Digging the Underlying Layers of Intelligent Transportation System Networks by Mobile Crowdsourcing

Understanding the underlying topologies of networks is very important for improving their performance and security, especially in Intelligent Transportation Systems (ITS). Anonymous router identification recognizes and merges anonymous interfaces belonging to the same router in the traceroute measurement data, which is regarded as one of the critical issues for recovering the router-level topologies of networks. In this paper, we studied the problem of recovering the router-level topologies of networks with mobile crowdsourcing and proposed a method based on graph embedding (called <monospace>GE)</monospace> for accurate identification of anonymous network routers from traceroute measurement data. We first use the graph embedding method to capture the connection characteristics of different interfaces of anonymous routers from the traceroute data and then, evaluate the distances between interfaces based on the extracted connection characteristics. Finally, we identify the interfaces that belong to the same anonymous router by using a heuristic maximum likelihood estimation algorithm that we have developed. Compared to the existing methods, <monospace>GE</monospace> is more felxible in ITS because it identifies anonymous network routers without requiring manually predefined subgraphs (or patterns). In the evaluation, we simulated a variety of scenarios to generate the measurement data and compared <monospace>GE</monospace> to two state-of-the-art methods (the neighborhood matching method and the graph induction-based method). The results suggest that <monospace>GE</monospace> can significantly improve the accuracy of anonymous router identification (with an average improvement of over 20&#x0025;) at a slight identification rate loss (less than 4&#x0025;).