Interpretable machine learning approach in estimating traffic volume on low-volume roadways

Estimating Missing Traffic Volume Using Low Multilinear Rank Tensor Completion

Estimating P2P Traffic Volume at USC

With the rise of peer-to-peer (P2P) file sharing applications there has been an increasing interest in understanding the popularity and use of P2P. In this study, we look at P2P use on the University of Southern California’s campus network throughout a 14-hour period. We quantify the volume of traffic from P2P activity as well as the number of campus hosts involved in P2P at USC. Since port-mat...

Evaluation of Pavement Markings on Low-Volume Rural Roadways in Iowa

Many rural roadways in Iowa have centerline and/or edgeline pavement markings. The current Manual on Uniform Traffic Control Devices (MUTCD), however, requires centerline and/or edgeline pavement markings only along streets and roadways with traffic volumes much greater than 400 vehicles per day (the volume-based definition of a low-volume roadway in the MUTCD). This project was initiated to ga...

Evaluation of Pavement Markings on Low-Volume Rural Roadways in Iowa Final Report

Poster: A DDoS Peak Traffic Volume Prediction Method Based on Machine Learning

DDoS defense nowadays relies on expensive and proprietary hardware appliances. When a massive attack begins, improper choices such as choosing fewer appliances or those without enough capacity may lead to more severe damage. As the previous work proposed[1], the choice heavily depends on the peak volume of the attack traffic(measured by packets per second). However, no prediction methods have b...