Federated Learning in Smart Healthcare, Homes, and Cities (FL-SHHC): A Systematic Literature Review

Federated learning (FL) has emerged as an acceptable approach for training machine learning (ML) models across distributed devices while preserving their private data. Recently, Internet of Things (IoTs) has been widely used across three application domains: smart healthcare, homes, and cities (SHHCs). In this study, we present a systematic literature review (SLR) using the PRISMA framework to comprehensively analyze existing research on FL-IoT smart healthcare, homes, and cities (FL-IoT SHHC). We identified and categorized 84 studies into three application domains (smart healthcare, homes, and cities) and critically analyzed them to identify three frequently used FL architectures: centralized, decentralized, and hierarchical FL. Furthermore, we discuss 17 optimization algorithms, seven hyperparameters, 76 datasets, and 13 evaluation metrics. Four explainable AI approaches, five privacy attacks, the limitations of this research, and future directions are also discussed. This SLR not only provides a comprehensive overview of the state of the art in FL-IoT smart healthcare, homes, and cities but also provides a roadmap for researchers and professionals seeking to advance the field and design more robust and resilient FL-IoT systems for user privacy domains.