Federated Learning (FL) enables artificial intelligence frameworks to train on private information without compromising privacy, which is especially useful in the medical and healthcare industries where the knowledge or data at hand is never enough. It paved the way for a substantial amount of study because of the high degree of communication efficacy it possessed, which is connected to dispersed training issues. The major goal of this paper is to shed light on how FL approaches might be adapted and put to use in several aspects of healthcare, including medicine discovery, medical assessment, digital health management, and the forecasting and identification of disease. This article presents a comprehensive and in-depth study of the data about fused federated learning in healthcare version 5.0. The purpose of this research is to develop a Healthcare 5.0 monitoring system by utilizing a fused federated learning approach integrated with RTS-DELM. It gives medical practitioners the ability to monitor patients through the use of various medical sensors and to take remedial action at regular intervals. The approach is shown to be successfully improved by the use of the recommended system, which is intended for healthcare monitoring. This paper introduces a novel framework leveraging Fused Federated Learning (FFL) integrated with IoMT devices aimed at securely monitoring patient health data in a decentralized manner. This study introduces a novel integration of Real-Time Sequential Deep Extreme Learning Machine (RTS-DELM) and Fused Federated Learning (FFL) for secure and decentralized chronic kidney disease diagnosis within Healthcare 5.0. The proposed approach efficiently aggregates data from distributed Internet of Medical Things (IoMT) devices, enhancing predictive accuracy while maintaining patient privacy. Experimental validation demonstrates significant improvements, achieving an accuracy rate of 98.21%, thereby showcasing superior performance over existing federated learning methodologies.

(1) Background: Soccer action recognition (SAR) is essential in modern sports analytics, supporting automated performance evaluation, tactical strategy analysis, and detailed player behavior modeling. Although recent advances in deep learning and computer vision have enhanced SAR capabilities, many existing methods remain limited to coarse-grained classifications, grouping actions into broad categories such as attacking, defending, or goalkeeping. These models often fall short in capturing fine-grained distinctions, contextual nuances, and long-range temporal dependencies. Transformer-based approaches offer potential improvements but are typically constrained by the need for large-scale datasets and high computational demands, limiting their practical applicability. Moreover, current SAR systems frequently encounter difficulties in handling occlusions, background clutter, and variable camera angles, which contribute to misclassifications and reduced accuracy. (2) Methods: To overcome these challenges, we propose TAT-SARNet, a structured framework designed for accurate and fine-grained SAR. The model begins by applying Sparse Dilated Attention (SDA) to emphasize relevant spatial dependencies while mitigating background noise. Refined spatial features are then processed through the Split-Stream Feature Processing Module (SSFPM), which separately extracts appearance-based (RGB) and motion-based (optical flow) features using ResNet and 3D CNNs. These features are temporally refined by the Multi-Granular Temporal Processing (MGTP) module, which integrates ResIncept Patch Consolidation (RIPC) and Progressive Scale Construction Module (PSCM) to capture both short- and long-range temporal patterns. The output is then fused via the Context-Guided Dual Transformer (CGDT), which models spatiotemporal interactions through a Bi-Transformer Connector (BTC) and Channel–Spatial Attention Block (CSAB); (3) Results: Finally, the Cascaded Temporal Classification (CTC) module maps these features to fine-grained action categories, enabling robust recognition even under challenging conditions such as occlusions and rapid movements. (4) Conclusions: This end-to-end architecture ensures high precision in complex real-world soccer scenarios.