1. FedLens: federated learning-based privacy-preserving mobile crowdsensing for virtual tourism.
- Author
-
De, Debashis
- Abstract
FedLens is the federated learning model based on viewing world tourist spots virtually in a privacy-preserving manner. We define Virtual Tourism as enjoying the natural beauty, other related activities online, using AR/VR/MR technology-based 'virtual eye', to interact actively with nature and people at tourist spots. Federated learning-based mobile crowdsensing is an emerging collaborative distributed learning paradigm for privacy-preserving, energy-efficient, and scalable networks. Edge intelligent mobile crowdsensing uses geotagged tourist attractions. The purpose of this study is to explore the geo-statistics of tourist areas. The proposed 'FedLens' brings tourists closer to the interests using augmented reality through the virtual guide. ArcGIS software maps a tourist area. 5G mobile crowdsensing helps to explore unknown tourist spots in real time. 'FedLens' provides a privacy-preserving incentive mechanism to encourage reliable contributors to get better Quality of Information. The average global data aggregation time is approximately 12%. The contributor's collection time is 88% of the total processing time. The contributors use multifaceted intelligent federated computing to provide detailed geospatial information and promote sustainable ecotourism. Augmented reality-based virtual tourism ecosystem development is the ultimate goal of this work to attract more virtual tourists for a sustainable environment. Future physical tour-planning recommendation systems are incorporated in the proposed model. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF