Rectification and diffusion of non-interacting self-propelled particles is numerically investigated in a two-dimensional corrugated channel. From numerical simulations, we obtain the average velocity and the effective diffusion coefficient. It is found that the self-propelled particles can be rectified by the self-propelled velocity. There exist optimal values of the parameters (the selfpropelled velocity, the translational diffusion constant, and the height of the potential) at which the average velocity takes its maximal value. There exists an optimal translational diffusion at which the effective diffusion constant is maximal. The self-propelled velocity can strongly increase the effective diffusion, while the large rotational diffusion rate can strongly suppress the effective diffusion.

The segmentation and classification of leaves in plant images are a great challenge, especially when several leaves are overlapping in images with a complicated background. In this paper, the segmentation and classification of leaf images with a complicated background using deep learning are studied. First, more than 2500 leaf images with a complicated background are collected and artificially labeled with target pixels and background pixels. Two-thousand of them are fed into a Mask Region-based Convolutional Neural Network (Mask R-CNN) to train a model for leaf segmentation. Then, a training set that contains more than 1500 training images of 15 species is fed into a very deep convolutional network with 16 layers (VGG16) to train a model for leaf classification. The best hyperparameters for these methods are found by comparing a variety of parameter combinations. The results show that the average Misclassification Error (ME) of 80 test images using Mask R-CNN is 1.15%. The average accuracy value for the leaf classification of 150 test images using VGG16 is up to 91.5%. This indicates that these methods can be used to segment and classify the leaf image with a complicated background effectively. It could provide a reference for the phenotype analysis and automatic classification of plants.

No abstract

We study the rectified transport of underdamped active noninteracting particles in an asymmetric periodic potential. It is found that the ratchet effect of active noninteracting particles occurs in a single direction (along the easy direction of the substrate asymmetry) in the overdamped limit. However, when the inertia is considered, it is possible to observe reversals of the ratchet effect, where the motion is along the hard direction of the substrate asymmetry. By changing the friction coefficient or the self-propulsion force, the average velocity can change its direction several times. Therefore, by suitably tailoring the parameters, underdamped active particles with different self-propulsion forces can move in different directions and can be separated.

No abstract