Knowledge Distillation Facilitates the Lightweight and Efficient Plant Diseases Detection Model

Plant disease diagnosis in time can inhibit the spread of the disease and prevent a large-scale drop in production,which benefits food production.Object detection-based plant disease diagnosis methods have attracted widespread attention due to their accuracy in classifying and locating diseases.However,existing methods are still limited to single crop disease diagnosis.More importantly,the existing model has a large number of parameters,which is not conducive to deploying it to agricultural mobile devices.Nonetheless,reducing the number of model parameters tends to cause a decrease in model accuracy.To solve these problems,we propose a plant disease detection method based on knowledge distillation to achieve a lightweight and efficient diagnosis of multiple diseases across multiple crops.In detail,we design 2 strategies to build 4 different lightweight models as student models:the YOLOR-Light-v1,YOLOR-Light-v2,Mobile-YOLOR-v1,and Mobile-YOLOR-v2 models,and adopt the YOLOR model as the teacher model.We develop a multistage knowledge distillation method to improve lightweight model performance,achieving 60.4%mAP@.5 in the PlantDoc dataset with small model parameters,outperforming existing methods.Overall,the multistage knowledge distillation technique can make the model lighter while maintaining high accuracy.Not only that,the technique can be extended to other tasks,such as image classification and image segmentation,to obtain automated plant disease diagnostic models with a wider range of lightweight applicability in smart agriculture.Our code is available at https://github.com/QDH/MSKD.

PDDD-PreTrain:A Series of Commonly Used Pre-Trained Models Support Image-Based Plant Disease Diagnosis

Plant diseases threaten global food security by reducing crop yield;thus,diagnosing plant diseases is critical to agricultural production.Artificial intelligence technologies gradually replace traditional plant disease diagnosis methods due to their time-consuming,costly,inefficient,and subjective disadvantages.As a mainstream AI method,deep learning has substantially improved plant disease detection and diagnosis for precision agriculture.In the meantime,most of the existing plant disease diagnosis methods usually adopt a pre-trained deep learning model to support diagnosing diseased leaves.However,the commonly used pre-trained models are from the computer vision dataset,not the botany dataset,which barely provides the pre-trained models sufficient domain knowledge about plant disease.Furthermore,this pre-trained way makes the final diagnosis model more difficult to distinguish between different plant diseases and lowers the diagnostic precision.To address this issue,we propose a series of commonly used pre-trained models based on plant disease images to promote the performance of disease diagnosis.In addition,we have experimented with the plant disease pre-trained model on plant disease diagnosis tasks such as plant disease identification,plant disease detection,plant disease segmentation,and other subtasks.The extended experiments prove that the plant disease pre-trained model can achieve higher accuracy than the existing pre-trained model with less training time,thereby supporting the better diagnosis of plant diseases.In addition,our pre-trained models will be open-sourced at https://pd.samlab.cn/and Zenodo platform https://doi.org/10.5281/zenodo.7856293.

Insight into the Structural Requirements of Protoporphyrino- gen Oxidase Inhibitors： Molecular Docking and CoMFA of Di- phenyl Ether, Isoxazole Phenyl, and Pyrazole Phenyl Ether

Protoporphyrinogen oxidase （PPO, EC 1.3.3.4） is one of the most significant targets for a large family of in- hibitors that may be used as herbicide, bactericide, fungicide, or photosensitizing activator to treat cancer through photodynamic therapy （PDT）. Molecular docking and CoMFA were combined in a multistep framework with the ultimate goal of identifying important factor contributing to the activity of PPO inhibitors. As a continuation of the previous research work on the development of new PPO inhibitors, the bioassay results indicated that good PPO in- hibitors were discovered in all of the three chemical series with ICs0 values ranging from 0.010 to 0.061 pmol·L ^-1. Using the crystal structure of tobacco mitochondrial PPO （mtPPO） as template, all the compounds were docked into the enzyme active site. The docking pose of each compound was subsequently used in a receptor-based alignment, leading to the development of a significant CoMFA model with r^2 value of 0.98 and q^2 （cross validation r^2） value of 0.63. This novel multistep framework gives insight into the and it can be extended to other classes of PPO inhibitors. In be particularly applicable in virtual screening procedures. structural characteristics for the binding of inhibitors, addition, the simplicity of the proposed approach may