{"112821":{"#nid":"112821","#data":{"type":"event","title":"Statistics Seminar - Spatiotemporal Event detection in Mobility Network","body":[{"value":"\u003Cp\u003ETITLE: Spatiotemporal Event detection in Mobility Network\n\u003C\/p\u003E\u003Cp\u003ESPEAKER: Rong Duan\u003C\/p\u003E\u003Cp\u003EABSTRACT:\u003C\/p\u003E\u003Cp\u003ELearning and identifying events in network traffic is crucial for service\nproviders to improve their mobility network performance. In fact, large\nspecial events attract cell phone users to relative small areas, which\ncauses sudden surge in network traffic. To handle such increased load,\nit is necessary to measure the increased network traffic and quantify\nthe impact of the events, so that relevant resources can be optimized\nto enhance the network capability. However, this problem\nis challenging due to several issues: (1) Multiple periodic temporal\ntraffic patterns (i.e., nonhomogeneous process) even for normal traffic;\n(2) Irregularly distributed spatial neighbor information;\n(3) Different temporal patterns driven by different events even for\nspatial neighborhoods; (4) Large scale data set.\n\n\u003C\/p\u003E\u003Cp\u003EThis paper proposes a systematic event detection method that deals\nwith the above problems. With the additivity property of Poisson process,\nwe propose an algorithm to integrate spatial information by aggregating\nthe behavior of temporal data under various areas. Markov Modulated\nNonhomogeneous Poisson Process (MMNHPP) is employed to estimate the\nprobability with which event happens, when and where the events take\nplace, and assess the spatial and temporal impacts of the events.\nLocalized events are then ranked globally for prioritizing more\nsignificant events. Synthetic data are generated to illustrate our\nprocedure and validate the performance. An industrial example from a\ntelecommunication company is also presented to\nshow the effectiveness of the proposed method.\n\u003C\/p\u003E\u003Cp\u003E\n\nContact: \u003Ca href=\u0022mailto:rongduan@research.att.com\u0022\u003Erongduan@research.att.com\u003C\/a\u003E\n\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Statistics Seminar - Rong Duan"}],"uid":"27187","created_gmt":"2012-02-28 08:24:45","changed_gmt":"2016-10-08 01:56:41","author":"Anita Race","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2012-03-01T15:00:00-05:00","event_time_end":"2012-03-01T16:00:00-05:00","event_time_end_last":"2012-03-01T16:00:00-05:00","gmt_time_start":"2012-03-01 20:00:00","gmt_time_end":"2012-03-01 21:00:00","gmt_time_end_last":"2012-03-01 21:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"1242","name":"School of Industrial and Systems Engineering (ISYE)"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EJan Shi \u003Ca href=\u0022mailto:jianjun.shi@isye.gatech.edu\u0022\u003E\u0026lt;jianjun.shi@isye.gatech.edu\u0026gt;\u003C\/a\u003E\n\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}