A fast automated biometric solution has been proposed to satisfy the future border control needs of airports resulting from rapid growth in number passengers worldwide. Automated (ABC) systems handle problems caused by this growth, such as congestion at electronic gates (e-gates) or delays planned arrival schedules. Different modalities, face, fingerprint, iris recognition, will be used most ABC located European/Schengen areas. Because facial recognition is modality that travelers consider...

Early in 2020, an unexpected and hazardous situation occurred threatening challenging all of humankind. A new coronavirus called SARS-CoV-2 was first identified Wuhan, China, its related disease, COVID-19, has induced one the most dangerous crises at a global level since World War II. The ultra-fast transmission rate virus high mortality led Health Organization (WHO) to officially declare pandemic. Governments, for their part, were forced implement unprecedented mobility restrictions cease...

Image captioning has become an essential Vision & Language research task. It is about predicting the most accurate caption given a specific image or video. The community achieved impressive results by continuously proposing new models and approaches to improve overall model's performance. Nevertheless, despite increasing proposals, performance metrics used measure their advances have remained practically untouched through years. A probe of that, nowadays like BLEU, METEOR, CIDEr, ROUGE are...

Microblogging social networks are easily subverted by automated fake identities that amass disproportionately large influence. In this paper we present an effort to profile and screen such kind of accounts from existing original ground truth obtained the Twitter platform. Seventy-one explanatory properties solely extracted timeline information evaluated used compare efficacy common supervised machine learning methods at classification task. Results confirm feasible largely effective...

Solar resource assessment is fundamental to reduce the risk in selecting solar power-plants’ location; also for designing appropriate solar-energy conversion technology and operating new sources of solar-power generation. Having a reliable methodology irradiance forecasting allows accurately identifying variations plant energy production and, as consequence, determining improvements supply strategies. A trend based on analysis sky dynamics by processing set images dome. In this paper, dome...

In this paper, a novel method (HoGG) for human detection in non-controlled surveillance environments based on Gabor filters and Histograms of Oriented Gradients is proposed. Complete performance results several alternative algorithms are presented. order to evaluate these methods situations, set standard video databases (PETS 2006, PETS 2007, 2009 CAVIAR) as well the classical (in people area) INRIA database used. An exhaustive test design has been built two complementary evaluations: an...

This paper describes the system used in SemEval-2017 Task 4 (Subtask A): Message Polarity Classification for both English and Arabic languages. Our proposed is an ensemble of two layers, first one uses our generic framework multilingual polarity classification (B4MSA) second layer combines all decision function values predicted by B4MSA systems using a non-linear evolved Genetic Programming system, EvoDAG. With this approach, best performances reached were macro-recall 0.68 (English) 0.477...

Sentiment analysis (SA) is a task related to understanding people's feelings in written text; the starting point would be identify polarity level (positive, neutral or negative) of given text, moving on emotions whether text humorous not. This has been subject several research competitions number languages, e.g., English, Spanish, and Arabic, among others. In this contribution, we propose an SA system, namely EvoMSA, that unifies our participating systems various competitions, making it...

A novel method for person identification based on soft-biometrics and oriented to work in real video surveillance environments is proposed this paper. Thus, an evaluation of relevance's level several appearance features carried out with purpose. First, a bag-of-soft-biometric related color, texture, local features, geometry are extracted from individuals. The relevance each feature has been deeply analyzed through different methods. Features ranked weighted according their value. Later,...

The growing interest in the use of clean energy has led to construction increasingly large photovoltaic systems. Consequently, monitoring proper functioning these systems become a highly relevant issue.In this paper, automatic detection, and analysis modules are proposed. To perform analysis, module identification step, based on digital image processing algorithm, is first carried out. This algorithm consists enhancement (contrast enhancement, noise reduction, etc.), followed by segmentation...