Federated deep learning frameworks can be used strategically to monitor land use locally and infer environmental impacts globally. Distributed data from across the world would be needed to build a global model for land use classification. The need for a federated approach in this application domain would be to avoid the transfer of data from distributed locations and save network bandwidth to reduce communication costs. We used a federated UNet model for the semantic segmentation of satellite and street view images. The novelty of the proposed architecture involves the integration of knowledge distillation to reduce communication costs and response times. The accuracy obtained was above 95% and we also brought in a significant model compression to over 17 times and 62 times for street-view and satellite images, respectively. Our proposed framework has the potential to significantly improve the efficiency and privacy of real-time tracking of climate change across the planet.
Recently, there has been a remarkable amount of research being done in both, the fields of Blockchain and Internet of Things (IoT). Blockchain technology synergises well with IoT, solving key problems such as privacy, concerns with interoperability and security. However, the consensus mechanisms that allows trustless parties to maintain an agreement, the same algorithms that underpins cryptocurrency mining, are usually extremely computationally expensive, making implementation on low-power IoT devices difficult. More importantly, mining requires downloading and synchronizing hundred of gigabytes worth of blocks which is far beyond the capabilities of most IoT devices. In this paper, we present an efficient, portable and platform-agnostic cryptocurrency mining algorithm using the Stratum protocol to avoid downloading the entire blockchain. We implement the algorithm in four different platforms-PC, ESP32, an emulator and an old PlayStation Portable (PSP) to demonstrate that it is indeed possible for any device to mine cryptocurrencies with no assumptions except the ability to connect to the internet. To make sure of ease of portability on any platform and for reproducibility of the reported results we make the implementation publicly available with detailed instructions at: https://anonymous.4open.science/r/cryptominer.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.