A fuzzy extractor (FE), proposed for deriving cryptographic keys from biometric data, enables reproducible generation of high-quality randomness from noisy inputs having sufficient min-entropy. FEs rely in their operation on a public “helper string” that is guaranteed not to leak too much information about the original input. Unfortunately, this guarantee may not hold when multiple independent ...

Coronavirus often called COVID-19 is a deadly viral disease that causes as result of severe acute respiratory syndrome coronavirus-2 needs to be identified especially at its early stages, and failure which can lead the further spread virus. Despite with huge success recorded towards use original convolutional neural networks (CNN) deep learning models. However, their architecture modified desig...

Powered by new advances in sensor development and artificial intelligence, the decreasing cost of computation, pervasiveness handheld computation devices, biometric user authentication (and identification) is rapidly becoming ubiquitous. Modern approaches to authentication, based on sophisticated machine learning techniques, cannot avoid storing either trained-classifier details or explicit dat...

This position paper proposes an interactive approach for developing information extractors based on the ontology definition process with knowledge about possible (in)correctness of annotations. We discuss the problem of managing and manipulating probabilistic dependencies.

A declarative constraint-violation checker and message generator can ease both administrator constraint specification and user adjudication. A prototype implementation of “sanity checks” in the context of an ensemble of automated information extractors illustrates its usefulness.

The problem of noisy and unbalanced training data for supervised keyphrase extraction results from the subjectivity of keyphrase assignment, which we quantify by crowdsourcing keyphrases for news and fashion magazine articles with many annotators per document. We show that annotators exhibit substantial disagreement, meaning that single annotator data could lead to very different training sets ...

Past work in computational sarcasm deals primarily with sarcasm detection. In this paper, we introduce a novel, related problem: sarcasm target identification (i.e., extracting the target of ridicule in a sarcastic sentence). We present an introductory approach for sarcasm target identification. Our approach employs two types of extractors: one based on rules, and another consisting of a statis...

In this paper, we present NERD, an evaluation framework we have developed that records and analyzes ratings of Named Entity (NE) extraction and disambiguation tools working on English plain text articles performed by human beings. NERD enables the comparison of different popular Linked Data entity extractors which expose APIs such as AlchemyAPI, DBPedia Spotlight, Extractiv, OpenCalais and Zema...

The main contributions of the thesis are two novel approaches for the increase of securing of biometric systems based on fingerprint recognition. The first approach is within the liveness detection and prevents the use of various fake fingers and other spoofing techniques during the capturing processes. This patented approach is based on a combination of change of papillary line color and width...

Acoustic models of an HMM-based classifier include various types of hidden factors such as speaker-specific characteristics and acoustic environments. If there exist a canonicalization process that represses the decrease of differences in acoustic-likelihood among categories resulted from hidden factors, a robust ASR system can be realized. We have previously proposed the canonicalization proce...