This study proposes a short-term traffic flow prediction model that combines community detection-based federated learning with a graph convolutional network (GCN) to alleviate the time-consuming training, higher communication costs, and data privacy risks of global GCNs as the amount of data increases. The federated community GCN (FCGCN) can achieve timely, accurate, and safe traffic state predictions in the era of big traffic data, which is critical for the efficient operation of intelligent transportation systems. The FCGCN prediction process has four steps: dividing the local subnetwork with community detection, local training based on the global parameters, uploading the local model parameters, and constructing a global model prediction based on the aggregated parameters. Numerical results on the PeMS04 and PeMS08 datasets show that the FCGCN outperforms four benchmark models, namely, the long short-term memory (LSTM), convolutional neural network (CNN), ChebNet, and graph attention network (GAT) models. The FCGCN prediction is closer to the real value, with nearly the same performance as the global model at a lower time cost, thus achieving accurate and secure short-term traffic flow predictions with three parameters: flow, speed, and occupancy.

Facial expression recognition (FER) technology has progressively matured over time. However, existing FER methods are primarily optimized for frontal face images, and their recognition accuracy significantly degrades when processing profile or large-angle rotated facial images. Consequently, this limitation hinders the practical deployment of FER systems. To mitigate the interference caused by large pose variations and improve recognition accuracy, we propose a FER method based on profile-to-frontal transformation and multimodal learning. Specifically, we first leverage the visual understanding and generation capabilities of Qwen-Image-Edit that transform profile images to frontal viewpoints, preserving key expression features while standardizing facial poses. Second, we introduce the CLIP model to enhance the semantic representation capability of expression features through vision–language joint learning. The qualitative and quantitative experiments on the RAF (89.39%), EXPW (67.17%), and AffectNet-7 (62.66%) datasets demonstrate that our method outperforms the existing approaches.

An ontology of the financial field can support effective association and integration of financial knowledge. Based on behavioral finance, social media is increasingly applied as one of the data sources for information fusion in stock forecasting to approximate the patterns of market changes. By predicting Tesla (TSLA) stock price trends, this study finds that satisfactory forecasting results can be achieved using classical models and incorporating key information features from the technical indicator ontology class and the investor behavior ontology class, even in the face of the impact of the COVID-19 epidemic. In the post-epidemic period, the back propagation neural network (BPNN) model is used to predict the price trend of TSLA for the next five trading days with an accuracy of up to 91.34%, an F1 score of 0.91, and a return of up to 268.42% obtained from simulated trading. This study extends the research on stock forecasting using fused information in the ontology of the financial field, providing a new basis for general investors in the selection of fusion information and the application of trading strategies and providing effective support for organizations to make intelligent financial decisions under uncertainty.