Online classification of contaminants based on multi-classification support vector machine using conventional water quality sensors

8Citations
Citations of this article
22Readers
Mendeley users who have this article in their library.

Abstract

Water quality early warning system is mainly used to detect deliberate or accidental water pollution events in water distribution systems. Identifying the types of pollutants is necessary after detecting the presence of pollutants to provide warning information about pollutant characteristics and emergency solutions. Thus, a real-time contaminant classification methodology, which uses the multi-classification support vector machine (SVM), is proposed in this study to obtain the probability for contaminants belonging to a category. The SVM-based model selected samples with indistinct feature, which were mostly low-concentration samples as the support vectors, thereby reducing the influence of the concentration of contaminants in the building process of a pattern library. The new sample points were classified into corresponding regions after constructing the classification boundaries with the support vector. Experimental results show that the multi-classification SVM-based approach is less affected by the concentration of contaminants when establishing a pattern library compared with the cosine distance classification method. Moreover, the proposed approach avoids making a single decision when classification features are unclear in the initial phase of injecting contaminants.

Cite

CITATION STYLE

APA

Huang, P., Jin, Y., Hou, D., Yu, J., Tu, D., Cao, Y., & Zhang, G. (2017). Online classification of contaminants based on multi-classification support vector machine using conventional water quality sensors. Sensors (Switzerland), 17(3). https://doi.org/10.3390/s17030581

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free