Convolutional neural network allows amylose content prediction in yam (Dioscorea alata L.) flour using near infrared spectroscopy
Houngbo, Mahugnon Ezekiel | Desfontaines, Lucienne | Diman, Jean-Louis | Arnau, Gemma | Mestres, Christian | Davrieux, Fabrice | Rouan, Lauriane | Beurier, Grégory | Marie-Magdeleine, Carine | Meghar, Karima | Alamu, Emmanuel Oladeji | Otegbayo, Bolanle Omolara | Cornet, Denis
Background: Yam (Dioscorea alata L.) is the staple food of many populations in the intertropical zone where it is grown. The lack of phenotyping methods for tuber quality hinders the adoption of new genotypes from the breeding programs. Recently, near infrared spectroscopy (NIRS) has been used as a reliable tool to characterize the chemical composition of the yam tuber. However, it failed to predict the amylose content, although this trait is strongly involved in the quality of the product. Results: This study used NIRS to predict the amylose content from 186 yam flour samples. Two calibration methods were developed and validated on an independent dataset: Partial Least Square (PLS) and Convolutional Neural Network (CNN). To evaluate final model performances, the coefficient of determination (R2), the root mean square error (RMSE), and the Ratio of Performance to Deviation (RPD) were calculated using predictions on an independent validation dataset. Tested models showed contrasting performances (i.e. R2 of 0.72 and 0.89, RMSE of 1.33 and 0.81, RPD of 2.13 and 3.49 respectively, for the PLS and the CNN model). Conclusion: According to the quality standard for NIRS model prediction used in food science, the PLS method proved unsuccessful (RPD<3 and R2<0.8) for predicting amylose content from yam flour, while the CNN proved reliable and efficient method. With the application of deep learning method, this study established the proof of concept that amylose content, a key driver of yam textural quality and acceptance, could be predicted accurately using NIRS as a high throughput phenotyping method.
Показать больше [+] Меньше [-]