The U-shaped and Transformer architectures have achieved exceptional performance in medical image segmentation and natural language processing, respectively. Their combination has also led to remarkable results but still suffers from enormous loss of image features during downsampling and the difficulty of recovering spatial information during upsampling. In this paper, we propose a novel encoder-decoder architecture for medical image segmentation, which has a flexibly adjustable hybrid encoder and two expanding paths decoder. The hybrid encoder incorporates the feature double reuse (FDR) block and the encoder of Vision Transformer (ViT), which can extract local and global pixel localization information, and alleviate image feature loss effectively. Meanwhile, we retain the original class-token sequence in the Vision Transformer and develop an additional corresponding expanding path. The class-token sequence and abstract image features are leveraged by two independent expanding paths with the deep-supervision strategy, which can better recover the image spatial information and accelerate model convergence. To further mitigate the feature loss and improve spatial information recovery, we introduce successive residual connections throughout the entire network. We evaluated our model on the COVID-19 lung segmentation and the infection area segmentation tasks. The mIoU index increased by 1.5 points and 3.9 points compared to other models which demonstrates a performance improvement.

The capacity to diagnose faults in rolling bearings is of significant practical importance to ensure the normal operation of the equipment. Frequency-domain features can effectively enhance the identification of fault modes. ... | Find, read and cite all the research you need on Tech Science Press

Meteorological science is becoming more and more familiar. The internal driving relationship of weather, timing sequence and its accurate prediction are hot topics in the field of meteorology. This paper proposes a granger weather, timing sequence causal prediction method combining mutual information. In this paper, the information entropy characteristic matrix of the Granger feature set is calculated through mutual information. It while verifying the causal relationship of the weather, timing variables such as temperature, humidity and wind speed, it mines the effective input variables to achieve the purpose of reducing the dimension of time-series data features and improves the prediction accuracy of the target model. Finally, the open source weather data set is used to make a comparative experiment between qualitative and quantitative analysis of the proposed algorithm. The simulation results show that the method is feasible and effective.

Arbitrary style transfer is attracting increasing attention due to its wide application potential. Existing approaches either directly fuse deep style features with deep content features or adaptively normalize content features to achieve global statistical matching. Although these approaches show some success, they frequently produce artifacts and messy textures. This primarily stems from a lack of exploration of the semantic distribution of style image features and an ineffective capture of long-range dependencies. This paper presents a Dual-Domain Style Transfer Network that incorporates Adaptive Normalization with Style Semantics Awareness and Global Style Texture Enhancement. The former aims to extract more style semantic information to reduce artifacts through self-attention mechanism and adaptive normalization, while the latter enhances global stylistic information in the frequency domain to suppress cluttered textures. On the MSCOCO and Wikiart datasets, compared to other state-of-the-art methods, our Learned Perceptual Image Patch Similarity, Structural Similarity Index, and content loss metrics achieved the best scores of 0.616, 0.467, and 2.31, respectively, while the style loss metric achieved the second-best score of 3.08.

Considering netizen opinion is influenced by many factors in the spread of public opinion, combine the Bass theory and traditional cellular automata model, add external influence, degree of neighbor and external influence, a hybrid model for the evolution of online public sentiment considering the external influence is set up. Propose a modified conversion formula of tendency, analyze simulation results by coarse and fine grained statistical method. The simulation results show that the model can better reflect the trend of network public opinion dissemination.

In view of the complexity of Internet and the heterogeneity of individual in public opinion spreading, established the Internet public opinion evolution model based on complex network. Through experiment simulation, observed influences of order parameter and network topology on the evolution of opinion. Simulation results show that: 1) this model can greatly reflect the synergy effect of order parameters on opinion system, and it is more consistent with the actual situation. 2) the evolution of opinion is related to average degree and clustering coefficient: when average degree is small, the bigger clustering coefficient is, the more it can restrain the propagation of opinion; but when aveage degree exceeds a critical value, clustering coefficient no longer plays a key role, and at this point system will converge rapidly to extreme attitude.