نوع مقاله : مقاله پژوهشی
نویسندگان
1 دانشگاه محقق اردبیلی- گروه مهندسی بیوسیستم- دانشکده کشاورزی و منابع طبیعی- دانشگاه محقق اردبیلی- اردبیل- ایران
2 'گروه مهندسی بیوسیستم، دانشکده کشاورزی و منابع طبیعی، دانشگاه محقق اردبیلی، اردبیل-ایران
چکیده
کلیدواژه‌ها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
This study investigates the application of the random forest algorithm in spectroscopic methods, especially Vis-NIR (Vis-NIR) spectroscopy, to predict key quality characteristics of cherries. This paper aims to present a reliable and efficient method for the non-destructive evaluation of sugar content, acidity, and firmness, which are essential factors determining cherry quality and consumer acceptance. In this study, 400 random samples of cherry products were prepared. Spectral data were obtained. Next, the spectral data obtained from Vis-NIR spectroscopy were evaluated by the Relief method, and five effective wavelengths (for firmness, soluble solid content and cherry acidity, wavelengths between 615 to 650, 650 to 675 and 818 to 945, respectively) were selected separately for each of the values of the dependent variables (sugar, acidity, and hardness values). Next, the reflection intensity values related to the selected effective wavelengths were selected as input features for the random forest model. The performance of the model was evaluated in terms of prediction accuracy through cross-validation and independent evaluation tests, using root mean square error (RMSE) and correlation coefficient (CC). The results show the effectiveness of the random forest algorithm in accurately predicting sugar content (with a correlation coefficient of about 0.93 and a mean square error of about 3.4), acidity (with a correlation coefficient of about 0.95 and a mean square error of about 0.87) and cherry firmness. (With a correlation coefficient of about 0.92 and a mean square error of about 1.2) is based on spectral information. This approach provides a quick, non-destructive, cost-effective solution for product quality assessment in the cherry industry. Also, with progress in this area, producers and stakeholders can make informed decisions about harvesting, sorting and post-harvest processes.
کلیدواژه‌ها [English]
)