Identification Method of Citrus Aurantium Diseases and Pests Based on Deep Convolutional Neural Network.

The traditional identification methods of Citrus aurantium diseases and pests are prone to convergence during the running process, resulting in low accuracy of identification. To this end, this study reviews the newest methods for the identification of Citrus aurantium diseases and pests based on a deep convolutional neural network (DCNN). The initial images of Citrus aurantium leaves are collected by hardware equipment and then preprocessed using the techniques of cropping, enhancement, and morphological transformation. By using the neural network to divide the disease spots of Citrus aurantium images, accurate recognition results are obtained through feature matching. The comparative experimental results show that, compared with the traditional recognition method, the recognition rate of the proposed method has increased by about 11.9%, indicating its better performance. The proposed method can overcome the interference of the external environment to a certain extent and can provide reference data for the prevention and control of Citrus aurantium diseases and pests.

An auto real-time jump tagging system for exploring stereotyped jumping behavior in mice.

The jump is one of the common stereotyped behavior in rodents which can be found in certain types of disease models, such as addiction. It can be easily identified by the human eye. However, it is difficult to be tagged in real-time by manual operation, which limits the detailed exploration of its neural mechanisms with the new techniques, such as fiber photometry recording. Here we introduced an auto real-time jump tagging system (Art-JT system) to record the jump based on online monitoring the pressure changes of the floor in which the mouse is free exploring. Meanwhile, the Art-JT system can send the digital signal of the jump timing to the external device for tagging the events in the fiber photometry system. We tested it with the mice induced by Naloxone precipitated withdrawal jumping and found that it could accurately record the jump events and provide several detailed parameters of the jump. We also confirmed that the jump was correlated with the medial prefrontal cortex and primary motor cortex neuronal activities by combining the Art-JT system, GCaMP6 mice, and fiber photometry system. Our results suggested that the Art-JT system may be a powerful tool for recording and analyzing jumps efficiently and helping us to understand stereotyped behavior.