Phase diagram combined with improved fuzzy support vector machine for rapid and nondestructive detection of Diarrhetic shellfish poisoning

Background. The diarrhoeal shellfish poisoning (DSP) toxin is a powerful marine biological toxin. Eating DSP toxin-contaminated mussels will lead to serious gastrointestinal diseases. To this end, method for the detection of toxins using near-infrared reflectance spectroscopy combined with pattern recognition proposed. Material and methods. In range from 950−1700 nm, spectral data healthy DSP-contaminated were obtained. select optimal band subsets, selection algorithm based on model cluster analysis was applied. As distinguishing classification problem imbalanced data, an improved fuzzy support vector machine-based influence parameters machine performance analyzed. Results. Compared traditional machine, proposed has better in detecting not affected by imbalance ratio. Its geometric mean value can reach 0.9886 accuracy 98.83%. Conclusion. results show that as innovative, fast convenient analytical method, feasible mussels.