Application of terahertz spectroscopy combined with feature improvement algorithm for the identification of adulterated rice seeds

In order to combat the adulteration of rice seeds for earning illegal huge profits, this paper presents a terahertz time-domain spectroscopy-based pattern recognition method for adulterated rice seeds. Based on the collected terahertz time-domain spectral data, the Relief algorithm, random forest (RF) algorithm and maximum corre-lation minimum redundancy (mRMR) algorithm are developed to select the characteristic frequencies, followed by two types of signal processing methods, Hilbert transform, Butterworth Low-Pass Filter, to process the spectral data and fuse them with the original spectral data. Finally, two machine learning models, support vector machine (SVM) model and extreme learning machine (ELM) model, are used to classify the spectral data samples after the feature processing. The results show that the sample spectral data processed by mRMR feature selection algo-rithm and Hilbert transform have the best recognition effect on the ELM model with an accuracy of 100%. This study has some reference significance for detecting adulterated rice seeds.

Automated summary

In this paper, a terahertz time-domain spectroscopy-based pattern recognition method is proposed to detect adulterated rice seeds in order to combat the adulteration behavior for illegal profits. Terahertz time-domain spectral data is collected, and the Relief algorithm, random forest (RF) algorithm, and maximum correlation minimum redundancy (mRMR) algorithm are employed to select characteristic frequencies. Two signal processing methods, Hilbert transform and Butterworth Low-Pass Filter, are used to process the spectral data and fuse them with the original data. Two machine learning models, support vector machine (SVM) and extreme learning machine (ELM), are applied for classification. The results show that the ELM model achieves an accuracy of 100% with the mRMR feature selection algorithm and Hilbert transform. This study is of reference significance for detecting adulterated rice seeds.