KNN weighted reduced universum twin SVM for class imbalance learning

نویسندگان

چکیده

In real world problems, imbalance of data samples poses major challenge for the classification problems as a particular class are dominating. Problems like fault and disease detection involve hence need attention to avoid bias towards class. The models support vector machines (SVM) get biased majority results in misclassification minority samples. SVM suffers no prior information related is involved generation hyperplanes. Also, local neighbourhood ignored thus treats each sample equally generating However, points may be contaminated mislead Inspired by idea information, we propose K-nearest neighbour based weighted reduced universum twin learning (KWRUTSVM-CIL). proposed KWRUTSVM-CIL embodies uses balance classes problems. Local incorporated via weight matrix objective function. model, vectors used corresponding constraints functions exploit interclass information. oversampling undersampling approaches followed Universum gives data. Twin SVM, implement empirical risk minimization principle lead overfitting. model regularization term maximize margin structural which marrow statistical overcomes issues Experimental analysis signify that generalization ability superior comparison other models. As an application, use diagnosis Alzheimer’s breast cancer disease. showed better performance compared biomedical datasets.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Universum Learning for Multiclass SVM

We introduce Universum learning [1], [2] for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM). We also propose a span bound for MU-SVM that can be used for model selection thereby avoiding resampling. Empirical results demonstrate the effectiveness of MU-SVM and the proposed bound.

متن کامل

Weighted Twin Support Vector Machine with Universum

Universum is a new concept proposed recently, which is defined to be the sample that does not belong to any classes concerned. Support Vector Machine with Universum (U-SVM) is a new algorithm, which can exploit Universum samples to improve the classification performance of SVM. In fact, samples in the different positions have different effects on the bound function. Then, we propose a weighted ...

متن کامل

Practical Analysis of the Universum SVM Learning

The idea of ‘inference through contradictions’ was introduced by Vapnik[1] in order to incorporate a priori knowledge into the learning process. This knowledge is introduced via additional unlabeled data samples (called virtual examples or the Universum) that are used along with labeled training samples, to perform an inductive inference. For example, if the goal of learning is to discriminate ...

متن کامل

Semi-supervised Learning for SVM-KNN

Compared with labeled data, unlabeled data are significantly easier to obtain. Currently, classification of unlabeled data is an open issue. In this paper a novel SVMKNN classification methodology based on Semi-supervised learning is proposed, we consider the problem of using a large number of unlabeled data to boost performance of the classifier when only a small set of labeled examples is ava...

متن کامل

Ensemble Universum SVM Learning for Multimodal Classification of Alzheimer's Disease

Recently, machine learning methods (e.g., support vector machine (SVM)) have received increasing attentions in neuroimaging-based Alzheimer’s disease (AD) classification studies. For classifying AD patients from normal controls (NC), standard SVM trains a classification model from only AD and NC subjects. However, in practice besides AD and NC subjects, there may also exist other subjects such ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Knowledge Based Systems

سال: 2022

ISSN: ['1872-7409', '0950-7051']

DOI: https://doi.org/10.1016/j.knosys.2022.108578