Most semi-supervised learning algorithms have been designed for binary classification, and are extended to multi-class classification by approaches such as one-against-the-rest. The main shortcoming of these approaches is that they are unable to exploit the fact that each example is only assigned to one class. Additional problems with extending semisupervised binary classifiers to multi-class p...

Due to myriads of classes, designing accurate and efficient classifiers becomes very challenging for multi-class classification. Recent research has shown that class structure learning can greatly facilitate multi-class learning. In this paper, we propose a novel method to learn the class structure for multi-class classification problems. The class structure is assumed to be a binary hierarchic...

There has been a lot of research targeting text classification. Many of them focus on a particular characteristic of text data multi-labelity. This arises due to the fact that a document may be associated with multiple classes at the same time. The consequence of such a characteristic is the low performance of traditional binary or multi-class classification techniques on multi-label text data....

In this work, we developed classifiers to distinguish between four ovarian tumor types using Bayesian least squares support vector machines (LS-SVMs) and kernel logistic regression. Input selection using rank-one updates for LS-SVMs performed better than automatic relevance determination. Evaluation on an independent test set showed good performance of the classifiers to distinguish between all...

An approach to build a multi-class classifier is proposed in this paper. This approach consists of a derivation to show under which loss function an optimal classifier can be obtained. It also consists of a method of selection of principal components for multi-class classification through univariate logistic regressions. And it consists of a derivation of certain derivatives to rank the feature...

Multi-class Gaussian Process Classifiers (MGPCs) are often affected by overfitting problems when labeling errors occur far from the decision boundaries. To prevent this, we investigate a robust MGPC (RMGPC) which considers labeling errors independently of their distance to the decision boundaries. Expectation propagation is used for approximate inference. Experiments with several datasets in wh...

This paper deals with the problem of multi-class classification in machine learning. Various techniques have been successfully proposed to solve such problems, with a computation cost often much higher than techniques dedicated to binary classification. To address this problem, we propose a novel formulation for designing multi-class classifiers, with essentially the same computational complexi...

When a digital forensics investigator suspects that steganography has been used to hide data in an image, he must not only determine that the image contains embedded information but also identify the method used for embedding. The determination of the embedding method – or stego fingerprint – is critical to extracting the hidden information. This paper focuses on identifying stego fingerprints ...