Pansharpening refers to the fusion between a multispectral (MS) image with abundant spectral information and a panchromatic (PAN) image with high spatial resolution to obtain a high spatial resolution multispectral (HRMS) image. The traditional pansharpening methods often ignore the effect of path-radiation caused by scattering from different atmospheric components, and the few methods that introduce haze correction only calibrate each band of the MS image individually, without exploring the intrinsic correlation among different bands. To address this problem, low rank tensor completion pansharpening based on haze correction (LRTCP) is proposed. The haze-line prior is first introduced into the joint haze correction of MS and PAN images, and obtain the pre-modulated images with the help of the improved high-pass modulation (HPM) injection scheme. We then use tensor completion to simulate the degradation problem by applying low-tubal-rank tensor complementation to the process of reconstructing HRMS images, thus constructing a low rank tensor completion pansharpening model based on haze correction. Finally, the alternating direction multiplier (ADMM) is employed to find the solution of the proposed approach, producing the final fusion result. Comprehensive qualitative and quantitative assessment of reduced- and full-resolution datasets from different satellites shows that the proposed method outperforms the state-of-the-art methods.

In intelligent transportation system (ITS), accurate and real-time prediction of short-term multi-lane traffic flow with existing traffic data is an important part of urban traffic planning, traffic management and control. The data generated in the process of vehicle driving has the cooperative characteristics of multi-source, space-time and dynamic. Combining the data with high-performance computing or cloud computing, a new space-time information framework is designed, which is of great significance for the analysis and prediction of traffic flow, as well as intelligent traffic management, service and decision-making. This paper analyzes the statistical characteristics of urban road traffic flow from the two dimensions of time and space through the spatial-temporal correlation between multi-lane short term traffic flow in single observation point and multi observation points. We constructed a data fusion powered bi-directional long short term memory (DFBD-LSTM) model for individual lane and aggregate traffic flow, then used this model to predict multi-lane short term traffic flow. By taking individual lane traffic flow and aggregate traffic flow as different variables, the model produces more accurate predictions, which can better guide people to travel, alleviate the congestion of urban road traffic network to a certain extent, and improve the utilization rate and transportation efficiency of traffic road.

The computer-aided system and chest X-ray images play an important role in the diagnosis of pneumonia, which are the main way of pneumonia diagnosis. The traditional deep learning models have achieved some success in medical images, which captures the potential features of the image by continuously sliding the fixed convolution kernel. The disadvantage of this method is that it cannot effectively capture the long-distance dependencies in the image, and it does not have the ability of dynamic adaptive modeling. Next, the high-quality labeled data of chest X-ray images are very scarce. In order to achieve high-quality artificial intelligence diagnosis, a large number of high-quality annotated chest X-ray images are required. In this work, based on technologies such as Internet of Medical Things (IoMT) and Digital Twins, we built an intelligent IoMT platform for automatic diagnosis of pneumonia. For the digital twin of the lung, we propose an enhanced vision transformer model (EVTM) for analyzing chest X-ray images to determine whether the patient is infected with pneumonia. The EVTM model utilizes the vision transformer for training and inference on chest X-ray images. Then the EVTM model uses the variational autoencoder model for data augmentation, so that the amount of chest X-ray images meets the training requirements of the model. Finally, we conducted extensive experiments on the standard chest X-ray image dataset to verify the effectiveness of the EVTM model.

This research explores the use of decentralized federated learning (DFL) in healthcare, focusing on overcoming the shortcomings of traditional centralized FL systems. DFL is proposed as a solution to enhance data privacy and improve system reliability by reducing dependence on central servers and increasing local data control. The research adopts a systematic literature review, following PRISMA guidelines, to provide a comprehensive understanding of DFL’s current applications and challenges within healthcare. The review synthesizes findings from various sources to identify the benefits and gaps in existing research, proposing research questions to further investigate the feasibility and optimization of DFL in medical environments. The study identifies four key challenges for DFL: security and privacy, communication efficiency, data and model heterogeneity, and incentive mechanisms. It discusses potential solutions, such as advanced cryptographic methods, optimized communication strategies, adaptive learning models, and robust incentive frameworks, to address these challenges. Furthermore, the research highlights the potential of DFL in enabling personalized healthcare through large, distributed data sets across multiple medical institutions. This study fills a critical gap in the literature by systematically reviewing DFL technologies in healthcare, offering valuable insights into applications, challenges, and future research directions that could improve the security, efficiency, and equity of healthcare data management.