No abstract

Apples are the fourth most produced fruit in the world, so it is important to safeguard them from disease damage. Although there are many deep learning-based plant disease detection models, the existing deep learning networks have complex structures and require large amounts of computational resources for support. Lightweight networks such as MobileNet and ShuffleNet designed for mobile devices could achieve better classification and faster recognition on public datasets, but their accuracy rates are not yet up to the requirements of practical applications. To address these problems, we constructed an improved apple leaf disease recognition algorithm based on MobileNetV2. We used feature reuse to improve the network structure, added a dense connection structure to the inverse residual module, and an ECA-Net attention module to increase the model's focus on diseased regions. We trained the improved model on the network on a dataset expanded by a generative adversarial network. The results showed that the improved model had a smaller number of model parameters, only 3.3 M, and a higher accuracy rate of 96.23% compared to Resnet50, ShuffleNet, and MobileNet models. The improved model had only 0.34 M addition in the number of parameters compared with MobileNet-V2, and had a 2.2% improvement in accuracy.

In this letter, we propose a nonlinear Magnetoelastic Energy (ME) with a material parameter related to electron interactions. An attenuating term is contained in the formula of the proposed nonlinear ME, which can predict the variation in the anisotropic magneto-crystalline constants induced by external stress more accurately than the classical linear ME. The domain wall velocity under stress and magnetic field can be predicted accurately based on the nonlinear ME. The proposed nonlinear ME model is concise and easy to use. It is important in sensor analysis and production, magneto-acoustic coupling motivation, magnetoelastic excitation, etc.