Privacy Preserving Federated Learning for Global Pilgrim Services

The rapid digitization of global pilgrimage services, such as those supporting Hajj and Umrah, has led to increased reliance on data-driven systems for optimizing crowd management, itinerary planning, and healthcare delivery. However, these services require continuous collection and processing of sensitive personal data, raising critical concerns about privacy and data security. Federated Learning (FL) has emerged as a promising paradigm to address these concerns by enabling collaborative model training across decentralized devices without sharing raw data. This study proposes a phase-adaptive, privacy-preserving FL framework tailored for large-scale pilgrim environments. By integrating mobile crowdsensing, edge-cloud computing, and differential privacy techniques, the proposed system supports personalized services such as smart itinerary generation, health monitoring, and assistive mobility without compromising user confidentiality. The framework also addresses technical challenges such as non-IID data, communication overhead, and model stability on heterogeneous devices. Drawing from existing implementations in healthcare, tourism, and IoT, this article outlines the design, benefits, and ethical implications of deploying FL for intelligent and secure pilgrim service ecosystems. The work contributes to both the theoretical development of federated architectures and practical applications in religious tourism, paving the way for scalable, secure, and inclusive digital pilgrimage management systems.