Aspect-oriented Fine-grained Opinion Extraction （AFOE） extracts aspect terms and opinion terms from reviews in the form of opinion pairs or additionally extracts sentiment polarities of aspect terms on the basis of the above to form opinion triplets. Aiming at the problem of neglecting correlation between the opinion pairs and contexts， an aspect-oriented Adaptive Span Feature-Grid Tagging Scheme （ASF-GTS） model was proposed. Firstly， BERT （Bidirectional Encode Representation from Transformers） model was used to obtain the feature representation of the sentence. Then， the correlation between the opinion pair and local context was enhanced by the Adaptive Span Feature （ASF） method. Next， Opinion Pair Extraction （OPE） was transformed into a uniform grid tagging task by Grid Tagging Scheme （GTS）. Finally， the corresponding opinion pairs or opinion triplet were generated by the specific decoding strategy. Experiments were carried out on four AFOE benchmark datasets adaptive to the task of opinion tuple extraction. The results show that compared with GTS-BERT （Grid Tagging Scheme-BERT） model， the proposed model has the F1-score improved by 2.42% to 7.30% and 2.62% to 6.61% on opinion pair or opinion triplet tasks， respectively. The proposed model can effectively reserve the sentiment correlation between opinion pair and context， and extract opinion pairs and their sentiment polarities more accurately.

Due to the complex and variable structure of fundus vessels， and the low contrast between the fundus vessel and the background， there are huge difficulties in segmentation of fundus vessels， especially small fundus vessels. U-Net based on deep fully convolutional neural network can effectively extract the global and local information of fundus vessel images，but its output is grayscale image binarized by a hard threshold， which will cause the loss of vessel area， too thin vessel and other problems. To solve these problems， U-Net and Pulse Coupled Neural Network （PCNN） were combined to give play to their respective advantages and design a fundus vessel segmentation method. First， the iterative U-Net model was used to highlight the vessels， the fusion results of the features extracted by the U-Net model and the original image were input again into the improved U-Net model to enhance the vessel image. Then， the U-Net output result was viewed as a gray image， and the PCNN with adaptive threshold was utilized to perform accurate vessel segmentation. The experimental results show that the AUC （Area Under the Curve） of the proposed method was 0.979 6，0.980 9 and 0.982 7 on the DRVIE， STARE and CHASE_DB1 datasets， respectively. The method can extract more vessel details， and has strong generalization ability and good application prospects.

The shape of a tree is mostly determined by the reality to the nature layout of branches. In order to simulate a 3D tree branch to mimic the natural tree shape, using the theory of fractal algorithm and mechanics of material, a simulating method for the 3D's bending branch and fractal root based on the gravity field was proposed. The stress state of the branch was reflected by its bending degree. Bending degree could be controlled by changing the value of Young's modulus. Also, with X3D and Java, fractal algorithm combined with Extrusion node of X3D was used to simulate the geotropism of the bending root. A realistic 3D tree can be easily created with some input data using our simulation. By using the close relationship of the tree's underground part and upper part, a simulation method of gravity's effect on the tree shape was established. The experimental results show that the method can easily generate realistic three-dimensional form of fractal trees.

The scheme to realize mobile Agent variation in TinyOS was provided. The variation transfers the code space and data space respectively, and the energy consumption to send code space is decreased greatly making use of the broadcast characteristic of wireless channel. The simulation results show that, network performance in mobile Agent variation mode is better than that in traditional C/S mode when the nodes are numerous.