A Meta-Ensemble Classifier Approach: Random Rotation Forest

Taşçı, Erdal

doi:10.17694/bajece.502156

Cited by 15 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Random Forest (a subprocess of the Meta-ensemble method) is used as a base learner in the rotation forest. This approach has enhanced performances [7].…”

Section: Related Workmentioning

confidence: 98%

A Stacking-based Ensemble Learning Method for Outlier Detection

Abro

2021

Preprint

View full text Add to dashboard Cite

Outlier detection is considered as one of the crucial research areas for data mining. Many methods have been studied widely and utilized for achieving better results in outlier detection from existing literature; however, the effects of these few ways are inadequate. In this paper, a stacking-based ensemble classifier has been proposed along with four base learners (namely, Rotation Forest, Random Forest, Bagging and Boosting) and a Meta-learner (namely, Logistic Regression) to progress the outlier detection performance. The proposedmechanism is evaluated on five datasets from the ODDS library by adopting five performance criteria. The experimental outcomes demonstrate that the proposed method outperforms than the conventional ensemble approaches concerning the accuracy, AUC (Area Under Curve), precision, recall and Fmeasure values.This method can be used for image recognition and machine learning problems, such as binary classification.

show abstract

“…Random Forest (a subprocess of the Meta-ensemble method) is used as a base learner in the rotation forest. This approach has enhanced performances [7].…”

Section: Related Workmentioning

confidence: 98%

A Stacking-based Ensemble Learning Method for Outlier Detection

Abro

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Even though there are a number of the supervised algorithms of ML, random forest has 2 distinctive features; initially, the error of the generalization converges with the increase of the number of the trees in the forest and the method suffers from no over-fitting. The precision of the distinct single trees making up the forest results in a convergence of the generalization errors and as a result, improvements in the accuracy of the classification [2,24,27].Figure ( 6) the structure of Random Forest.…”

Section: Fig (5): the Structure Of Decision Treementioning

confidence: 99%

“…This process will keep on going to the point where any additional pruning will result in reducing accuracy. Where, p (Cj | x1, x2,….., xd) represent the class membership posterior probabilities [11,24,30].…”

Section: Fig (8): Random Tree Structure [31]mentioning

confidence: 99%

Toward Generating a new Video Education Lectures Dataset and Performance Comparison with Various Machine Learning Algorithms

Abdulameer¹,

Abdullah²

2019

ATMPH

View full text Add to dashboard Cite

During the last decade, Data has a significant role in analytic processes, applications, and numerous areas of the human activities. With the growth in data complexity and size, we come across a vital necessity for tools promoting the explanations and understanding over dataassociated procedures. Due to the lack of adequate dataset, anomaly-based approaches in education resources datasets which are monopoly to the universities or educational institutions. The objective of this research is to build a new dataset called video educational lectures dataset due to the lake of educational resources datasets this dataset designed for postgraduate students, then test the performance of (Video Lectures) dataset by applying a set of algorithms of machine learning for the tasks of data mining, the different classification methods, are: J48, Decision Tree, OneR, Bayes Network, Random Forest, LMT, Random Tree, LWL, REP, and Navies Bayes algorithm, after that the new dataset will be tested and evaluated by compare it with a public dataset (Good Book) dataset through using the same classification algorithms. The several measures which are considered for the analytical purposes are Sensitivity, Accuracy, Precision, F-measure, and False positive Rate. All the results of those parameters are taken for all of the described methods of classification. Finally, results have been provided in tabular way to test and evaluate the performance of the Video Lectures dataset, and other tabular form to facilitate comparative between the Video Lectures and Good Book datasets that proved the Video Lectures dataset get better Accuracy percentage than Good Book dataset.

show abstract

“…Supervised learning also known as classification is a widely used technique for variety of problems, such as face recognition (Yavuz et al 2016), bioinformatics (Yılmaz 2020), medical (Saleh & Hussein 2019), and intrusion detection (Özgür & Erdem 2012). Widely different classification algorithms are proposed in the literature (Taşcı 2019. Proposed algorithms mostly assume that necessary computing capabilities exist for algorithms to work and rarely address low computing requirements.…”

Section: Introductionmentioning

confidence: 99%

Classifier Selection in Resource Limited Hardware: Decision Analysis and Resolution Approach

Özgür¹

2021

Journal of Intelligent Systems: Theory and Applications

View full text Add to dashboard Cite

Digitalization, Industry 4.0 and Internet of things (IoT) have become more popular in the recent years. Most of these systems depend on micro-controllers and sensors. These micro-controllers and sensors are mostly cheap, low RAM and low CPU systems; thus, they are resource constrained environments. In this study, a supervised learning classifier comparison technique suitable for resource constrained environments is proposed. This technique, Decision Analysis and Resolution (DAR), is originated in the domain of Software Engineering. First, DAR is explained using an example of car buying scenario. Then 11 off-the-shelf classifiers are compared using DAR for low RAM and less powerful CPU environments in an intrusion detection scenario. This scenario simulated on wellknown KDD99 intrusion detection dataset. All the experiments are realized using python scikit-learn package. According to the experiments, Decision Tree classifier is the most suitable to implement for resource constrained environments with a small lead. Results for the other three classifiers (Bagging, Multi Layer Perceptron, Random Forest) are also very similar. To aid the reproducibility of the experiments, the whole source code of the study is provided in the popular open source repository https://github.com/atiozgur/classifier-comparison-using-DAR.

show abstract

A Meta-Ensemble Classifier Approach: Random Rotation Forest

Cited by 15 publications

References 20 publications

A Stacking-based Ensemble Learning Method for Outlier Detection

A Stacking-based Ensemble Learning Method for Outlier Detection

Toward Generating a new Video Education Lectures Dataset and Performance Comparison with Various Machine Learning Algorithms

Classifier Selection in Resource Limited Hardware: Decision Analysis and Resolution Approach

Contact Info

Product

Resources

About