Combining multiple class distribution modified subsamples in a single tree

Pérez, Jesús M.; Muguerza, Javier; Arbelaitz, Olatz; Gurrutxaga, Ibai; Martín, Jesús Izquierdo

doi:10.1016/j.patrec.2006.08.013

Cited by 43 publications

(28 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Testuinguru honetan, ALDAPA ikerketa-taldeak zuhaitz kontsolidatuak sortzeko algoritmoa proposatu zuen, CTC (Consolidated Tree Construction) algoritmoa, hain zuzen [12,13]. Algoritmo honek lagin multzo bat erabiltzen du eta zuhaitzak pausuz pausu sortzen diren heinean, hauen erabakietan oinarrituta, beste zuhaitz bat sortzen du, zuhaitz kontsolidatua deritzona, hain zuzen.…”

Section: Sarreraunclassified

“…Klase anitzeko datu-basetan (2 baino gehiagokoetan), klaseak orekatzea izango da onartzen den aukera bakarra. Mota honetako azpilaginak hainbat lanetan erabili dira zuhaitz kontsolidatuak sortzeko; kasu batzuetan, gutxiengoaren klasearen proportzio berri bat erabilita (desberdina datu-basearen arabera [13] edo beti %50a, hau da, lagin orekatuak, berriki argitaratutako lanean [16]) eta, beste batzuetan, klase-banaketa balio desberdin zabal bat erabilita [18,19], gutxiengoaren %2-tik %98-ra, honek duen eragina emaitzetan aztertzeko.…”

Section: Inplementatutako Laginketakunclassified

See 1 more Smart Citation

J48Consolidated WEKA paketea, adibide ezohikoen patroiak identifikatzeko tresna

Ibarguren

Pérez

Muguerza

2016

EKAIA

Self Cite

View full text Add to dashboard Cite

Laburpena: Artikulu honetan WEKA ikasketa automatikorako tresnarako CTC algoritmoaren inplementazioa aurkeztuko da: J48Consolidated paketea. CTC algoritmoak lagin multzo bat sortzen du eta lagin guztietan dagoen ezagutza kontuan hartuta sailkapen zuhaitz bakarra eraikitzeko gai da, kasu berrien sailkapenaren azalpena galdu gabe. Gainera, lan honetan J48Consolidated paketeak sortutako zuhaitzen emaitzak aztertuko dira, errealitateko 36 sailkapen problematarako, laginketa mota desberdinetan oinarrituta, eta jatorrizko laginaren estaldura-maila desberdinekin. Emaitzek erakusten dute estaldura-maila altuek orokorrean sailkatzeko gaitasuna handitzen dutela eta %75eko lagin estratifikatuak erabiltzea dela problema hauetan aukerarik lehiakorrena. Hitz-gakoak:Ikasketa automatikoa, Sailkapen gainbegiratua, Zuhaitz kontsolidatuak, CTC algoritmoa, Estalduran oinarritutako laginketa, J48Consolidated, WEKA.Abstract: This article presents the implementation of the CTC algorithm for the WEKA machine learning tool, the J48Consolidated package. The CTC algorithm creates a set of samples and taking the knowledge of all samples into account, is able to build a single classification tree, keeping the explanation of how new examples are classified. In addition, this work analyzes the results achieved by trees built by J48Con-solidated on 36 real world problems, using multiple sampling strategies and with different coverage values of the original sample. Results show that higher coverage values increase discriminating capacity and using stratified subsamples reduced to a 75% of the size give the most competitive results on these datasets.

show abstract

Section: Sarreraunclassified

Section: Inplementatutako Laginketakunclassified

J48Consolidated WEKA paketea, adibide ezohikoen patroiak identifikatzeko tresna

Ibarguren

Pérez

Muguerza

2016

EKAIA

Self Cite

View full text Add to dashboard Cite

show abstract

“…CTC (Perez et al, 2007), ID5R (Utgoff, 1989), ITI (Utgoff et al, 1997), UFFT (Gama & Medes, 2005), StreamTree (Jin & Agrawal, 2003), FDT (Janikowo, 1998), G-DT (Pedrycz, 2005) and Spider (Wang, et al, 2007).…”

Section: Introductionmentioning

confidence: 99%

New Implementations of Data Mining in a Plethora of Human Activities

Ochoa¹,

Ponce²,

Ornelas³

et al. 2011

Knowledge-Oriented Applications in Data Mining

View full text Add to dashboard Cite

“…Pruning is an important step for reducing the size of the tree, reducing the likelihood of over-fitting and resulting in a tree that is faster and easier to interpret (Pérez, Muguerza, Arbelaitz, Gurrutxaga, & Martín, 2007). In relation to the J48 Consolidated algorithm, there are many internal parameters that are available to be varied as part of the pruning mechanisms.…”

Section: Decision Trees Decision Trees Allow For a Visual (Or Graphimentioning

confidence: 99%

“…All trees (from each subsample) then comply with the majority vote, regardless of their individual vote. This process is repeated until the trees agree to stop growing, and a single decision tree output is then generated (Pérez et al, 2007). There are many parameters that can be manipulated in this way.…”

Section: Decision Trees Decision Trees Allow For a Visual (Or Graphimentioning

confidence: 99%

Language disorder from infancy to adulthood: predictors and outcomes

Armstrong¹

View full text Add to dashboard Cite

Developmental language delays are common and are associated with increased risk of adverse educational and psychosocial outcomes later in life. Early intervention services supporting language development may prevent these later problems from occurring.However, with the variability that exists in language development, it is less clear which children with developmental language delays actually require intervention. As such, increased understanding of the trajectory of language impairment and the long-term outcomes in adulthood is needed. The purpose of this thesis was to: (i) determine the early life characteristics that placed children at risk for poor language outcomes, and (ii) profile the long-term psychosocial outcomes in adulthood for language impaired populations. To address these aims prospective longitudinal data from two Australian pregnancy cohort studies; the Mater-University of Queensland Study of Pregnancy (MUSP) and the Western Australian Pregnancy Cohort (Raine) Study, were utilised.The first three studies of this thesis investigated the early life characteristics that predicted later language outcomes in childhood and adulthood. Firstly, Chapter 2 investigated the parental and early childhood factors present at, or prior to 5 years, which were associated with different vocabulary developmental profiles in the MUSP cohort. Receptive vocabulary skills were measured at 5-and 21-years, using the Peabody Picture Vocabulary TestRevised (PPVT-R). A one standard deviation cut-off was applied to determine average and below average performances at the two assessment points. Four vocabulary developmental profiles were then identified, including: 'consistently typical' (average performance at both time points), 'consistently low' (below average scores at both time points), 'improved' (below average performance at 5 years but average performance at 21 years), and 'deteriorated' (average skills at 5 years but below average performance at 21 years). The results revealed that adults with deteriorating vocabulary profiles were more likely to have had internalising behaviours at 5 years, mothers who smoked during pregnancy, and fathers with lower educational attainment, compared to adults with consistently typical vocabulary histories. No significant risk factors were identified for adults showing consistently low vocabulary in comparison to those adults whose early vocabulary delays had improved.

show abstract

Combining multiple class distribution modified subsamples in a single tree

Cited by 43 publications

References 8 publications

J48Consolidated WEKA paketea, adibide ezohikoen patroiak identifikatzeko tresna

J48Consolidated WEKA paketea, adibide ezohikoen patroiak identifikatzeko tresna

New Implementations of Data Mining in a Plethora of Human Activities

Language disorder from infancy to adulthood: predictors and outcomes

Contact Info

Product

Resources

About