| abstract |
The purpose of the present invention is to provide a method for evaluating the overall sensory quality of tobacco leaves based on near-infrared spectroscopy. The present invention uses near-infrared spectroscopy to model and predict a comprehensive sensory index. In the modeling process, a constraint matrix is introduced to maintain high-scoring samples. In the case of constraint solving, it is easier to find abnormal sensory data and adjust the model, and the accuracy of the model has reached the accuracy required by the actual work; the prediction results of the model, for Samples with large differences have a good degree of discrimination, which is more in line with the evaluation results in actual work. |