In one-class classification, one class of data, called the target class, has to be distinguished from the rest of the feature space. It is assumed that only examples of the target class are available. This classifier has to be constructed such that objects not originating from the target set, by definition outlier objects, are not classified as target objects. In previous research the support v...

The purpose of this note is to show that some of the recent results of Mariño, Moore, and Peradze [18], [17] can be understood in a simple and direct way via a mechanism pointed out in [7], [4], using the PU(2)-monopole cobordism of Pidstrigach and Tyurin [21]. Throughout this paper, let X denote an oriented smooth four-manifold with b2 (X) > 1 and with b1(X) = 0. Once an orientation of H2 +(X)...

Project co-funded by the European Commission within the 7th Framework Programme Dissemination Level PU Public X PP Restricted to other programme participants (including the Commission services) RE Restricted to a group specified by the consortium (including the Commission services) CO Confidential, only for members of the consortium (including the Commission services) The information in this do...

Support vector data description (SVDD) is a well-known kernel method that constructs a minimal hypersphere regarded as a data description for a given data set. However SVDD does not take into account any statistical distribution of the data set in constructing that optimal hypersphere, and SVDD is applied to solving one-class classification problems only. This paper proposes a new approach to S...

In PU learning, a binary classifier is trained from positive (P) and unlabeled (U) data without negative (N) data. Although N data is missing, it sometimes outperforms PN learning (i.e., ordinary supervised learning). Hitherto, neither theoretical nor experimental analysis has been given to explain this phenomenon. In this paper, we theoretically compare PU (and NU) learning against PN learning...

More and more product information, including advertisements and user reviews, are presented to Internet users nowadays. Some of the information is false, misleading or overstated, which can cause seriousness and needs to be identified. Authorities, advertisers, website owners and consumers all have the needs to detect such statements. In this paper, we propose a False Advertisements Recognition...

In PU learning, a binary classifier is trained from positive (P) and unlabeled (U) data without negative (N) data. Although N data is missing, it sometimes outperforms PN learning (i.e., ordinary supervised learning). Hitherto, neither theoretical nor experimental analysis has been given to explain this phenomenon. In this paper, we theoretically compare PU (and NU) learning against PN learning...

Advances in remote sensing (RS) technology recent years have increased the interest including RS data into one-class classifiers (OCCs). However, this integration is complex given interdisciplinary issues involved. In context, review highlights advances and current challenges integrating OCCs to map vegetation classes. A systematic was performed for period 2013–2020. total of 136 articles were ...