@techreport{TD:101723,
	att_abstract={{The need for improved traffic planning and control is growing.  The Transportation Institute at Texas A&M reports the congestion problem is large and that from 2013 to 2014, 95 of the largest U.S. metro areas saw increased traffic congestion.  For the average commuter this means an additional 42 hours in traffic, and it is even worse for drivers in the San Francisco Bay Area in California, who spend an additional 78 hours a year sitting in traffic. That is why we are conducting research to determine how anonymous cellphone data can improve traffic planning and operations. The focus of the SmartBay project is on the San Francisco Bay Area.  We show that anonymized cell phone data can be used to reduce latency and increase sample sizes in datasets for transportation planning.  We present solutions for modeling, inference and microsimulation.}},
	att_authors={as9325, jp9618, cg2198},
	att_categories={},
	att_copyright={{}},
	att_copyright_notice={{}},
	att_donotupload={},
	att_private={false},
	att_projects={},
	att_tags={Cellular data,  urban mobility},
	att_techdoc={true},
	att_techdoc_key={TD:101723},
	att_url={http://web1-clone.research.att.com:81/techdocs_downloads/TD:101723_DS1_2016-06-20T22:01:23.288Z.pdf},
	author={Ann Skudlark and Jean-francois Paiement and Colin Goodall and Alexei Pozdnoukhov and Mogeng Yin and Sid Feygin},
	institution={{21st Biennial Conference of the International Telecommunications Society }},
	month={June},
	title={{Data analytics for traffic planning and control}},
	year=2016,
}