Handling High Dimensionality in Ensemble Learning for Arrhythmia Prediction

Multilabel learning is now receiving an increasing attention from a variety of domains and many learning algorithms have been witnessed. Similarly, the multilabel learning may also suffer from the problems of high dimensionality, and little attention has been paid to this issue. In this paper, we propose a new ensemble learning algorithms for multilabel data. The main characteristic of our method is that it exploits the features with local discriminative capabilities for each label to serve the purpose of classification. Specifically, for each label, the discriminative capabilities of features on positive and negative data are estimated, and then the top features with the highest capabilities are obtained. Finally, a binary classifier for each label is constructed on the top features. Experimental results on the benchmark data sets show that the proposed method outperforms four popular and previously published multilabel learning algorithms.

Download Full-text

A New Hybrid Strategy for Malware Detection Classification with Multiple Feature Selection Methods and Ensemble Learning Methods

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.b4666.129219 ◽

2019 ◽

Vol 9 (2) ◽

pp. 4013-4018

Keyword(s):

Feature Selection ◽

Ensemble Learning ◽

Hybrid Approach ◽

High Dimensionality ◽

Gradient Boosting ◽

Learning Approaches ◽

Ensemble Classifiers ◽

Selection Methods ◽

Learning Methods ◽

Hybrid Strategy

A dramatic increase in malware in our day-to-day life causes a noteworthy problem in cyber security. The traditional approaches and signature-based models are not sufficient to defense with the new malware. To achieve zero-day attacks of malware, these approaches are not much competent to face new malware. To enhance the compete for the mechanism of classifying new malware the machine learning approaches are highly effective. To classify new malware with the high dimensionality of data leads to reduce the quality of output and low-performance results. In this paper, we propose a new hybrid strategy that combines the power of feature selection methods along with ensemble learning methods to improve accuracy for high dimensionality of data. This hybrid approach having three stages, preprocessing, feature selection and classification. Three different types of feature selection methods: ExtraTreesClassifier, Percentile and KBest feature selection methods are used to select the best features (dimensionality reduction) and four ensemble classifiers: AdaBoost, Gradient Boosting, Random Forest and Bagging are used for classification. The accuracy of ensemble classifiers are increased with this hybrid model and produces better results of classification with 91.50% accuracy. For dealing with the high dimensionality of data this hybrid approach is very effective and gives better results

Download Full-text