Have a personal or library account? Click to login

Research on gas concentration identification based on sparrow search algorithm optimization SVR

Open Access
|Jul 2025

Figures & Tables

Figure 1:

Flow chart of the gas concentration prediction algorithm. SSA, sparrow search algorithm; SVR, support vector regression.
Flow chart of the gas concentration prediction algorithm. SSA, sparrow search algorithm; SVR, support vector regression.

Figure 2:

Fitness change curves of two different algorithms. SSA, sparrow search algorithm.
Fitness change curves of two different algorithms. SSA, sparrow search algorithm.

Figure 3:

The absolute error of the two algorithm models. SSA, sparrow search algorithm; SVM, support vector machine.
The absolute error of the two algorithm models. SSA, sparrow search algorithm; SVM, support vector machine.

Initial parameter table

ParameterValue
Maximum iterations200
Population size100
Optimization parameter number2
Upper limit of optimization parameter2−10
Lower limit of optimization parameter210
Cross-check the number of folds5

Model parameter settings

AlgorithmParameterValue rangeOptimum value
SVRC/10
g 0.5
SSA-SVRAlarm value[0.5, 1]0.8
Safety threshold[0, 1]0.2
TSSA-SVRAlarm value[0.5, 1]0.8
Safety threshold[0, 1]0.2

Quantitative identification results of mixed gases

ModelRMSEMAER2Acc (%)
SVR2.6262.3360.09581.80
SSA-SVR1.9821.4850.37587.43
GA-SVR1.8921.3670.48289.67
PSO-SVR1.7651.2200.51290.36
TSSA-SVR0.2860.4250.89694.47
Language: English
Submitted on: Oct 13, 2024
Published on: Jul 26, 2025
Published by: Professor Subhas Chandra Mukhopadhyay
In partnership with: Paradigm Publishing Services
Publication frequency: 1 times per year

© 2025 Yuanman Zhang, Yanan Zou, Qingyun Wu, published by Professor Subhas Chandra Mukhopadhyay
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.