There are numerous formats which represent the micro-Doppler signature. Our goal is to determine which one is the most adapted to classify small UAV (Unmanned Aerial Vehicules) with Deep Learning. To achieve this goal, we compare drone classification results with the different micro-Doppler signatures for a given neural network. This comparison has been performed on data obtained during a radar measurement campaign. We evaluate the classification performance in function of different use conditions we identified with a given neural network. According to the experiments conducted, the recommended format is a spectrum issued from long observations as its classification results are better for most criteria.
Numerous studies based on complex measurement platforms have been carried out for over ten years now in order to discover the Internet topology on domain level. It turns out that this topology exhibits certain invariant properties such as a distribution of node degree. This distribution follows a power law. Moreover, the revealed topology is hierarchical. The hierarchy is caused by commercial contracts signed between domain operators. The routing realized by BGP is influenced by these relationships because operators do not want to make public the routes they know, as announcing certain routes would deprive them of a possible financial benefit. Consequently, routes available in BGP tables are valley-free. This fact has an impact on the performance of protocols which are proposed notably to assure the QoS.In order to evaluate the performance of new protocols in the inter-domain context their designers have to have at their disposal a random topology generator which is able to furnish a random graph whose nodes' degree follows a power law typical for the Internet, and to impose the commercial hierarchy on it. Our aSHIIP (autonomous Supélec Hierarchy Inter-domain Program) does both. It is a reliable flat Internet-like topology generator which also allows the modeler to introduce the realistic hierarchy.
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.