Predictive analytics on evolving data streams anticipating and adapting to changes in known and unknown contexts
DOI: 10.1109/HPCSIM.2015.7237112
关键词:
摘要: Ever increasing volumes of sensor readings, transactional records, web data and event logs call for next generation big mining technology providing effective efficient tools making use the streaming data. Predictive analytics on streams is actively studied in research communities used real-world applications that turn put spotlight several important challenges to be addressed. In this talk I will focus dealing with evolving streams. dynamically changing nonstationary environments, distribution can change over time. When such changes anticipated modeled explicitly, we design context-aware predictive models. underlying time are unexpected, deal so-called problem concept drift. highlight some recent developments proactive handling drift link them modeling. also share insights gained through performed case studies domains analytics, stress food sales analytics.
narcis.nl参考文章(16)
R. P. Jagadeesh Chandra Bose, Wil M. P. van der Aalst, Indre Zliobaite, Mykola Pechenizkiy, Dealing With Concept Drifts in Process Mining IEEE Transactions on Neural Networks. ,vol. 25, pp. 154- 171 ,(2014) , 10.1109/TNNLS.2013.2278313
Jorn Bakker, Leszek Holenderski, Rafal Kocielnik, Mykola Pechenizkiy, Natalia Sidorova, Stess@Work: from measuring stress to its understanding, prediction and handling with personalized coaching international health informatics symposium. pp. 673- 678 ,(2012) , 10.1145/2110363.2110439
Julia Kiseleva, Eric Crestan, Riccardo Brigo, Roland Dittel, Modelling and Detecting Changes in User Satisfaction conference on information and knowledge management. pp. 1449- 1458 ,(2014) , 10.1145/2661829.2661960
Indrė Žliobaitė, Jorn Bakker, Mykola Pechenizkiy, Beating the baseline prediction in food sales: How intelligent an intelligent predictor is? Expert Systems With Applications. ,vol. 39, pp. 806- 815 ,(2012) , 10.1016/J.ESWA.2011.07.078
Indre Zliobaite, Mykola Pechenizkiy, Learning with Actionable Attributes: Attention -- Boundary Cases! international conference on data mining. pp. 1021- 1028 ,(2010) , 10.1109/ICDMW.2010.140
João Gama, Indrė Žliobaitė, Albert Bifet, Mykola Pechenizkiy, Abdelhamid Bouchachia, A survey on concept drift adaptation ACM Computing Surveys. ,vol. 46, pp. 44- ,(2014) , 10.1145/2523813
I. Žliobaitė, J. Hollmén, H. Junninen, Regression models tolerant to massively missing data: a case study in solar-radiation nowcasting Atmospheric Measurement Techniques. ,vol. 7, pp. 4387- 4399 ,(2014) , 10.5194/AMT-7-4387-2014
Hock Hee Ang, Vivekanand Gopalkrishnan, Indre Zliobaite, Mykola Pechenizkiy, Steven C.H. Hoi, Predictive Handling of Asynchronous Concept Drifts in Distributed Environments IEEE Transactions on Knowledge and Data Engineering. ,vol. 25, pp. 2343- 2355 ,(2013) , 10.1109/TKDE.2012.172
Julia Kiseleva, Hoang Thanh Lam, Mykola Pechenizkiy, Toon Calders, Predicting Current User Intent with Contextual Markov Models international conference on data mining. pp. 391- 398 ,(2013) , 10.1109/ICDMW.2013.143
Hindra Kurniawan, Alexandr V. Maslov, Mykola Pechenizkiy, Stress detection from speech and Galvanic Skin Response signals Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems. pp. 209- 214 ,(2013) , 10.1109/CBMS.2013.6627790