Abstract
Electronic nose (E-nose), as a device intended to detect odors or flavors, has been widely used in many fields. Many labeled samples are needed to gain an ideal E-nose classification model. However, the labeled samples are not easy to obtain and there are some cases where the gas samples in the real world are complex and unlabeled. As a result, it is necessary to make an E-nose that cannot only classify unlabeled samples, but also use these samples to modify its classification model. In this paper, we first introduce a semi-supervised learning algorithm called S4VMs and improve its use within a multi-classification algorithm to classify the samples for an E-nose. Then, we enhance its performance by adding the unlabeled samples that it has classified to modify its model and by using an optimization algorithm called quantum-behaved particle swarm optimization (QPSO) to find the optimal parameters for classification. The results of comparing this with other semi-supervised learning algorithms show that our multi-classification algorithm performs well in the classification system of an E-nose after learning from unlabeled samples.
Highlights
Pollution attracts more and more attention as people grow more highly aware of air quality issues.As a result, it is important to detect indoor air pollution effectively
Many effective feature extraction methods have been applied for Electronic nose (E-nose); for example, principal component analysis (PCA) [20,21] uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables, which can significantly reduce the dimensions of target samples
The rest of this paper is organized as follows: Section 2 introduces the E-nose system, experimental procedure, and the data set of this paper; Section 3 presents the theory of the S4VMs technique and our enhancement algorithm; Section 4 describes the results of multi-classification S4VMs (M-S4VMs) while it is used for training the classification system of E-nose to distinguish target pollution gases, and to compare with other semi-supervised algorithms
Summary
Pollution attracts more and more attention as people grow more highly aware of air quality issues. Many effective feature extraction methods have been applied for E-nose; for example, principal component analysis (PCA) [20,21] uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables, which can significantly reduce the dimensions of target samples Another way to enhance the efficiency of an E-nose system is to use advanced analysis algorithms. The rest of this paper is organized as follows: Section 2 introduces the E-nose system, experimental procedure, and the data set of this paper; Section 3 presents the theory of the S4VMs technique and our enhancement algorithm; Section 4 describes the results of multi-classification S4VMs (M-S4VMs) while it is used for training the classification system of E-nose to distinguish target pollution gases, and to compare with other semi-supervised algorithms.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have