Rakkrit Duangsoithong

Embedded Feature Ranking for Ensemble MLP Classifiers

A feature ranking scheme for multilayer perceptron (MLP) ensembles is proposed, along with a stopping criterion based upon the out-of-bootstrap estimate. To solve multi-class problems feature ranking is combined with modified error-correcting output coding. Experimental results on benchmark data demonstrate the versatility of the MLP base classifier in removing irrelevant features.

Relevance and Redundancy Analysis for Ensemble Classifiers

In machine learning systems, especially in medical applications, clinical datasets usually contain high dimensional feature spaces with relatively few samples that lead to poor classifier performance. To overcome this problem, feature selection and ensemble classification are applied in order to improve accuracy and stability. This research presents an analysis of the effect of removing irrelevant and redundant features with ensemble classifiers using five datasets and compared with floating search method. Eliminating redundant features provides better accuracy and computational time than removing irrelevant features of the ensemble.

Relevant and Redundant Feature Analysis with Ensemble Classification

Feature selection and ensemble classification increase system efficiency and accuracy in machine learning, data mining and biomedical informatics. This research presents an analysis of the effect of removing irrelevant and redundant features with ensemble classifiers using two datasets from UCI machine learning repository. Accuracy and computational time were evaluated by four base classifiers; NaiveBayes, Multilayer Perceptron, Support Vector Machines and Decision Tree. Eliminating irrelevant features improves accuracy and reduces computational time while removing redundant features reduces computational time and reduces accuracy of the ensemble.

Bootstrap feature selection for ensemble classifiers

Small number of samples with high dimensional feature space leads to degradation of classifier performance for machine learning, statistics and data mining systems. This paper presents a bootstrap feature selection for ensemble classifiers to deal with this problem and compares with traditional feature selection for ensemble (select optimal features from whole dataset before bootstrap selected data). Four base classifiers: Multilayer Perceptron, Support Vector Machines, Naive Bayes and Decision Tree are used to evaluate the performance of UCI machine learning repository and causal discovery datasets. Bootstrap feature selection algorithm provides slightly better accuracy than traditional feature selection for ensemble classifiers.

Correlation-based and causal feature selection analysis for ensemble classifiers

High dimensional feature spaces with relatively few samples usually leads to poor classifier performance for machine learning, neural networks and data mining systems. This paper presents a comparison analysis between correlation-based and causal feature selection for ensemble classifiers. MLP and SVM are used as base classifier and compared with Naive Bayes and Decision Tree. According to the results, correlation-based feature selection algorithm can eliminate more redundant and irrelevant features, provides slightly better accuracy and less complexity than causal feature selection. Ensemble using Bagging algorithm can improve accuracy in both correlation-based and causal feature selection.

SDSoC based development of vehicle counting system using adaptive background method

This paper presents a processing system of vehicle detection and counting for a camera on the city street using a heterogeneous ARM/FPGA processor and Xilinx SDSoC (Software-Defined System on Chip). An adaptive background method for reducing the impact of environment have been developed by analyzing luminance approximation changes over time and luminance approximation changes suddenly to improve background image of the object and to eliminate shadows so that the process of vehicles detecting and counting worked effectively.

Correlation Feature Selection Analysis for Fault Diagnosis of Induction Motors

This paper presents a feature selection method for stator winding fault analysis of induction motors by using a Correlation-based Feature Selection (CFS) method. The 14 original motor parameters are selected from the feature selection method with various searching approaches. The classification efficiency of optimal features obtained from the feature selection method is compared with results from the feature extraction method and the original features. In our experiment, we employ a 2.2 kW delta-connected motor which drives a dc generator as a load. The experimental results demonstrate that 4 common selected features for stator winding fault analysis of induction motors are a percent of load (%Load), a power factor (pf), a negative sequence voltage (V n ), and a negative sequence impedance (Z n ). The accuracy of the classification using this feature subset is higher than using all original features for three classification methods.

Hybrid Correlation and Causal Feature Selection for Ensemble Classifiers

PC and TPDA algorithms are robust and well known prototype algorithms, incorporating constraint-based approaches for causal discovery. However, both algorithms cannot scale up to deal with high dimensional data, that is more than few hundred features. This chapter presents hybrid correlation and causal feature selection for ensemble classifiers to deal with this problem. Redundant features are removed by correlation-based feature selection and then irrelevant features are eliminated by causal feature selection. The number of eliminated features, accuracy, the area under the receiver operating characteristic curve (AUC) and false negative rate (FNR) of proposed algorithms are compared with correlation-based feature selection (FCBF and CFS) and causal based feature selection algorithms (PC, TPDA, GS, IAMB).