Data stream mining seeks to extract useful information from quickly-arriving, infinitely-sized and evolving data streams. Although these challenges have been addressed throughout the literature, none of them can be considered “solved.” We contribute to closing this gap for the task of data stream clustering by proposing two modifications to the well-known ClusTree data stream clustering algorithm: pruning unused branches and detecting concept drift. Our experimental results show the difficulty in tackling these aspects of data stream mining and the sensitivity of stream mining algorithms to parameter values. We conclude that further research is required to better equip stream learners for the data stream clustering task.
GamaJ.Knowledge Discovery from Data Streams, CRC Press, 2010.
2.
ZhangP., ZhuX., TanJ. and GuoL.Classifier and cluster ensembles for mining concept drifting data streams, in: Proc of IEEE International Conference on Data Mining, pp. 1175–1180.
3.
KrawczykB., MinkuL.L., ao GamaJ., StefanowskiJ. and WoźniakM., Ensemble learning for data stream analysis: A survey, Information Fusion37 (2017), 132–156.
4.
EverittB.S., LandauS. and LeeseM.Cluster Analysis, Wiley Publishing, 4th edition, 2009.
5.
SilvaJ.A., FariaE.R., BarrosR.C., HruschkaE.R., d. CarvalhoA.C.P.L.F. and GamaJ.a., Data stream clustering: A survey, ACM Comput Surv46 (2013), 13:1–13:31.
6.
RodriguesP.P., GamaJ.a. and PedrosoJ., Hierarchical clustering of time-series data streams, IEEE Trans on Knowl and Data Eng20 (2008), 615–627.
7.
KremplG., SpiliopoulouM., StefanowskiJ., ŽliobaitėI., BrzezińskiD., HüllermeierE., LastM., LemaireV., NoackT., ShakerA. and SieviS., Open challenges for data stream mining research, ACM SIGKDD Explorations Newsletter16 (2014), 1–10.
8.
GamaJ., ŽliobaitėI., BifetA., PechenizkiyM. and BouchachiaA., A survey on concept drift adaptation, ACM Computing Surveys46 (2014), 1–37.
9.
ŽliobaitėI.Learning under Concept Drift: An Overview, Technical Report, Vilnius University, 2010.
10.
WebbG.I., HydeR., CaoH., NguyenH.L. and PetitjeanF., Characterizing concept drift, Data Mining and Knowledge Discovery30 (2016), 964–994.
11.
MoultonR.H., ViktorH.L., JapkowiczN. and GamaJ.Clustering in the presence of concept drift, in: Machine Learning and Knowledge Discovery in Databases – European Conference, ECML PKDD 2018, Dublin, Ireland, Setember 10–14, 2018, Proceedings, Part I, pp. 339–355.
12.
KranenP., AssentI., BaldaufC. and SeidlT., The ClusTree: Indexing micro-clusters for anytime stream mining, Knowledge and Information Systems29 (2011), 249–272.
13.
ZgrajaJ. and WoźniakM.Drifted data stream clustering based on clustree algorithm, in:
de Cos JuezF.J., VillarJ.R., de la Cal, ÁE. A., HerreroÁ., QuintiańH., SáezJ. A., CorchadoE., (Eds.), Hybrid Artificial Intelligent Systems, Springer International Publishing, Cham2018, pp. 338–349.
14.
AggarwalC., HanJ., WangJ. and YuP.A framework for clustering evolving data streams, in: Proc of the 29th Int Conf. on Very Large Data Bases ȓ Volume 29, VLDB ’03, VLDB Endowment, 2003, pp. 81–92.
KremerH., KranenP., JansenT., SeidlT., BifetA., HolmesG. and PfahringerB.An effective evaluation measure for clustering on evolving data streams, in: Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’11, ACM, New York, NY, USA, 2011, pp. 868–876.
17.
EsterM., SanderJ. and MoiseG., P3C: A robust projected clustering algorithm, 2013 IEEE 13th International Conference on Data Mining00 (2006), 414–425.
18.
WilcoxonF., Individual comparisons by ranking methods, Biometrics bulletin1 (1945), 80–83.
19.
FriedmanM., The use of ranks to avoid the assumption of normality implicit in the analysis of variance, Journal of the American Statistical Association32 (1937), 675–701.
20.
Alcalá-FdezJ., SánchezL., GarcíaS., del JesusM.J., VenturaS., GarrellJ.M., OteroJ., RomeroC., BacarditJ., RivasV.M., FernándezJ.C. and HerreraF., KEEL: A software tool to assess evolutionary algorithms to data mining problems, Soft Computing13 (2009), 307–318.
21.
Alcalá-FdezJ., FernandezA., LuengoJ., DerracJ., GarcíaS., SánchezL. and HerreraF., KEEL data-mining software tool: Data set repository, integration of algorithms and experimental analysis framework, Journal of Multiple-Valued Logic and Soft Computing17 (2011), 255–287.
22.
HultenG., SpencerL. and DomingosP.Mining time-changing data streams, in: Proceedings of the seventh ACM SIGKDD in ternational conference on Knowledge discovery and data mining, ACM, pp. 97–106.
23.
StreetW.N. and KimY.A streaming ensemble algorithm (sea) for large-scale classification, in: Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’01, ACM, New York, NY, USA, 2001, pp. 377–382.
24.
DomingosP. and HultenG., Mining high-speed data streams, in: Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’00, ACM, New York, NY, USA, 2000, pp. 71–80.
25.
LyonR.J., StappersB.W., CooperS., BrookeJ.D. and KnowlesJ.M., Fifty Years of Pulsar Candidate Selection: From simple filters to a new principled real-time classification approach, MNRAS000 (2015), 000–000.
26.
BifetA., GavaldáR. Adaptive learning from evolving data streams, in: N.M. Adams, C. Robardet, A. Siebes, J.-F. Boulicaut (Eds.), Advances in Intelligent Data Analysis VIII, Springer Berlin Heidelberg, Berlin, Heidelberg 2009, pp. 249–260.
RöslerO. and SuendermannD. A first step towards eye state prediction using eeg, Proc. of the AIHLS, (2013).
29.
MoultonR.H. and ZgrajaJ. The Wilderness Area Data Set: Adapting the Covertype data set for unsupervised learning, arXiv e-prints (2019) arXiv:1901.11040.
30.
DuaD. and Karra TaniskidouE. UCI machine learning repository, 2017.
31.
BlackardJ.A. and DeanD.J., Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables, Computers and Electronics in Agriculture24 (1999), 131–151.
