Detecting Changes in Dynamic Events Over Networks. Li, S., Xie, Y., Farajtabar, M., Verma, A., & Song, L. IEEE Transactions on Signal and Information Processing over Networks, 3(2):346-359, June, 2017. doi abstract bibtex Large volumes of networked streaming event data are becoming increasingly available in a wide variety of applications such as social network analysis, Internet traffic monitoring, and health care analytics. Streaming event data are discrete observations occurring in continuous time, and the precise time interval between two events carries substantial information about the dynamics of the underlying systems. How does one promptly detect changes in these dynamic systems using these streaming event data? In this paper, we propose a novel change-point detection framework for multidimensional event data over networks. We cast the problem into a sequential hypothesis test, and we derive the likelihood ratios for point processes, which are computed efficiently via an expectation-maximization (EM) like algorithm that is parameter free and can be computed in a distributed manner. We derive a highly accurate theoretical characterization of the falsealarm rate, and we show that the method can provide weak signal detection by aggregating local statistics over time and networks. Finally, we demonstrate the good performance of our algorithm on numerical examples and real-world datasets from Twitter and Memetracker.
@ARTICLE{7907333,
author={Li, Shuang and Xie, Yao and Farajtabar, Mehrdad and Verma, Apurv and Song, Le},
journal={IEEE Transactions on Signal and Information Processing over Networks},
title={Detecting Changes in Dynamic Events Over Networks},
year={2017},
volume={3},
number={2},
pages={346-359},
abstract={Large volumes of networked streaming event data are becoming increasingly available in a wide variety of applications such as social network analysis, Internet traffic monitoring, and health care analytics. Streaming event data are discrete observations occurring in continuous time, and the precise time interval between two events carries substantial information about the dynamics of the underlying systems. How does one promptly detect changes in these dynamic systems using these streaming event data? In this paper, we propose a novel change-point detection framework for multidimensional event data over networks. We cast the problem into a sequential hypothesis test, and we derive the likelihood ratios for point processes, which are computed efficiently via an expectation-maximization (EM) like algorithm that is parameter free and can be computed in a distributed manner. We derive a highly accurate theoretical characterization of the falsealarm rate, and we show that the method can provide weak signal detection by aggregating local statistics over time and networks. Finally, we demonstrate the good performance of our algorithm on numerical examples and real-world datasets from Twitter and Memetracker.},
keywords={Approximation algorithms;Electronic mail;Distributed databases;Aggregates;Information processing;Monitoring;Heuristic algorithms;Change-point detection for event data;Hawkes process;online detection algorithm;false alarm control},
doi={10.1109/TSIPN.2017.2696264},
ISSN={2373-776X},
month={June},}
Downloads: 0
{"_id":"P2tkifhX29R9mZH2K","bibbaseid":"li-xie-farajtabar-verma-song-detectingchangesindynamiceventsovernetworks-2017","author_short":["Li, S.","Xie, Y.","Farajtabar, M.","Verma, A.","Song, L."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Li"],"firstnames":["Shuang"],"suffixes":[]},{"propositions":[],"lastnames":["Xie"],"firstnames":["Yao"],"suffixes":[]},{"propositions":[],"lastnames":["Farajtabar"],"firstnames":["Mehrdad"],"suffixes":[]},{"propositions":[],"lastnames":["Verma"],"firstnames":["Apurv"],"suffixes":[]},{"propositions":[],"lastnames":["Song"],"firstnames":["Le"],"suffixes":[]}],"journal":"IEEE Transactions on Signal and Information Processing over Networks","title":"Detecting Changes in Dynamic Events Over Networks","year":"2017","volume":"3","number":"2","pages":"346-359","abstract":"Large volumes of networked streaming event data are becoming increasingly available in a wide variety of applications such as social network analysis, Internet traffic monitoring, and health care analytics. Streaming event data are discrete observations occurring in continuous time, and the precise time interval between two events carries substantial information about the dynamics of the underlying systems. How does one promptly detect changes in these dynamic systems using these streaming event data? In this paper, we propose a novel change-point detection framework for multidimensional event data over networks. We cast the problem into a sequential hypothesis test, and we derive the likelihood ratios for point processes, which are computed efficiently via an expectation-maximization (EM) like algorithm that is parameter free and can be computed in a distributed manner. We derive a highly accurate theoretical characterization of the falsealarm rate, and we show that the method can provide weak signal detection by aggregating local statistics over time and networks. Finally, we demonstrate the good performance of our algorithm on numerical examples and real-world datasets from Twitter and Memetracker.","keywords":"Approximation algorithms;Electronic mail;Distributed databases;Aggregates;Information processing;Monitoring;Heuristic algorithms;Change-point detection for event data;Hawkes process;online detection algorithm;false alarm control","doi":"10.1109/TSIPN.2017.2696264","issn":"2373-776X","month":"June","bibtex":"@ARTICLE{7907333,\n author={Li, Shuang and Xie, Yao and Farajtabar, Mehrdad and Verma, Apurv and Song, Le},\n journal={IEEE Transactions on Signal and Information Processing over Networks}, \n title={Detecting Changes in Dynamic Events Over Networks}, \n year={2017},\n volume={3},\n number={2},\n pages={346-359},\n abstract={Large volumes of networked streaming event data are becoming increasingly available in a wide variety of applications such as social network analysis, Internet traffic monitoring, and health care analytics. Streaming event data are discrete observations occurring in continuous time, and the precise time interval between two events carries substantial information about the dynamics of the underlying systems. How does one promptly detect changes in these dynamic systems using these streaming event data? In this paper, we propose a novel change-point detection framework for multidimensional event data over networks. We cast the problem into a sequential hypothesis test, and we derive the likelihood ratios for point processes, which are computed efficiently via an expectation-maximization (EM) like algorithm that is parameter free and can be computed in a distributed manner. We derive a highly accurate theoretical characterization of the falsealarm rate, and we show that the method can provide weak signal detection by aggregating local statistics over time and networks. Finally, we demonstrate the good performance of our algorithm on numerical examples and real-world datasets from Twitter and Memetracker.},\n keywords={Approximation algorithms;Electronic mail;Distributed databases;Aggregates;Information processing;Monitoring;Heuristic algorithms;Change-point detection for event data;Hawkes process;online detection algorithm;false alarm control},\n doi={10.1109/TSIPN.2017.2696264},\n ISSN={2373-776X},\n month={June},}\n\n\n","author_short":["Li, S.","Xie, Y.","Farajtabar, M.","Verma, A.","Song, L."],"key":"7907333","id":"7907333","bibbaseid":"li-xie-farajtabar-verma-song-detectingchangesindynamiceventsovernetworks-2017","role":"author","urls":{},"keyword":["Approximation algorithms;Electronic mail;Distributed databases;Aggregates;Information processing;Monitoring;Heuristic algorithms;Change-point detection for event data;Hawkes process;online detection algorithm;false alarm control"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/network/files/c9YT3bPQbbKhRpNjQ","dataSources":["cHsbGgduWECnNiuXH","oeAiTHqrkizzWaYvm","zBsRPq756yvs86a9i"],"keywords":["approximation algorithms;electronic mail;distributed databases;aggregates;information processing;monitoring;heuristic algorithms;change-point detection for event data;hawkes process;online detection algorithm;false alarm control"],"search_terms":["detecting","changes","dynamic","events","over","networks","li","xie","farajtabar","verma","song"],"title":"Detecting Changes in Dynamic Events Over Networks","year":2017}