Geographical traceability of Marsdenia tenacissima by Fourier transform infrared spectroscopy and chemometrics

• Five pretreatment methods and six machine learning techniques were compared.
• Optimal discrimination model was obtained by K-nearest neighbors algorithm.
• 100% correct classification was achieved for the prediction set.

A combination of Fourier transform infrared spectroscopy with chemometrics tools provided an approach for studying Marsdenia tenacissima according to its geographical origin. A total of 128 M. tenacissima samples from four provinces in China were analyzed with FTIR spectroscopy. Six pattern recognition methods were used to construct the discrimination models: support vector machine–genetic algorithms, support vector machine–particle swarm optimization, K-nearest neighbors, radial basis function neural network, random forest and support vector machine–grid search. Experimental results showed that K-nearest neighbors was superior to other mathematical algorithms after data were preprocessed with wavelet de-noising, with a discrimination rate of 100% in both the training and prediction sets. This study demonstrated that FTIR spectroscopy coupled with K-nearest neighbors could be successfully applied to determine the geographical origins of M. tenacissima samples, thereby providing reliable authentication in a rapid, cheap and noninvasive way.

Figure optionsDownload as PowerPoint slide