Jump to content

Massive Online Analysis: Difference between revisions

From Wikipedia, the free encyclopedia
Browse history interactively
← Previous editNext edit →
Content deleted Content added
VisualWikitext
No edit summary
Add algorithms
Line 12: Line 12:
}}
}}


'''MOA (Massive Online Analysis)''' is a free open-source software specific for mining data streams with concept drift.<ref name="bifet2010moa">{{cite journal
'''MOA (Massive Online Analysis)'''<ref name="bifet2010moa">{{cite journal
|last1=Bifet |first1=Albert
|last1=Bifet |first1=Albert
|last2=Holmes |first2=Geoff
|last2=Holmes |first2=Geoff
|last3=Kirkby |first3=Richard
|last3=Kirkby |first3=Richard
|last4=Pfahringer |first4=Bernhard
|last4=Pfahringer |first4=Bernhard
|title=Moa: Massive online analysis
|title=MOA: Massive online analysis
|journal=The Journal of Machine Learning Research
|journal=The Journal of Machine Learning Research
|volume=99
|volume=99
|pages=1601–1604|year=2010
|pages=1601–1604|year=2010
}}</ref>. It's written in [[Java (programming language)|Java]] and developed at the [[University of Waikato]], [[New Zealand]].
}}</ref> is a free open-source software specific for [[Data stream mining]] with [[Concept drift]]. It's written in [[Java (programming language)|Java]] and developed at the [[University of Waikato]], [[New Zealand]].


==Description==
==Description==


MOA is an open-source framework software that allows to build and run experiments
MOA contains several collections of machine learning algorithms ( [[Statistical classification|classification]], [[Regression analysis|regression]], [[data clustering|clustering]], outlier detection and recommender systems). These algorithms are designed for large scale machine learning, dealing with concept drift, and big data streams in real time.
of machine learning or data mining on evolving data streams. It includes a set of learners and stream generators that can be used from the Graphical User Interface (GUI), the command-line, and the Java API.
MOA contains several collections of machine learning algorithms:

* [[Statistical classification|Classification]]
** Bayesian classifiers
*** Naive Bayes
*** Naive Bayes Multinomial
** Decision trees classifiers
*** Decision Stump
*** Hoeffding Tree
*** Hoeffding Option Tree
*** Hoeffding Adaptive Tree
** Meta classifiers
*** Bagging
*** Boosting
*** Bagging using ADWIN
*** Bagging using Adaptive-Size Hoeffding Trees.
*** Perceptron Stacking of Restricted Hoeffding Trees
*** Leveraging Bagging
*** Online Accuracy Updated Ensemble
** Function classifiers
*** Perceptron
*** [[Stochastic gradient descent]] (SGD)
*** Pegasos
** Drift classifiers
** Multi-label classifiers<ref name="ReadBifet2012">{{cite journal|last1=Read|first1=Jesse|last2=Bifet|first2=Albert|last3=Holmes|first3=Geoff|last4=Pfahringer|first4=Bernhard|title=Scalable and efficient multi-label classification for evolving data streams|journal=Machine Learning|volume=88|issue=1-2|year=2012|pages=243–272|issn=0885-6125|doi=10.1007/s10994-012-5279-6}}</ref>
** [[Active_learning_(machine_learning)|Active learning]] classifiers <ref name="ZliobaiteBifet2014">{{cite journal|last1=Zliobaite|first1=Indre|last2=Bifet|first2=Albert|last3=Pfahringer|first3=Bernhard|last4=Holmes|first4=Geoffrey|title=Active Learning With Drifting Streaming Data|journal=IEEE Transactions on Neural Networks and Learning Systems|volume=25|issue=1|year=2014|pages=27–39|issn=2162-237X|doi=10.1109/TNNLS.2012.2236570}}</ref>
* [[Regression analysis|Regression]]
** FIMTDD<ref name="IkonomovskaGama2010">{{cite journal|last1=Ikonomovska|first1=Elena|last2=Gama|first2=João|last3=Džeroski|first3=Sašo|title=Learning model trees from evolving data streams|journal=Data Mining and Knowledge Discovery|volume=23|issue=1|year=2010|pages=128–168|issn=1384-5810|doi=10.1007/s10618-010-0201-y}}</ref>
** AMRules<ref name="AlmeidaFerreira2013">{{cite journal|last1=Almeida|first1=Ezilda|last2=Ferreira|first2=Carlos|last3=Gama|first3=João|title=Adaptive Model Rules from Data Streams|volume=8188|year=2013|pages=480–492|issn=0302-9743|doi=10.1007/978-3-642-40988-2_31}}</ref>
* [[data clustering|Clustering]]<ref name="KranenKremer2010">{{cite journal|last1=Kranen|first1=Philipp|last2=Kremer|first2=Hardy|last3=Jansen|first3=Timm|last4=Seidl|first4=Thomas|last5=Bifet|first5=Albert|last6=Holmes|first6=Geoff|last7=Pfahringer|first7=Bernhard|title=Clustering Performance on Evolving Data Streams: Assessing Algorithms and Evaluation Measures within MOA|year=2010|pages=1400–1403|doi=10.1109/ICDMW.2010.17}}</ref>
** StreamKM++
** CluStream
** ClusTree
** D-Stream
** CobWeb.
* Outlier detection<ref name="GeorgiadisKontaki2013">{{cite journal|last1=Georgiadis|first1=Dimitrios|last2=Kontaki|first2=Maria|last3=Gounaris|first3=Anastasios|last4=Papadopoulos|first4=Apostolos N.|last5=Tsichlas|first5=Kostas|last6=Manolopoulos|first6=Yannis|title=Continuous outlier detection in data streams|year=2013|pages=1061|doi=10.1145/2463676.2463691}}</ref>
** STORM
** Abstract-C
** COD
** MCOD
** AnyOut<ref name="AssentKranen2012">{{cite journal|last1=Assent|first1=Ira|last2=Kranen|first2=Philipp|last3=Baldauf|first3=Corinna|last4=Seidl|first4=Thomas|title=AnyOut: Anytime Outlier Detection on Streaming Data|volume=7238|year=2012|pages=228–242|issn=0302-9743|doi=10.1007/978-3-642-29038-1_18}}</ref>
* [[Recommender system|Recommender systems]]
** BRISMFPredictor
* Frequent pattern mining
** Itemsets<ref name="Quadrana2013">{{cite journal|last1=Quadrana|first1=Massimo|last2=Bifet|first2=Albert|last3=Gavaldà|first3=Ricard|title=An Efficient Closed Frequent Itemset Miner for the MOA Stream Mining System|year=2013|pages=203|doi=10.3233/978-1-61499-320-9-203}}</ref>
** Graphs<ref name="BifetHolmes2011">{{cite journal|last1=Bifet|first1=Albert|last2=Holmes|first2=Geoff|last3=Pfahringer|first3=Bernhard|last4=Gavaldà|first4=Ricard|title=Mining frequent closed graphs on evolving data streams|year=2011|pages=591|doi=10.1145/2020408.2020501}}</ref>
* Change detection algorithms<ref name="BifetRead2013">{{cite journal|last1=Bifet|first1=Albert|last2=Read|first2=Jesse|last3=Pfahringer|first3=Bernhard|last4=Holmes|first4=Geoff|last5=Žliobaitė|first5=Indrė|title=CD-MOA: Change Detection Framework for Massive Online Analysis|volume=8207|year=2013|pages=92–103|issn=0302-9743|doi=10.1007/978-3-642-41398-8_9}}</ref>

These algorithms are designed for large scale machine learning, dealing with concept drift, and big data streams in real time.


MOA supports bi-directional interaction with [[Weka (machine learning)]]. MOA is [[free software]] released under the [[GNU GPL]].
MOA supports bi-directional interaction with [[Weka (machine learning)]]. MOA is [[free software]] released under the [[GNU GPL]].

==See also==
{{Portal|Free software}}
* [https://adams.cms.waikato.ac.nz/ ADAMS Workflow]: Workflow engine for MOA and [[Weka (machine learning)]]
* [http://www-ai.cs.uni-dortmund.de/SOFTWARE/streams/ Streams]: Flexible module environment for the design and execution of data stream experiments
* [[Weka (machine learning)]]
* [[Vowpal Wabbit]]
* [[List of numerical analysis software]]


== References ==
== References ==

Revision as of 15:42, 26 February 2014

MOA
Developer(s)University of Waikato
Stable release
2013.11 / 2013/11/01
Repository
Operating systemCross-platform
TypeMachine Learning
LicenseGNU General Public License
Websitehttp://moa.cms.waikato.ac.nz/

MOA (Massive Online Analysis)[1] is a free open-source software specific for Data stream mining with Concept drift. It's written in Java and developed at the University of Waikato, New Zealand.

Description

MOA is an open-source framework software that allows to build and run experiments of machine learning or data mining on evolving data streams. It includes a set of learners and stream generators that can be used from the Graphical User Interface (GUI), the command-line, and the Java API. MOA contains several collections of machine learning algorithms:

  • Classification
    • Bayesian classifiers
      • Naive Bayes
      • Naive Bayes Multinomial
    • Decision trees classifiers
      • Decision Stump
      • Hoeffding Tree
      • Hoeffding Option Tree
      • Hoeffding Adaptive Tree
    • Meta classifiers
      • Bagging
      • Boosting
      • Bagging using ADWIN
      • Bagging using Adaptive-Size Hoeffding Trees.
      • Perceptron Stacking of Restricted Hoeffding Trees
      • Leveraging Bagging
      • Online Accuracy Updated Ensemble
    • Function classifiers
    • Drift classifiers
    • Multi-label classifiers[2]
    • Active learning classifiers [3]
  • Regression
  • Clustering[6]
    • StreamKM++
    • CluStream
    • ClusTree
    • D-Stream
    • CobWeb.
  • Outlier detection[7]
    • STORM
    • Abstract-C
    • COD
    • MCOD
    • AnyOut[8]
  • Recommender systems
    • BRISMFPredictor
  • Frequent pattern mining
  • Change detection algorithms[11]

These algorithms are designed for large scale machine learning, dealing with concept drift, and big data streams in real time.

MOA supports bi-directional interaction with Weka (machine learning). MOA is free software released under the GNU GPL.

See also

References

  1. ^ Bifet, Albert; Holmes, Geoff; Kirkby, Richard; Pfahringer, Bernhard (2010). "MOA: Massive online analysis". The Journal of Machine Learning Research. 99: 1601–1604.
  2. ^ Read, Jesse; Bifet, Albert; Holmes, Geoff; Pfahringer, Bernhard (2012). "Scalable and efficient multi-label classification for evolving data streams". Machine Learning. 88 (1–2): 243–272. doi:10.1007/s10994-012-5279-6. ISSN 0885-6125.
  3. ^ Zliobaite, Indre; Bifet, Albert; Pfahringer, Bernhard; Holmes, Geoffrey (2014). "Active Learning With Drifting Streaming Data". IEEE Transactions on Neural Networks and Learning Systems. 25 (1): 27–39. doi:10.1109/TNNLS.2012.2236570. ISSN 2162-237X.
  4. ^ Ikonomovska, Elena; Gama, João; Džeroski, Sašo (2010). "Learning model trees from evolving data streams". Data Mining and Knowledge Discovery. 23 (1): 128–168. doi:10.1007/s10618-010-0201-y. ISSN 1384-5810.
  5. ^ Almeida, Ezilda; Ferreira, Carlos; Gama, João (2013). "Adaptive Model Rules from Data Streams". 8188: 480–492. doi:10.1007/978-3-642-40988-2_31. ISSN 0302-9743. {{cite journal}}: Cite journal requires |journal= (help)
  6. ^ Kranen, Philipp; Kremer, Hardy; Jansen, Timm; Seidl, Thomas; Bifet, Albert; Holmes, Geoff; Pfahringer, Bernhard (2010). "Clustering Performance on Evolving Data Streams: Assessing Algorithms and Evaluation Measures within MOA": 1400–1403. doi:10.1109/ICDMW.2010.17. {{cite journal}}: Cite journal requires |journal= (help)
  7. ^ Georgiadis, Dimitrios; Kontaki, Maria; Gounaris, Anastasios; Papadopoulos, Apostolos N.; Tsichlas, Kostas; Manolopoulos, Yannis (2013). "Continuous outlier detection in data streams": 1061. doi:10.1145/2463676.2463691. {{cite journal}}: Cite journal requires |journal= (help)
  8. ^ Assent, Ira; Kranen, Philipp; Baldauf, Corinna; Seidl, Thomas (2012). "AnyOut: Anytime Outlier Detection on Streaming Data". 7238: 228–242. doi:10.1007/978-3-642-29038-1_18. ISSN 0302-9743. {{cite journal}}: Cite journal requires |journal= (help)
  9. ^ Quadrana, Massimo; Bifet, Albert; Gavaldà, Ricard (2013). "An Efficient Closed Frequent Itemset Miner for the MOA Stream Mining System": 203. doi:10.3233/978-1-61499-320-9-203. {{cite journal}}: Cite journal requires |journal= (help)
  10. ^ Bifet, Albert; Holmes, Geoff; Pfahringer, Bernhard; Gavaldà, Ricard (2011). "Mining frequent closed graphs on evolving data streams": 591. doi:10.1145/2020408.2020501. {{cite journal}}: Cite journal requires |journal= (help)
  11. ^ Bifet, Albert; Read, Jesse; Pfahringer, Bernhard; Holmes, Geoff; Žliobaitė, Indrė (2013). "CD-MOA: Change Detection Framework for Massive Online Analysis". 8207: 92–103. doi:10.1007/978-3-642-41398-8_9. ISSN 0302-9743. {{cite journal}}: Cite journal requires |journal= (help)
Retrieved from "https://en.wikipedia.org/enwiki/w/index.php?title=Massive_Online_Analysis&oldid=597235770"