A Method of Water Quality Assessment Based on Biomonitoring and Multiclass Support Vector Machine

Integrating biological monitoring method with computer vision technology, acute toxicity test was performed to study the toxic effects of Cu2+ with different concentration on zebrafish (Danio rerio). The Behavioral response of school of fish in a tank was quantified and an early warning system was developed in the study. In the system, the real-time quantified data were saved to database and the Multiclass Support Vector Machine (SVM) was used to make comprehensive assessment according to behavioral difference of fish school in different toxicity environment. The prediction accuracies are satisfactory, which indicate that this approach is effectual for assessment of water quality.