@inproceedings{conf/wsdm/Kibanov15,
  added-at = {2018-11-06T00:00:00.000+0100},
  author = {Kibanov, Mark},
  biburl = {https://www.bibsonomy.org/bibtex/24216cc65a36dbb177282a0aa8c00dc6e/dblp},
  booktitle = {WSDM},
  crossref = {conf/wsdm/2015},
  editor = {Cheng, Xueqi and Li, Hang and Gabrilovich, Evgeniy and Tang, Jie},
  ee = {https://doi.org/10.1145/2684822.2697034},
  interhash = {b50245ebaf41ed949bb75f084f9febd0},
  intrahash = {4216cc65a36dbb177282a0aa8c00dc6e},
  isbn = {978-1-4503-3317-7},
  keywords = {dblp},
  pages = {441-446},
  publisher = {ACM},
  timestamp = {2019-05-22T11:54:34.000+0200},
  title = {Mining Groups Stability in Ubiquitous and Social Environments: Communities, Classes and Clusters.},
  url = {http://dblp.uni-trier.de/db/conf/wsdm/wsdm2015.html#Kibanov15},
  year = 2015
}

@inproceedings{kibanov2015mining,
  abstract = {Ubiquitous Computing is an emerging research area of computer science. Similarly, social network analysis and mining became very important in the last years. We aim to combine these two research areas to explore the nature of processes happening around users. The presented research focuses on exploring and analyzing different groups of persons or entities (communities, clusters and classes), their stability and semantics. An example of ubiquitous social data are social networks captured during scientific conferences using face-to-face RFID proximity tags. Another example of ubiquitous data is crowd-generated environmental sensor data. In this paper we generalize various problems connected to these and further datasets and consider them as a task for measuring group stability. Group stability can be used to improve state-of-the-art methods to analyze data. We also aim to improve the performance of different data mining algorithms, eg. by better handling of data with a skewed density distribution. We describe significant results some experiments that show how the presented approach can be applied and discuss the planned experiments.},
  acmid = {2697034},
  added-at = {2018-08-30T12:37:43.000+0200},
  address = {New York, NY, USA},
  author = {Kibanov, Mark},
  biburl = {https://www.bibsonomy.org/bibtex/217ed02a44f9050e7b9178c11bdfed3cd/kde-alumni},
  booktitle = {Proceedings of the Eighth ACM International Conference on Web Search and Data Mining},
  description = {Mining Groups Stability in Ubiquitous and Social Environments},
  doi = {10.1145/2684822.2697034},
  editor = {Cheng, Xueqi and Li, Hang and Gabrilovich, Evgeniy and Tang, Jie},
  interhash = {b50245ebaf41ed949bb75f084f9febd0},
  intrahash = {17ed02a44f9050e7b9178c11bdfed3cd},
  isbn = {978-1-4503-3317-7},
  keywords = {2015 itegpub myown},
  location = {Shanghai, China},
  numpages = {6},
  pages = {441--446},
  publisher = {ACM},
  series = {WSDM '15},
  timestamp = {2018-08-30T12:37:43.000+0200},
  title = {Mining Groups Stability in Ubiquitous and Social Environments: Communities, Classes and Clusters},
  url = {http://doi.acm.org/10.1145/2684822.2697034},
  year = 2015
}

@inproceedings{kibanov2015mining,
  abstract = {Ubiquitous Computing is an emerging research area of computer science. Similarly, social network analysis and mining became very important in the last years. We aim to combine these two research areas to explore the nature of processes happening around users. The presented research focuses on exploring and analyzing different groups of persons or entities (communities, clusters and classes), their stability and semantics. An example of ubiquitous social data are social networks captured during scientific conferences using face-to-face RFID proximity tags. Another example of ubiquitous data is crowd-generated environmental sensor data. In this paper we generalize various problems connected to these and further datasets and consider them as a task for measuring group stability. Group stability can be used to improve state-of-the-art methods to analyze data. We also aim to improve the performance of different data mining algorithms, eg. by better handling of data with a skewed density distribution. We describe significant results some experiments that show how the presented approach can be applied and discuss the planned experiments.},
  acmid = {2697034},
  added-at = {2015-12-16T16:57:48.000+0100},
  address = {New York, NY, USA},
  author = {Kibanov, Mark},
  biburl = {https://www.bibsonomy.org/bibtex/217ed02a44f9050e7b9178c11bdfed3cd/kibanov},
  booktitle = {Proceedings of the Eighth ACM International Conference on Web Search and Data Mining},
  description = {Mining Groups Stability in Ubiquitous and Social Environments},
  doi = {10.1145/2684822.2697034},
  editor = {Cheng, Xueqi and Li, Hang and Gabrilovich, Evgeniy and Tang, Jie},
  interhash = {b50245ebaf41ed949bb75f084f9febd0},
  intrahash = {17ed02a44f9050e7b9178c11bdfed3cd},
  isbn = {978-1-4503-3317-7},
  keywords = {2015 itegpub myown},
  location = {Shanghai, China},
  numpages = {6},
  pages = {441--446},
  publisher = {ACM},
  series = {WSDM '15},
  timestamp = {2016-03-17T16:29:52.000+0100},
  title = {Mining Groups Stability in Ubiquitous and Social Environments: Communities, Classes and Clusters},
  url = {http://doi.acm.org/10.1145/2684822.2697034},
  year = 2015
}