Improved intuitionistic fuzzy twin support vector machine ensemble training for imbalanced data classification

Aiming at the sensitivity of twin support vector machines to noise and outliers, an improved fuzzy twin support vector machine is proposed. Aiming at the shortcomings of fuzzy membership based on the distance between a sample and its class center, this algorithm proposes a new fuzzy membership function that can effectively reflect sample uncertainty— based on intra-class hyperplane and sample affinity. When determining the membership function, the intra-class hyperplane replaces the class center, reducing the dependence on the sample set geometry and improving the model generalization ability. At the same time, considering the relation between each sample and the confusion degree of sample points, the sample affinity is applied to the design of membership function, so as to effectively distinguish the effective sample from noise and outliers and improve the classification accuracy. The experimental results show that compared with the twin support vector machine and the classic fuzzy support vector machine, the improved fuzzy twin support vector machine has better classification performance.

This paper proposes a fuzzy-based Lagrangian twin parametric-margin support vector machine (FLTPMSVM) to reduce the effect of the outliers presented in biomedical data. The proposed FLTPMSVM assigns the weights to each data sample on the basis of fuzzy membership values to reduce the effect of outliers. This paper also adopts the square of the 2-norm of slack variables to make the objective function more convex. The proposed FLTPMSVM solves simple linearly convergent iterative schemes instead of solving a pair of quadratic programming problems. No external toolbox is required for the proposed FLTPMSVM as compared to the other methods. To establish the applicability of the proposed FLTPMSVM in the area of biomedical data classification, numerical experiments are performed on several biomedical datasets. The proposed FLTPMSVM gives an improved generalization performance and reduced training cost as compared to support vector machine (SVM), twin support vector machine (TWSVM), fuzzy twin support vector machine (FTSVM), twin parametric-margin support vector machine (TPMSVM) and new fuzzy twin support vector machine (NFTSVM).

Safe intuitionistic fuzzy twin support vector machine for semi-supervised learning

The twin support vector machine (TWSVM) classifier and its fuzzy variant fuzzy twin support vector machine (FTSVM) have received considerable attention due to their low computational complexity. However, their performance often deteriorates when the input data is affected by noise. To overcome this limitation, this study leverages the robustness of granular-ball computing (GBC) against noise to develop more effective classification models by integrating GBC with TWSVM and FTSVM. First, we introduce the granular-ball TWSVM (GBTWSVM) classifier, which incorporates GBC with the TWSVM framework. By replacing traditional point-wise inputs with granular-ball representations, we derive a pair of nonparallel hyperplanes for the GBTWSVM classifier by solving a quadratic programming problem. Afterwards, we develop the granular-ball FTSVM (GBFTSVM) classifier, where the membership and nonmembership functions of granular-balls are defined using Pythagorean fuzzy sets, enabling a more nuanced differentiation of the contributions of granular-balls from distinct regions within the input space. By incorporating these functions into the FTSVM framework, we derive a pair of nonparallel hyperplanes for the GBFTSVM classifier through the solution of a quadratic programming problem. Finally, we present algorithms for the GBTWSVM and GBFTSVM classifiers and evaluate their performance on 21 benchmark datasets. Experimental results demonstrate the superior scalability, computational efficiency, and robustness of the proposed classifiers in pattern recognition, highlighting their potential as advanced tools for noise-tolerant classification.

In order to develop Human-centric Driver Fatigue Monitoring Systems (HDFMS) with aims to increase driving safety, an efficient combined features extraction from Curvelet transform and Gabor wavelet transform for fatigue expressions descriptions of vehicle drivers is proposed, and Random Subspace Ensemble (RSE) of Support Vector Machines (SVMs) with polynomial kernel as the base classifier is then exploited for classification of three predefined fatigue expressions classes, namely, awake expressions, moderate fatigue expressions, and severe fatigue expressions. The results of holdout and cross-validation experiments show that CF by RSE of SVMs with polynomial kernel outperforms other seven classifiers, i.e., Curvelet features by SVMs classifier, Gabor features by SVMs classifier, CF by five individual SVMs classifiers. With CF and RSE of SVMs with polynomial kernel, the classification accuracies of drivers' fatigue expressions are over 90% in both of the holdout and cross-validation experiments, which show the proposed approach of combined features extraction and RSE of SVMs can be used for developing Human-centric Driver Fatigue Monitoring Systems to increase driving safety.

Kreĭn twin support vector machines for imbalanced data classification

Support Vector Machines (SVMs) ensembles have been widely used to improve classification accuracy in complicated pattern recognition tasks. In this work we propose to apply an ensemble of SVMs coupled with feature-subset selection methods to aleviate the curse of dimensionality associated with expression-based classification of DNA microarray data. We compare the single SVM classifier to SVM ensembles applying two different feature-subset selection techniques, namely random selection and k-means clustering, the base classifiers are combined using either majority vote or SVM fusion. Two real-world benchmarks datasets are used to evaluate and compare the performance. Experimental results show that the SVM ensemble of SVM base classifiers using k-means clustering for feature-subset selection and employing an SVM combiner achieve the best classification accuracy, and that feature-subset-selection methods can have considerable impact on the classification accuracy.

In this paper, the algorithm design of the support vector machines (SVMs) ensemble in a practical multi-stage framework is analyzed which can be implemented efficiently by evolutionary multi-objective optimization algorithm. The designing of SVMs ensemble is considered in three stages: first, the bootstrap method and a strategy of dynamical parameter range adjustment are used to generate more diverse base SVMs, and the NSGA-II algorithm which can efficiently tune the parameters of SVMs is applied to ensure the accuracy of base SVMs; Second, the NSGA-II algorithm is used again to select the member of ensemble based on the accuracy and diversity of the ensemble we have measured; Last, the reliability of different class is computed and combined to decide the outputs of ensemble in terms of the decision values of base SVMs. The proposed algorithm is applied to the UCI datasets, some useful results has been concluded for the future work in this field.

In this paper we propose a system for visual object detection and tracking based on the extended structural tensor and the ensemble of one-class support vector machines. First, the input color image is transformed with the anisotropic process into the extended structural tensor. Then the tensor space is clustered into the number of partitions which are used to train a corresponding number of one-class support vector machines composing an ensemble of classifiers. In run-time the ensemble classifies the input video stream into an object and background. Thanks to high discriminative properties of the extended structural tensor and to the diversity of the ensemble of classifiers the method shows very good properties which were shown by experiments on real video sequences.

Imbalanced datasets exist widely in real life. The identification of the minority class in imbalanced datasets tends to be the focus of classification. The twin support vector machine (TWSVM) as a variant of enhanced SVM provides an effective technique for data classification. In the paper, we propose to combine a re-sampling technique, which utilizes over-sampling and under-sampling to balance the training data, with TWSVM to deal with imbalanced data classification. Experimental results show that our proposed approach outperforms other state-of–art methods.

Online dynamic security assessment of wind integrated power system using SDAE with SVM ensemble boosting learner

abstractUniversum, a third class not belonging to either class of the classification problem, allows to incorporate the prior knowledge into the learning process. A lot of previous work have demonstrated that the Universum is helpful to the supervised and semi-supervised classification. Moreover, Universum has already been introduced into the support vector machine (SVM) and twin support vector machine (TSVM) to enhance the generalisation performance. To further increase the generalisation performance, we propose a least squares TSVM with Universum data (-TSVM) in this paper. Our -TSVM possesses the following advantages: first, it exploits Universum data to improve generalisation performance. Besides, it implements the structural risk minimisation principle by adding a regularisation to the objective function. Finally, it costs less computing time by solving two small-sized systems of linear equations instead of a single larger-sized quadratic programming problem. To verify the validity of our proposed algorithm, we conduct various experiments around the size of labelled samples and the number of Universum data on data-sets including seven benchmark data-sets, Toy data, MNIST and Face images. Empirical experiments indicate that Universum contributes to making prediction accuracy improved even stable. Especially when fewer labelled samples given, -TSVM is far superior to the improved LS-TSVM (ILS-TSVM), and slightly superior to the -TSVM.

Modeling radiation-induced lung injury risk with an ensemble of support vector machines

Fine-grained classification is a recognition task where subtle differences distinguish between different classes. To tackle this classification problem, part-based classification methods are mostly used. Partbased methods learn an algorithm to detect parts of the observed object and extract local part features for the detected part regions. In this paper we show that not all extracted part features are always useful for the classification. Furthermore, given a part selection algorithm that actively selects parts for the classification we estimate the upper bound for the fine-grained recognition performance. This upper bound lies way above the current state-of-the-art recognition performances which shows the need for such an active part selection method. Though we do not present such an active part selection algorithm in this work, we propose a novel method that is required by active part selection and enables sequential part-based classification. This method uses a support vector machine (SVM) ensemble and allows to classify an image based on arbitrary number of part features. Additionally, the training time of our method does not increase with the amount of possible part features. This fact allows to extend the SVM ensemble with an active part selection component that operates on a large amount of part feature proposals without suffering from increasing training time.

Cancer recognition with bagged ensembles of support vector machines