Open-world classification requires a classifier not only to classify samples of the observed classes but also to detect samples which are not suitable to be classified as the known classes. State-of-the-art methods train a feature extractor to ...

Convolutional neural networks (CNNs) are widely used in many natural language processing tasks, which employ some convolutional filters to capture useful semantic features of a text. However, a small window size convolutional filter is short of ...

Learning-based classifiers are found to be susceptible to adversarial examples. Recent studies suggested that ensemble classifiers tend to be more robust than single classifiers against evasion attacks. In this paper, we argue that this is not ...

Semantic interoperability between disparate systems in open, distributed environments has become the quest of many practitioners in a variety of fields. One way to achieve such a goal is through ontology mapping. The perspective users of such technology,...

Automated techniques and tools are required to effectively locate services that fulfill a given user request in a mobility context. To this purpose, the use of semantic descriptions of services has been widely motivated and recommended for automated ...

Data mining is one of the most important areas in the 21 century for its applications are wide ranging. This includes medicine, finance, commerce and engineering, to name a few. Pattern mining is amongst the most important and challenging techniques ...

XML has emerged as the language for exchanging data on the web and has attracted considerable interest both in industry and in academia. Nevertheless, to date, little is known about the XML documents published on the web. This paper presents a ...

The phenomenal growth of online Flash movies in recent years has made Flash one of the most prevalent media formats on the Web. The retrieval and management issues of Flash, vital to the utilization of the enormous Flash resource, are unfortunately ...

The World Wide Web provides a vast resource to genomics researchers, with Web-based access to distributed data sources such as BLAST sequence homology search interfaces. However, finding the desired scientific information can still be very tedious and ...