Showing papers by "Miguel Ferrer published in 2015"

Static Signature Synthesis: A Neuromotor Inspired Approach for Biometrics

Abstract: In this paper we propose a new method for generating synthetic handwritten signature images for biometric applications. The procedures we introduce imitate the mechanism of motor equivalence which divides human handwriting into two steps: the working out of an effector independent action plan and its execution via the corresponding neuromuscular path. The action plan is represented as a trajectory on a spatial grid. This contains both the signature text and its flourish, if there is one. The neuromuscular path is simulated by applying a kinematic Kaiser filter to the trajectory plan. The length of the filter depends on the pen speed which is generated using a scalar version of the sigma lognormal model. An ink deposition model, applied pixel by pixel to the pen trajectory, provides realistic static signature images. The lexical and morphological properties of the synthesized signatures as well as the range of the synthesis parameters have been estimated from real databases of real signatures such as the MCYT Off-line and the GPDS960GraySignature corpuses. The performance experiments show that by tuning only four parameters it is possible to generate synthetic identities with different stability and forgers with different skills. Therefore it is possible to create datasets of synthetic signatures with a performance similar to databases of real signatures. Moreover, we can customize the created dataset to produce skilled forgeries or simple forgeries which are easier to detect, depending on what the researcher needs. Perceptual evaluation gives an average confusion of 44.06 percent between real and synthetic signatures which shows the realism of the synthetic ones. The utility of the synthesized signatures is demonstrated by studying the influence of the pen type and number of users on an automatic signature verifier.

Effects of human presence on the long-term trends of migrant and resident shorebirds: Evidence of local population declines

Abstract: This study examines the responses to human presence of the most abundant shorebird species in an important coastal migration staging area (Los Lances Beach, southern Spain). Long-term census data were used to assess the relationship between bird abundances and human densities and to determine population trends. In addition, changes in individual bird behaviour in relation to human presence were evaluated by direct observation of a shorebird resident species. Our results show that a rapid increase in the recreational use of the study area in summer has dramatically reduced the number of shorebirds and gulls which occur, limiting the capacity of the site as a post-breeding stop-over area. In addition, the presence of people at the beach significantly reduced the time that resident species spent consuming prey. Negative effects of human presence on bird abundance remain constant over the study period, showing no habituation to human disturbance in any of the studied species. Moreover, although intense human disturbance at Los Lances Beach occurs mainly in summer, the human presence observed is sufficient to have a negative impact on the long-term trends of a resident shorebird species. The impacts of disturbance detected on shorebirds and gulls may be reversible through management actions that decrease human presence. We suggest a minimum distance of 80 m for any track or walkway from those areas where shorebirds are usually present, particularly during spring and summer, as well as an appropriate fencing in the most sensitive area.

Robust score normalization for DTW-based on-line signature verification

Abstract: In the field of automatic signature verification, a major challenge for statistical analysis and pattern recognition is the small number of reference signatures per user. Score normalization, in particular, is challenged by the lack of information about intra-user variability. In this paper, we analyze several approaches to score normalization for dynamic time warping and propose a new two-stage normalization which detects simple forgeries in a first stage and copes with more skilled forgeries in a second stage. An experimental evaluation is conducted on two data sets with different characteristics, namely the MCYT online signature corpus, which contains over three hundred users, and the SUSIG visual sub-corpus, which contains highly skilled forgeries. The results demonstrate that score normalization is a key component for signature verification and that the proposed two-stage normalization achieves some of the best results on these difficult data sets both for random and for skilled forgeries.

Sibling aggression and brood reduction: a review

Abstract: Siblicide may be “facultative” or “obligate”. When food resources provided by the parents are insufficient to rear a whole litter successfully, dominants may kill their subordinate siblings, either directly by physical damage, or indirectly through enforced starvation. This phenomenon is termed “facultative siblicide” and occurs in a wide range of bird species and at least one mammalian species. In contrast, when the lowest ranking sibling is routinely killed by its dominant brood mate or littermate this is called “obligate siblicide”, and seems to affect in particular large, long-lived species characterized by intense competition for breeding sites. This “obligate siblicide” has intrigued researchers for decades, trying to find an evolutionarily satisfactory explanation for this extreme behaviour. We review all scientific literature concerning sibling aggression published in the last 66 years. A bibliography search resulted in 104 references during the last 66 years, where birds represented 88% of the to...

Towards an automatic on-line signature verifier using only one reference per signer

Abstract: What can be done with only one enrolled real hand-written signature in Automatic Signature Verification (ASV)? Using 5 or 10 signatures for training is the most common case to evaluate ASV. In the scarcely addressed case of only one available signature for training, we propose to use modified duplicates. Our novel technique relies on a fully neuromuscular representation of the signatures based on the Kinematic Theory of rapid human movements and its Sigma-Lognormal model. This way, a real on-line signature is converted into the Sigma-Lognormal model domain. The model parameters are then varied to generate new duplicated signatures.

A Survey on Traffic Light Detection

Abstract: Traffic light detection is an important matter in urban environments during the transition to fully autonomous driving. Many literature has been generated in the recent years approaching different pattern recognition strategies. In this paper we present a survey summarizing relevant works in the field of detection of both suspended and supported traffic light. This survey organizes different methods highlighting main reasearch areas in the computer vision field.

Early Diagnosis of Neurodegenerative Diseases by Handwritten Signature Analysis

Abstract: Handwritten signatures are generally considered a powerful biometric traits for personal verification. Recently, handwritten signatures have been also investigated for early diagnosis of neurodegenerative diseases. This paper presents a new approach for early diagnosis of neurodegenerative diseases by the analysis of handwritten dynamic signatures. For the purpose, the sigma-lognormal model was considered and dynamic parameters are extracted for signatures. Based on these parameters, the health condition of the signer is analysed in terms of Alzheimer disease. The approach is cheap and effective, therefore it can be considered as a very promising direction for further research.

Endotracheal tube biofilm translocation in the lateral Trendelenburg position

Abstract: Laboratory studies demonstrated that the lateral Trendelenburg position (LTP) is superior to the semirecumbent position (SRP) in the prevention of ventilator-associated pulmonary infections. We assessed whether the LTP could also prevent pulmonary colonization and infections caused by an endotracheal tube (ETT) biofilm. Eighteen pigs were intubated with ETTs colonized by Pseudomonas aeruginosa biofilm. Pigs were positioned in LTP and randomized to be on mechanical ventilatin (MV) up to 24 hour, 48 hour, 48 hour with acute lung injury (ALI) by oleic acid and 72 hour. Bacteriologic and microscopy studies confirmed presence of biofilm within the ETT. Upon autopsy, samples from the proximal and distal airways were excised for P.aeruginosa quantification. Ventilator-associated tracheobronchitis (VAT) was confirmed by bronchial tissue culture ≥3 log colony forming units per gram (cfu/g). In pulmonary lobes with gross findings of pneumonia, ventilator-associated pneumonia (VAP) was confirmed by lung tissue culture ≥3 log cfu/g. P.aeruginosa colonized the internal lumen of 16 out of 18 ETTs (88.89%), and a mature biofilm was consistently present. P.aeruginosa colonization did not differ among groups, and was found in 23.6% of samples from the proximal airways, and in 7.1% from the distal bronchi (P = 0.001). Animals of the 24 hour group never developed respiratory infections, whereas 20%, 60% and 25% of the animals in group 48 hour, 48 hour-ALI and 72 hour developed P.aeruginosa VAT, respectively (P = 0.327). Nevertheless, VAP never developed. Our findings imply that during the course of invasive MV up to 72 hour, an ETT P.aeruginosa biofilm hastily colonizes the respiratory tract. Yet, the LTP compartmentalizes colonization and infection within the proximal airways and VAP never develops.

Modeling the lexical morphology of Western handwritten signatures.

Abstract: A handwritten signature is the final response to a complex cognitive and neuromuscular process which is the result of the learning process. Because of the many factors involved in signing, it is possible to study the signature from many points of view: graphologists, forensic experts, neurologists and computer vision experts have all examined them. Researchers study written signatures for psychiatric, penal, health and automatic verification purposes. As a potentially useful, multi-purpose study, this paper is focused on the lexical morphology of handwritten signatures. This we understand to mean the identification, analysis, and description of the signature structures of a given signer. In this work we analyze different public datasets involving 1533 signers from different Western geographical areas. Some relevant characteristics of signature lexical morphology have been selected, examined in terms of their probability distribution functions and modeled through a General Extreme Value distribution. This study suggests some useful models for multi-disciplinary sciences which depend on handwriting signatures.

Floater interference reflects territory quality in the Spanish Imperial Eagle Aquila adalberti: a test of a density‐dependent mechanism

Abstract: We report on an 11–year study of floater interference in a population of Spanish Imperial Eagles Aquila adalberti. We analyzed changes over the years in the productivity of 15 territories to test predictions of two hypotheses of density-dependent productivity in relation to the presence of floaters (birds without territories). According to the ‘interference’ hypothesis, the frequency of intrusion by floaters increases with density, resulting in a decrease in productivity. Thus, in a high-density population a negative relationship between floater intrusions and productivity of the territory is expected. In contrast, under the ‘habitat heterogeneity’ hypothesis, as density increases a higher proportion of individuals is forced to occupy lower quality habitats. Support of this hypothesis requires that floaters detect differences in quality among territories and preferentially visit the better quality territories. Consequently, a positive relationship between floater intrusions and productivity is expected. Results showed that floaters tended to visit their natal area at the beginning of the breeding season. Among floater eagles, males made significantly more intrusions per day than did females, but females stayed in the natal population for longer each year than males. Floater intrusions and productivity were highly positively correlated, supporting the ‘habitat heterogeneity’ hypothesis; individuals were apparently able to assess the quality of a territory and, at the frequencies observed, their interference with the breeding pair had no obvious negative effect on productivity.

FCGR polymorphisms in the treatment of rheumatoid arthritis with Fc-containing TNF inhibitors.

Abstract: Objectives: Reproducible association of a functional polymorphism in FCGR2A with response to a TNF inhibitor (TNFi) in patients with rheumatoid arthritis (RA) led us to explore other FcγR functional polymorphisms. Methods: Functional polymorphisms FCGR3A F158V, FCGR2B I223T and promoter VNTR in FCGRT were analyzed in up to 429 patients with RA. Response to TNFi was recorded during standard care at 3, 6 and 12 months of follow-up. Fixed effects meta-analysis of studies addressing FCGR3A F158V polymorphism, which is the most studied of these polymorphisms, was conducted with inverse variance weighting. Results: None of the functional polymorphisms were associated with change in DAS28. Meta-analysis of the seven studies (899 patients) with available data addressing association of FCGR3A F158V with response to TNFi in RA showed no association (OR: 1.11, 95% CI: 0.8–1.5; p = 0.5). Conclusion: None of the three functional polymorphisms in FcγR genes showed association with response to TNFi in patients with RA. ...

Earprint recognition based on an ensemble of global and local features

Abstract: The earmarks are usual evidences in many real criminal investigations. The earprint appears for example when a criminal tries to listen through a window or a door before entering, and the methods to make it visible are similar to those used in latent fingerprint lifting. However, its acceptance as evidence in real prosecutions still raises doubts. Although it is well-accepted the uniqueness of the ear and its usefulness for person identification, the permanence of such discriminate ability in earprints is not obvious. Although the earprints do not have a powerful distinctiveness information, they are useful in a bag of evidences, being a promising soft biometric. This paper explores the discriminant properties of local descriptors for earprint-based automatic biometric recognition systems. The literature has focused on automatic systems based on the global aspect of the images, however scarcely studies have coped with in the well-known discriminate ability of earprint local characteristics. The experiments using more than 6000 images from 1200 people suggest a promising performance in comparison with previous existing proposals based on global features and encourage to further explore in this new soft biometric traits.

Genetic variants within the TNFRSF1B gene and susceptibility to rheumatoid arthritis and response to anti-TNF drugs: a multicenter study.

Abstract: BACKGROUND Recent research suggests that genetic variants in the tumor necrosis factor receptor 2 (TNFRSF1B) gene may have an impact on susceptibility to rheumatoid arthritis (RA) and drug response. The present population-based case-control study was carried out to evaluate whether 5 tagging single-nucleotide polymorphisms (SNPs) within the TNFRSF1B gene are associated with the risk of RA and response to antitumor necrosis factor (TNF) drugs. METHODS The study population included 1412 RA patients and 1225 healthy controls. A subset of 596 anti-TNF-naive RA patients was selected to assess the association of TNFRSF1B SNPs and drug response according to the EULAR response criteria. RESULTS We found that carriers of the TNFRSF1Brs3397C allele had a significantly increased risk of developing RA (P=0.0006). Importantly, this association remained significant after correction for multiple testing. We also confirmed the lack of association of the TNFRSF1Brs1061622 SNP with the risk of RA in the single-SNP analysis (P=0.89), but also through well-powered meta-analyses (PDOM=0.67 and PREC=0.37, respectively). In addition, our study showed that carriers of the TNFRSF1Brs3397C/C, TNFRSF1Brs1061622G/G, and TNFRSF1Brs1061631A/A genotypes had an increased risk of having a worse response to anti-TNF drugs at the level of P less than 0.05 (P=0.014, 0.0085 and 0.028, respectively). We also observed that, according to a log-additive model, carriers of the TNFRSF1Brs3397C or TNFRSF1Brs1061622G alleles showed an increased risk of having worse response to anti-TNF medications (P=0.018 and 0.0059). However, the association of the TNFRSF1Brs1061622 SNP only reached marginal significance after correction for multiple testing according to a log-additive model (P=0.0059) and it was not confirmed through a meta-analysis (PDOM=0.12). CONCLUSION Our results suggest that the TNFRSF1Brs3397 variant may play a role in modulating the risk of RA, but does not provide strong evidence of an impact of TNFRSF1B variants in determining response to anti-TNF drugs.

Genetic variants within immune-modulating genes influence the risk of developing rheumatoid arthritis and anti-TNF drug response: a two-stage case-control study.

Abstract: Background Rheumatoid arthritis (RA) is a chronic autoimmune disease that arises as a result of the interaction between genetic and environmental factors. A growing body of research suggests that genetic variants within immune-related genes can influence the risk of developing the disease and affect drug response. Materials and methods To test this hypothesis, we carried out a comprehensive two-stage case–control study in a White population of 1239 White RA patients and 1229 healthy controls to investigate whether 49 single nucleotide polymorphisms within or near 17 immune-related genes modulate the risk of developing RA and antitumor necrosis factor (anti-TNF) drug response. Results Logistic regression analyses showed that carriers of the IL4rs2070874T and IL4rs2243250T and IL8RBrs1126580A alleles or the IL8RBrs2230054C/C genotype had a significantly increased risk of developing RA [odds ratio (OR)=1.37, 95% confidence interval (CI) 1.13–1.67, P=0.0016; OR=1.24, 95% CI 1.03–1.49, P=0.020; OR=1.23, 95% CI 1.08–1.41, P=0.002 and OR=1.19, 95% CI 1.04–1.36, P=0.01, respectively]. The association of the IL4 variants was further supported by a meta-analysis including 7150 individuals (P =0.0010), whereas the involvement of the IL8RB locus in determining the susceptibility to RA was also supported by gene–gene interaction analyses that identified significant two-locus and three-locus interaction models including IL8RB variants that act synergistically to increase the risk of the disease (P=0.014 and 0.018). Interestingly, we also found that patients harbouring the IFNGrs2069705C allele showed a significantly better response to anti-TNF drugs than those patients carrying the wild-type allele (P=0.0075). Conclusions Our data suggest that IL4 and IL8RB loci may have a small-effect genetic impact on the risk of developing RA, whereas IFNG might be involved in modulating the response to anti-TNF drugs.

Disentangling the effect of parental care, food supply, and offspring decisions on the duration of the postfledging period

Abstract: The postfledging dependence period (PFDP) is a crucial stage in the development of altricial birds. This period is regulated by parental investment, in terms of food provisioning and protection, and the demands of young associated with their development and physical condition. We examine the relative role of parental investment, food provisioning, and offspring decisions on the PFDP regulation in the Spanish imperial eagle (Aquila adalberti) by comparing the PFDP timing among young from non-manipulated territories, food supplemented territories, and birds translocated by hacking methods in the absence of adults and with ad libitum food supply. We found that extra food homogenized the nutritional condition of young and reduced the length of the first stage of PFDP, which is related to flight development and thus dependent on body condition. However, hacked birds did not reduce this stage despite ad libitum food, likely due to the lack of parental stimulus to develop advanced flights. Although the presence of adults might accelerate young becoming independent, hacked birds did not extend significantly the whole PFDP and all birds eventually started dispersal. Thereby, the PFDP regulation was primarily under offspring control, and modulated secondarily by parental effects independently of food provisioning and laying date. The length of this period seems to be constrained mainly by the inherent benefits of early dispersal on ultimate fitness in accordance with ontogenic hypotheses. In addition, hacking was shown to be an effective translocation method when properly used, without negative drawbacks for young development during the PFDP.

Temporally variable environments maintain more beta-diversity in Mediterranean landscapes

Abstract: We examined the relationships between different environmental factors and the alpha and beta-diversity of terrestrial vertebrates (birds, mammals, amphibians and reptiles) in a Mediterranean region at the landscape level. We investigated whether the mechanisms underlying alpha and beta-diversity patterns are influenced by energy availability, habitat heterogeneity and temporal variability and if the drivers of the diversity patterns differed between both components of diversity. We defined alpha-diversity as synonym of species richness whereas beta-diversity was measured as distinctiveness. We evaluated a total of 13 different predictors using generalized linear mixed model (GLMM) analysis. Habitat spatial heterogeneity increased alpha-diversity, but contrastingly, it did not significantly affect beta-diversity among sites. Disturbed landscapes may show higher habitat spatial variation and higher alpha-diversity due to the contribution of highly generalist species that are wide-distributed and do not differ in composition (beta-diversity) among different sites within the region. Contrastingly, higher beta-diversity levels were negatively related to more stable sites in terms of temporal environmental variation. This negative relationship between environmental stability and beta-diversity levels is explained in terms of species adaptation to the local environmental conditions. Our study highlights the importance of temporal environmental variability in maintaining beta-diversity patterns under highly variable environmental conditions.

Rheumatoid arthritis response to treatment across IgG1 allotype - anti-TNF incompatibility: a case-only study.

Abstract: Introduction We have hypothesized that incompatibility between the G1m genotype of the patient and the G1m1 and G1m17 allotypes carried by infliximab (INX) and adalimumab (ADM) could decrease the efficacy of these anti-tumor necrosis factor (anti-TNF) antibodies in the treatment of rheumatoid arthritis (RA).

Off-line signature stability by optical flow: Feasibility study of predicting the verifier performance

Abstract: Prediction of performance in Off-line Automatic Signature Verification (ASV) per signer is one of the important topics regarding to automatic verification. It could be hypothesized that the performance of a signer is related to its global stability. This way, the more stable the signer signatures, the smaller the area of its feature space is, being more difficult to get inside for an impostor. In this paper we assess the feasibility to predict the performance of a signer through his/her global stability. As in a real scenario, only the enrolled signatures are used to calculate the stability of the signer. Similarly, only these signatures are used to train two completely different off-line ASVs. Then, the performance and the stability per signer are compared. Our results suggest that there is a certain relationship between the global stability of the enrolled signatures and the performance in terms of Equal Error Rate.

Novel method for early bearing fault detection based on dynamic stability measure

Abstract: Early fault detection leads to faster and more effective maintenance, avoiding serious damage in machines and increasing the reliability, security and fault tolerance in industrial scenarios. It is observed that a vibration signal of an onset fault in different parts of the bearing (inner race, outer race and ball) describes certain stable profile among their respective cycles. A methodology to estimate the stability of two dynamic handwriting signatures has been proposed using the Direct Matching Points (DMP) of the elastic align function Dynamic Time Warping (DTW). This methodology is evaluated in this paper and extrapolated to machinery vibration signals affected by an early bearing fault. Results confirm the feasibility to study the stability in both free-fault and fault bearing signals to detect automatically early faults in the bearings by using recorded vibration signals.

An Online Learning-Based Adaptive Biometric System

Abstract: In the last decade, adaptive biometrics has become an emerging field of research. Considering the fact that limited work has been undertaken on adaptive biometrics using machine learning techniques, in this chapter we list and discuss a few out of many potential learning techniques that can be applied to build an adaptive biometric system. In order to illustrate the efficacy of one of the incremental learning techniques from the literature, we built an adaptive biometric system. For experimentation, we have used multi-modal ocular (sclera and iris) data. The preliminary results have been reported in the results section, which are very promising.

Behaviour of dynamic and static feature dependences in constrained signatures

Abstract: In the networked society, in which a multitude of different devices can be used for signature acquisition, specific research is still needed to determine the extent to which features of an input signature depend on the characteristics of the signature acquisition process. In this paper an experimental investigation is carried out on constrained signatures, which were acquired using writing boxes with different areas and shapes. The paper discusses different behaviour of dynamic and static features with respect to the writing boxes.

Emotional states discrimination in voice in secure environments

Abstract: In this paper we present the use of emotions in security. The access control security systems by speech recognition can be complemented by means of an emotions discrimination system from the speech. An emotions recognition system has the advantage of increasing the security allowing identifying if an authorized user in the system is being coerced while he executes speech identification, reflecting his speech some nervousness. In this study we use four emotional states. We use three emotional states that would produce alarm in a security system: anxiety, hot anger and panic. and a fourth emotional state that corresponds to emotions set without interest for the security, like happiness, shame, sadness, boredom or the absence of emotion (neutral), and that we have called rest. In our simulations, the proposed emotions discrimination system has obtained an average accuracy about 79%.