RESUMEN
The value of Baijiu is affected by its flavor, age, and adulteration. Therefore, a simple and rapid identification method is crucial for the market. In this study, we present a rapid, non-intrusive identification technique for Baijiu utilizing the Tyndall effect combined with chemometrics analysis. Our experiment begins illuminating Baijiu with a 405 nm wavelength laser and recording the resulting bright light path due to the Tyndall effect. To further analyze the color and brightness information, Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Hierarchical Cluster Analysis (HCA), and Multilayer Perceptron (MLP) were employed. This study establishes correlations between the brightness of the Tyndall light path and seven trace flavor compounds in Baijiu. The findings demonstrate that this method effectively identifies the flavor, age cellar, and adulteration of Baijiu and also quantitatively detects the concentrations of flavor compounds. Additionally, an analysis platform was developed to enable the rapid identification of Baijiu.
RESUMEN
There are many rice diseases, which have very serious negative effects on rice growth and final yield. It is very important to identify the categories of rice diseases and control them. In the past, the identification of rice disease types was completely dependent on manual work, which required a high level of human experience. But the method often could not achieve the desired effect, and was difficult to popularize on a large scale. Convolutional neural networks are good at extracting localized features from input data, converting low-level shape and texture features into high-level semantic features. Models trained by convolutional neural network technology based on existing data can extract common features of data and make the framework have generalization ability. Applying ensemble learning or transfer learning techniques to convolutional neural network can further improve the performance of the model. In recent years, convolutional neural network technology has been applied to the automatic recognition of rice diseases, which reduces the manpower burden and ensures the accuracy of recognition. In this paper, the applications of convolutional neural network technology in rice disease recognition are summarized, and the fruitful achievements in rice disease recognition accuracy, speed, and mobile device deployment are described. This paper also elaborates on the lightweighting of convolutional neural networks for real-time applications as well as mobile deployments, and the various improvements in the dataset and model structure to enhance the model recognition performance.