mixed-gas identification, the classification accuracy is significantly improved under the proposed SSA optimization SVM method (SSA-SVM), compared with random forest (RF), extreme-learning machine (ELM), and BP neural network methods. With respect to gas-concentration prediction, the maximum fitting degrees reached 99.34% for single gas-concentration prediction and 97.55% for mixed-gas-concentration prediction. The experimental results show that the SSA-SVM method had a high recognition rate and high concentration-prediction accuracy in gas-mixture detection.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s22228977