San Francisco / Stockholm / Sacramento / Cascais / /
Company
Network Appliance / BitTorrent / Ericsson / NIPS Analyzing Networks / IBM / Amazon / Oracle / Nokia / Intelligent Transport Systems / Google / NEC Labs / VMWare / Intel / Microsoft / /
Country
Canada / Portugal / Jordan / United States / /
Currency
USD / /
Event
Business Partnership / /
Facility
Mobile Millennium pipeline / Texas Transportation Institute / University of California / K. Hall / Alexandre M. Bayen University of California / /
IndustryTerm
transportation / road network / recent cluster computing frameworks / transportation community / in-memory cluster computing / storage infrastructure / per-link travel distribution parameters / iterative machine learning algorithms / learning-based applications / cloud applications / large-scale graph processing / iterative algorithms / weighted travel time samples / travel time distribution parameters / software stack / parallel applications / real-time conditions / data processing / in-memory computing frameworks / traffic estimation algorithm / cloud computing frameworks / storage solution / travel time inference / travel time distributions / travel time / non-cloud infrastructure / freeway travel time estimation / transportation network / distributed data-parallel computing / machine learning applications / computing / closed-form solution / em algorithm / iterative applications / random travel time samples / parallel machine learning algorithms / machine learning algorithms / per-link travel time samples / arterial network / road networks / traffic information algorithm / final solution / traffic algorithms / low-latency networks / large server / arterial road network / observed travel time / Cloud storage solutions / simpler machine learning applications / web interface / off-cloud storage systems / real-world machine learning applications / real road network / cell phone applications / real-time traffic inference / parallel data processing / iterative data processing / datacenter networks / optimization algorithms / travel time sei / computational infrastructure / cluster computing framework / storage systems / travel time distribution / traffic information system using cloud computing / typical traffic engineering systems / travel times / estimation algorithm / parallel algorithm / cluster computing frameworks / learning algorithm / Web Services / /
NaturalFeature
San Francisco Bay / /
Organization
UC Berkeley / Royal Statistical Society / National Energy Research Scientific Computing Center / Texas Transportation Institute / Royal Society of London / University of California / Berkeley / Association of Computation Linguistics / Alexandre M. Bayen University / California Department of Transportation / US Department of Transportation / North American Chapter / National Sciences and Engineering Research Council of Canada / EECS Department / /
Person
Pieter Abbeel / Michael J. Franklin / Justin Ma / Teodor Moldovan / J. Ma / V / /
Position
representative / programmer / traffic model for velocity data assimilation / Cloud Timothy Hunter / /
Product
PostgreSQL / Gamma / /
ProgrammingLanguage
Java / Scala / Python / /
ProvinceOrState
California / Manitoba / /
PublishedMedium
Proceedings of the Royal Society / Journal of the Royal Statistical Society / /
Technology
Mobile Millennium EM traffic estimation algorithm / iterative machine learning algorithms / parallel algorithm / mobile phones / EM algorithm / traffic estimation algorithm / traffic algorithms / importance sampling EM algorithm / main algorithms / Java / optimization algorithms / Large Parameter Vectors Parallel machine learning algorithms / machine learning algorithms / GPS / Mobile Millennium traffic information algorithm / parallel machine learning algorithms / machine learning / Terms Algorithms / learning algorithm / cellular telephone / http / caching / /