Data Mining Algorithms

Cichosz, Paweł

doi:10.1002/9781118950951

Cited by 83 publications

(41 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In both cases, ensemble method provides significant improvement over a single model at the expense of investing more computation time due to building multiple models. To utilize this potential for superior predictive power, suitable techniques for building of base models (models used as inputs for ensemble methods) and aggregation are needed [108]. The base models often generated using machine learning algorithms.…”

Section: Ensemble Methodsmentioning

confidence: 99%

“…Though there are several ensemble models in the machine learning literature, there are two models that use decision tree learners as a base model and have proven to be effective on solving regression problems for a wide range of datasets. These ensemble models are: bagging and boosting decision trees [76,90,108]. Both types of models are integrated in the developed carbonation depth prediction model presented in Publication II of the dissertation.…”

Section: Ensemble Methodsmentioning

confidence: 99%

“…If a split's outcome can be explicitly ascertained for any attainable instance, then it does partition the domain into disjoint subsets, in proportion to the outgoing branches. Hence, it is easy to realize that each node of a decision tree complies with a region (subset) of the domain (Equation 2.17) determined by the sequence of splits 1 , 2 , … , and their outcomes 1 , 2 , … , occurring on the path from the root to the node [108].…”

Section: Decision Treementioning

confidence: 99%

See 2 more Smart Citations

Neural network based hygrothermal prediction for deterioration risk analysis of surface-protected concrete façade element

Taffese

Sistonen

2016

Construction and Building Materials

View full text Add to dashboard Cite

Section: Ensemble Methodsmentioning

confidence: 99%

Section: Ensemble Methodsmentioning

confidence: 99%

Section: Decision Treementioning

confidence: 99%

See 1 more Smart Citation

Neural network based hygrothermal prediction for deterioration risk analysis of surface-protected concrete façade element

Taffese

Sistonen

2016

Construction and Building Materials

View full text Add to dashboard Cite

“…Centroid means it's at the center of all the data points in a cluster. -means is a simple algorithm based on www.ijarai.thesai.org similarity and the measure of similarity plays an important role in the process of clustering [18,19,20].…”

Section: Density Based Svm For Special Casesmentioning

confidence: 99%

Density Based Support Vector Machines for Classification

Nazari¹,

Kang²

2015

ijarai

View full text Add to dashboard Cite

Abstract-Support Vector Machines (SVM) is the most successful algorithm for classification problems. SVM learns the decision boundary from two classes (for Binary Classification) of training points. However, sometimes there are some less meaningful samples amongst training points, which are corrupted by noises or misplaced in wrong side, called outliers. These outliers are affecting on margin and classification performance, and machine should better to discard them. SVM as a popular and widely used classification algorithm is very sensitive to these outliers and lacks the ability to discard them. Many research results prove this sensitivity which is a weak point for SVM. Different approaches are proposed to reduce the effect of outliers but no method is suitable for all types of data sets. In this paper, the new method of Density Based SVM (DBSVM) is introduced. Population Density is the basic concept which is used in this method for both linear and non-linear SVM to detect outliers.Experiments on artificial data sets, real highdimensional benchmark data sets of Liver disorder and Heart disease, and data sets of new and fatigued banknotes' acoustic signals can prove the efficiency of this method on noisy data classification and the better generalization that it can provide compared to the standard SVM.

show abstract

“…Given the appropriate representation of the training data, Random Forest methods are capable of learning complex non-linear mapping with great accuracy and generalisation [237]. Randomness induced into the trees during the training stage (Section 4.2) makes them highly resistant to overfitting[238]. Moreover, they are easily distributable on parallel hardware architecture and can be easily deployed to real-time systems with no specialized hardware requirements.…”

mentioning

confidence: 99%