Dual Stream Transmission and Downlink Power Control for Multiple LEO Satellites-Assisted IoT Networks.

The multi-satellites cooperative transmission can effectively increase the data rate that can be achieved by internet of things (IoT) terminals. However, the dynamic characteristics brought by low Earth orbit (LEO) satellites will seriously decrease the data rate and make the data rate fluctuate. In this paper, dual-stream transmission and downlink power control for multiple LEO satellites-assisted IoT networks are investigated. To mitigate the effects of the frequency offset caused by different LEO satellites, a multi-satellites synchronization scheme is proposed. Then, different power control schemes are given to resist the data rate fluctuation during the transmission. The simulation results show that the proposed schemes can effectively compensate for the varied frequency offset and keep the data rate stable.

Explainable Federated Medical Image Analysis Through Causal Learning and Blockchain.

Federated learning (FL) enables collaborative training of machine learning models across distributed medical data sources without compromising privacy. However, applying FL to medical image analysis presents challenges like high communication overhead and data heterogeneity. This paper proposes novel FL techniques using explainable artificial intelligence (XAI) for efficient, accurate, and trustworthy analysis. A heterogeneity-aware causal learning approach selectively sparsifies model weights based on their causal contributions, significantly reducing communication requirements while retaining performance and improving interpretability. Furthermore, blockchain provides decentralized quality assessment of client datasets. The assessment scores adjust aggregation weights so higher-quality data has more influence during training, improving model generalization. Comprehensive experiments show our XAI-integrated FL framework enhances efficiency, accuracy and interpretability. The causal learning method decreases communication overhead while maintaining segmentation accuracy. The blockchain-based data valuation mitigates issues from low-quality local datasets. Our framework provides essential model explanations and trust mechanisms, making FL viable for clinical adoption in medical image analysis.