Leveraging IoT Mesh Networks for Machine Learning Knowledge Transfer

In an era of Internet of Things, the exchange of knowledge between devices is critical for intelligent and autonomous decision-making. Leveraging IoT mesh networks, this proposal aims to facilitate seamless knowledge transfer of machine learning models. Specifically, it explores the integration of federated learning and transfer learning into IoT mesh networks, enhancing device capabilities without having to rely on time expensive traditional data exchanges via gateways and network servers. This research can have a profound impact on various applications, including smart cities, environmental monitoring, and industrial automation, where knowledge sharing is pivotal. The goal of this project is to develop an innovative framework that facilitates transfer of knowledge between devices within IoT mesh networks (e.g., LoRa, M2M). By combining federated learning and transfer learning, our goal is to enhance energy efficiency, scalability, and privacy in IoT networks for various applications.