Deep learning can be an effective and efficient means to automatically detect and classify targets in synthetic aperture radar (SAR) images, but it is critical for trained neural networks to be robust to variations that exist between training and test environments. The layers in a neural network can be understood to be successive transformations of an input image into embedded feature represent...

To represent a text as a bag of properly identified “phrases” and use the representation for processing the text is proved to be useful. The key question here is how to identify the phrases and represent them. The traditional method of utilizing n-grams can be regarded as an approximation of the approach. Such a method can suffer from data sparsity, however, particularly when the length of n-gr...

Topic identification as a specific case of text classification is one of the primary steps toward knowledge extraction from the raw textual data. In such tasks, words are dealt with as a set of features. Due to high dimensionality and sparseness of feature vector result from traditional feature selection methods, most of the proposed text classification methods for this purpose lack performance...

To represent a text as a bag of properly identified “phrases” and use the representation for processing the text is proved to be useful. The key question here is how to identify the phrases and represent them. The traditional method of utilizing n-grams can be regarded as an approximation of the approach. Such a method can suffer from data sparsity, however, particularly when the length of n-gr...

Clinical Named Entity Recognition (NER) is a critical task for extracting important patient information from clinical text to support clinical and translational research. This study explored the neural word embeddings derived from a large unlabeled clinical corpus for clinical NER. We systematically compared two neural word embedding algorithms and three different strategies for deriving distri...

Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Processing and Information Retrieval. We introduce a model that is able to represent the meaning of documents by embedding them in a low dimensional vector space, while preserving distinctions of word and sentence order crucial for capturing nuanced...

Digital images can be copied without authorization and have to be protected. Two schemes for watermarking images in PDF document were considered. Both schemes include a converter to extract images from PDF pages and return the protected images back. Frequency and spatial domain embedding were used for hiding a message presented by a binary pattern. We considered visible and invisible watermarki...

Multi-label document classification is a challenge task in many real-world applications. Recently, hierarchical classification methods have been widely used in document classification. However, at each layer of the hierarchical architecture, a classifier is trained independently, ignoring the relations between the other layers. In addition, compared with general documents, the biomedical litera...

This work provides to web users copyright protection of their Portable Document Format (PDF) documents by proposing efficient and easily implementable techniques for PDF watermarking; our techniques are based on the ideas of our recently proposed watermarking techniques for software, image, and audio, expanding thus the digital objects that can be efficiently watermarked through the use of self...

In respect to the issues on privacy, security and legal significance of a document, some sorts of security protections should be put on a document to ensure its genuineness and integrity. In this research, signatories’ encrypted digital biometric fingerprint in binary format will be embedded into a binary text document by Flipping – one of the methods in spatial domain. During the embedding pro...