Kernel Based Online Change Point Detection. Bouchikhi, I., Ferrari, A., Richard, C., Bourrier, A., & Bernot, M. In 2019 27th European Signal Processing Conference (EUSIPCO), pages 1-5, Sep., 2019. Paper doi abstract bibtex 5 downloads Detecting change points in time series data is a challenging problem, in particular when no prior information on the data distribution and the nature of the change is available. In a former work, we introduced an online non-parametric change-point detection framework built upon direct density ratio estimation over two consecutive time segments, rather than modeling densities separately. This algorithm based on the theory of reproducing kernels showed positive and reliable detection results for a variety of problems. To further improve the detection performance of this approach, we propose in this paper to modify the original cost function in order to achieve unbiasedness of the density ratio estimation under the null hypothesis. Theoretical analysis and numerical simulations confirm the improved behavior of this method, as well as its efficiency compared to a state of the art one. Application to sentiment change detection in Twitter data streams is also presented.
@InProceedings{8902582,
author = {I. Bouchikhi and A. Ferrari and C. Richard and A. Bourrier and M. Bernot},
booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)},
title = {Kernel Based Online Change Point Detection},
year = {2019},
pages = {1-5},
abstract = {Detecting change points in time series data is a challenging problem, in particular when no prior information on the data distribution and the nature of the change is available. In a former work, we introduced an online non-parametric change-point detection framework built upon direct density ratio estimation over two consecutive time segments, rather than modeling densities separately. This algorithm based on the theory of reproducing kernels showed positive and reliable detection results for a variety of problems. To further improve the detection performance of this approach, we propose in this paper to modify the original cost function in order to achieve unbiasedness of the density ratio estimation under the null hypothesis. Theoretical analysis and numerical simulations confirm the improved behavior of this method, as well as its efficiency compared to a state of the art one. Application to sentiment change detection in Twitter data streams is also presented.},
keywords = {estimation theory;sentiment analysis;social networking (online);statistical analysis;time series;detection performance;sentiment change detection;Twitter data streams;time series data;data distribution;nonparametric change-point detection framework;direct density ratio estimation;consecutive time segments;kernel based online change point detection;null hypothesis;Kernel;Signal processing algorithms;Dictionaries;Estimation;Change detection algorithms;Europe;Signal processing;Non-parametric change-point detection;reproducing kernel Hilbert space;kernel least-mean-square algorithm;online learning;convergence analysis},
doi = {10.23919/EUSIPCO.2019.8902582},
issn = {2076-1465},
month = {Sep.},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570531342.pdf},
}
Downloads: 5
{"_id":"k5ytrMFBhGQckgZhy","bibbaseid":"bouchikhi-ferrari-richard-bourrier-bernot-kernelbasedonlinechangepointdetection-2019","authorIDs":["3dqow2dKnPDcuSiPG","44ExyWKBKa8DdymND","4W2BCWd6BtDZHyb7h","5BKZdbyxbnscaDyuE","5c3dc310fe79271000000141","5de832364e3c5af3010001fd","5de8c4a89e80cdde0100004d","5de8f502978afbdf010001ad","5def26b9e83f7dde0100005d","5def3d6066cfe0df01000019","5df0a592f651f5df0100015d","5df0f6ad45b054df01000183","5df0fe2e092ae5df01000004","5df1f36778da84de010000c1","5df246ba480e6fde01000137","5df30695bc9e6cde01000099","5df3257d3b310cde010000f8","5df49e1ba50a84df01000003","5df755e3182af9de0100015c","5df86c4fb99bcff3010000a8","5dfb647e012925de01000125","5dffbb761ce6f1df0100002e","5e00b15905b03cf3010000dc","5e0134732e225bde010000bb","5e04cbf3de66fbdf01000046","5e05a79b901debdf0100000b","5e070de83bc0fede010000ae","5e0da6e9675bf1de010000c7","5e123ef0c196d3de010000fc","5e13d015280ddede0100016a","5e1442b9b8b351de01000004","5e14abec830852de010001d9","5e15304e18da2edf010000cf","5e1573471e2528de010000de","5e17700e4df69dde01000210","5e179104d954d8df01000023","5e181a649a3d0bde01000140","5e185dba809b84f20100009c","5e18755f67b9ebde01000081","5e18d79ba382e2de0100009f","5e19410c86b4aade0100005f","5e1ab6de9da435de01000091","5e1b15c897579ade0100002b","5e1c08a5badffbde010000cd","5e1c271a7530ebe8010000f2","5e1d80e13a6d8cde01000047","5e1d81ca3a6d8cde01000058","5e1d83893a6d8cde0100008f","5e1db4abd9acfbde01000200","5e1ddd054986afdf01000143","5e1edc58875c69df010000b8","5e1f4fa29ddd0fde010001a0","5e2032e702c04cde0100012c","5e2064fcfd802cde010000cf","5e2198303ef35cdf01000074","5e246779079bb2df010000f1","5e256a0cf58a5cde01000039","5e2714b5f51e02de010000b3","5e27644158994fde0100006a","5e2831b4e6485dde010000b1","5e2870ab6ae365de0100017f","5e28910b67e11edf0100017b","5e2934f177c165de01000088","5e2adeb9638921df01000173","5e2c1ff4eb4d3ddf0100002f","5e2c5479c1aa2fde01000013","5e2c5987c1aa2fde0100004e","5e2cffbe6b217bdf01000020","5e2d4ae504d333de010000b8","5e2da477732e89de0100000b","5e2fe02b4e91a9df01000076","5e30301746a666df010000d4","5e303e0146a666df010001f2","5e3167fd04dccade0100007d","5e31ac4b6be690de010001ba","5e32c4e6466076df01000129","5e332695a5c1fdde01000068","5e34235f41f782de01000055","5e34a1e453b794de0100018d","5e3a886c0b62daf30100007d","5e3adb651b85fadf010000b0","5e3adf8b1b85fadf01000106","5e3ae5431b85fadf01000174","5e3cefb9ad8243de01000055","5e3d2432c405ecde01000023","5e3db77807ca74de01000084","5e3ebc63f657b4f201000062","5e3ebf49f657b4f201000099","5e3f4e1c77baf5df010000e7","5e412967b54187de01000183","5e424c2d82b0c2de0100000b","5e42cdade7fe39df0100014c","5e448887ec14b3de0100009c","5e4656086a7198de0100010f","5e590a199bb6d2df01000016","5e5923f79bb6d2df01000204","5e5b58f1502fdadf01000014","5e5b89f199fee0df01000520","5e5c61a2f4282ddf0100009b","5e5cd947aab7afde01000140","5e5cfba8d12a0ade01000111","5e5f6cd65766d9df0100003f","5e5fd1606b32b0f201000198","5e60e833839e59df010000ec","5e611d6f1cc34ede01000163","5e6136b497c182e9010000f4","5e66a67944d2c4de01000224","5e6a322de3f54ade010000ac","5e6b0e0c86bf9cde0100000c","5kmqJTkScJHuMHshP","6Mg2bKLZJsFKPRXAA","7DycH5RWYMjFZZYp6","7PJup3bJSmeBhPdHS","7ysdpboDdCn3z9NrQ","83b3m9TywarJ4dHwi","8BzeP7vjXajvaZgo2","8SDB6xT2jfZMAJhBw","8k2tNeFp36w5fivfp","8pcR6nTSJ75v65FWv","8q9fcEgNdwnAj9FZf","8whPukZxmTJSCBHd7","9HiZkGcPtntCZWtBd","9WH9QtEd8cDLnAAZb","9hMJ5vt7fKAJWZxqo","9jghRkxKnQQs4AMSC","AKFyR9KLDXusEJpvX","AgR6j8AGyg3LYgHJK","AhJr2A6XAt2EipM7m","BmJAhWKnhh7EbHwC7","C8Aprp7kzGxaDmoP4","CGmstd5bev9YKZBuJ","D9JxvLAYzMcJiRRDG","D9fnT8NL44edoFZYi","D9oGEcbekftGE9F8m","DBv4Q7nKxKXrytxo7","DKQ8Wn8Zaa7n3QDPF","DWpdb3EQviWNAZG8o","EPTZcCHNGtqghFZqd","FY8AGPXysvmbNzxmw","Fe9Mm33MwMnvbqzQZ","FyyZkwwRGXuFDE4Yg","GKNLHXXEr9f4FiTXp","Ge3r8kSCPDwQhQQLv","GrekZqZH5mnnZkQuR","HPkCvvCegZJ6obMuT","JXNto6uSXJNAP2Mq4","JjnBiaiyCrJet6D3G","K847C6Zc7Ag8rsChn","LNAYR8RZWfu2MnvnE","LPegkoCdYmSeMkpwq","LoJBNLS3LNivLDg42","LowL8786CCKzcknw2","MNLfwKeCsqCXJT2W3","NBK3DEt4bj7McXv7P","NN5y5KSLE78FLwYoZ","PK88kT7zBGXDhwwNa","PhSNoBEipQcivx3SB","PrAJgGCCf8ShZFvfM","QeHD8bEWzZxmE9L9a","RGLnAe2anALaBwtCa","RjuM7BxJRux5phxE2","SroHdHvdxcZY2Pjsi","TKmMmXLcb4B7nAhiz","TQCDu9nLRK6fAjs7r","TiAHmCTn2AWmFpAdL","TxwgzZ5A7dY7ZJ8nh","Wik3iNgPFyDerGiPR","Wsnk7FBE7Mes8FTe4","X7RtDD33qHYcGZozw","XdyoppbAdPbooKouS","YAqQNZcZXAa6ZD9wx","YRxPQHGDD4WksgANu","Ybj8Xqw5gS3XWTwB4","ZFEXhSkHXZSzdcuFx","aoQRBCYq7YWrhRbHB","b4q4ADXYn8EqnpasP","bbPQqj3y9Qd7vEM52","bmWLNWYYxudtxocR8","cJzgMdN7Jsbvttrts","cPSAWzDZcsMcdE6aw","d6SRGYQwnhRPhqRQd","e2PoGEKnXAbmWyyR5","f9nENxkfRvoejwEMX","fEpJmFyGqc5ZqQ7Yd","fb5TKYRo25t5xu7YC","gbZJDmK7RjycnwSv5","hZdWHG4QGrsLfHzRv","haFv4zGJHRZHfTLfj","i23ErgtoTCwLjtWiq","i96dCevc8KWN56kZF","jKqr47WTTatHjv8R3","jYkzkrdMe9YkPqcbC","jbPdbdLgrQwGoAwuG","jvfWFkFc6zD5GC4vK","m7sJiveByRfLiaYdt","mLezi2y3wtWvczHwJ","mveK5cSzciqksjBun","pAzqAagiwzyjCidcB","pwmXnrXBrxd9X8Rcb","px4h4tQgcBZrkZbd3","qwhJhTfA4itvFFc2j","sKYHhPjsZuWSggXuc","sXNi6AnTHMPrY2iNR","snLo3sMiLmiaSh4Ds","tNxZCpYN8KozeeYAQ","tR3M9q8ttABE5aoXZ","tfDWbdnBWeYCXsoDg","ufetFEAdBh39un3M6","ufksvhbveKqdMZnR2","unnfd7taTpNfNWYqq","vEZPZTCPbpisS8NmP","vhBmnxFHyH3YTRacq","x4NfYFoGFjKJJyBeK","xgTeEg9eRon4sgPHn","xhoyYggQ9ecAwfMuQ","zE4M49SNvJY3LbT39","zLPre87NdHKpMQCFW","zeztsTw9vrSvTBtX7"],"author_short":["Bouchikhi, I.","Ferrari, A.","Richard, C.","Bourrier, A.","Bernot, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["I."],"propositions":[],"lastnames":["Bouchikhi"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Ferrari"],"suffixes":[]},{"firstnames":["C."],"propositions":[],"lastnames":["Richard"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Bourrier"],"suffixes":[]},{"firstnames":["M."],"propositions":[],"lastnames":["Bernot"],"suffixes":[]}],"booktitle":"2019 27th European Signal Processing Conference (EUSIPCO)","title":"Kernel Based Online Change Point Detection","year":"2019","pages":"1-5","abstract":"Detecting change points in time series data is a challenging problem, in particular when no prior information on the data distribution and the nature of the change is available. In a former work, we introduced an online non-parametric change-point detection framework built upon direct density ratio estimation over two consecutive time segments, rather than modeling densities separately. This algorithm based on the theory of reproducing kernels showed positive and reliable detection results for a variety of problems. To further improve the detection performance of this approach, we propose in this paper to modify the original cost function in order to achieve unbiasedness of the density ratio estimation under the null hypothesis. Theoretical analysis and numerical simulations confirm the improved behavior of this method, as well as its efficiency compared to a state of the art one. Application to sentiment change detection in Twitter data streams is also presented.","keywords":"estimation theory;sentiment analysis;social networking (online);statistical analysis;time series;detection performance;sentiment change detection;Twitter data streams;time series data;data distribution;nonparametric change-point detection framework;direct density ratio estimation;consecutive time segments;kernel based online change point detection;null hypothesis;Kernel;Signal processing algorithms;Dictionaries;Estimation;Change detection algorithms;Europe;Signal processing;Non-parametric change-point detection;reproducing kernel Hilbert space;kernel least-mean-square algorithm;online learning;convergence analysis","doi":"10.23919/EUSIPCO.2019.8902582","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570531342.pdf","bibtex":"@InProceedings{8902582,\n author = {I. Bouchikhi and A. Ferrari and C. Richard and A. Bourrier and M. Bernot},\n booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)},\n title = {Kernel Based Online Change Point Detection},\n year = {2019},\n pages = {1-5},\n abstract = {Detecting change points in time series data is a challenging problem, in particular when no prior information on the data distribution and the nature of the change is available. In a former work, we introduced an online non-parametric change-point detection framework built upon direct density ratio estimation over two consecutive time segments, rather than modeling densities separately. This algorithm based on the theory of reproducing kernels showed positive and reliable detection results for a variety of problems. To further improve the detection performance of this approach, we propose in this paper to modify the original cost function in order to achieve unbiasedness of the density ratio estimation under the null hypothesis. Theoretical analysis and numerical simulations confirm the improved behavior of this method, as well as its efficiency compared to a state of the art one. Application to sentiment change detection in Twitter data streams is also presented.},\n keywords = {estimation theory;sentiment analysis;social networking (online);statistical analysis;time series;detection performance;sentiment change detection;Twitter data streams;time series data;data distribution;nonparametric change-point detection framework;direct density ratio estimation;consecutive time segments;kernel based online change point detection;null hypothesis;Kernel;Signal processing algorithms;Dictionaries;Estimation;Change detection algorithms;Europe;Signal processing;Non-parametric change-point detection;reproducing kernel Hilbert space;kernel least-mean-square algorithm;online learning;convergence analysis},\n doi = {10.23919/EUSIPCO.2019.8902582},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570531342.pdf},\n}\n\n","author_short":["Bouchikhi, I.","Ferrari, A.","Richard, C.","Bourrier, A.","Bernot, M."],"key":"8902582","id":"8902582","bibbaseid":"bouchikhi-ferrari-richard-bourrier-bernot-kernelbasedonlinechangepointdetection-2019","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2019/proceedings/papers/1570531342.pdf"},"keyword":["estimation theory;sentiment analysis;social networking (online);statistical analysis;time series;detection performance;sentiment change detection;Twitter data streams;time series data;data distribution;nonparametric change-point detection framework;direct density ratio estimation;consecutive time segments;kernel based online change point detection;null hypothesis;Kernel;Signal processing algorithms;Dictionaries;Estimation;Change detection algorithms;Europe;Signal processing;Non-parametric change-point detection;reproducing kernel Hilbert space;kernel least-mean-square algorithm;online learning;convergence analysis"],"metadata":{"authorlinks":{"richard, c":"http://www.cedric-richard.fr/pub.html","ferrari, a":"https://bibbase.org/show?bib=https://dl.dropboxusercontent.com/s/is80a9wjw4k1qps/monbibarticles.bib"}},"downloads":5},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2019url.bib","creationDate":"2019-11-06T10:16:08.782Z","downloads":5,"keywords":["estimation theory;sentiment analysis;social networking (online);statistical analysis;time series;detection performance;sentiment change detection;twitter data streams;time series data;data distribution;nonparametric change-point detection framework;direct density ratio estimation;consecutive time segments;kernel based online change point detection;null hypothesis;kernel;signal processing algorithms;dictionaries;estimation;change detection algorithms;europe;signal processing;non-parametric change-point detection;reproducing kernel hilbert space;kernel least-mean-square algorithm;online learning;convergence analysis"],"search_terms":["kernel","based","online","change","point","detection","bouchikhi","ferrari","richard","bourrier","bernot"],"title":"Kernel Based Online Change Point Detection","year":2019,"dataSources":["HJFfA26WGrY3pcuPR","QkBTkcvkaK7xmMZNe","5ngH9z7sNEXFuGxfN","NqWTiMfRR56v86wRs","jqibchEkHvJ4Ntog9","r6oz3cMyC99QfiuHW","iwKepCrWBps7ojhDx"]}