The use of a person's signature is considered as one of the most commonly used biometric methods for recognition, either as a standalone feature or as part of multimodal systems. Based on the inter-writer variability, handwritten signatures have been accepted as a personal trait in many transactions to verify the consent or the author's presence. The main challenges for handwritten signature verification are the limited amount of available data for each writer and the intra-writer variability. Sparse Representation (i.e. dictionary learning and sparse coding) achieved state of the art results at handwritten signature verification, using only a small set of genuine reference samples of the writer. The extension of Sparse Representation to an efficient multi-layer architecture is Deep Sparse Coding. Deep Sparse Coding architecture connects multiple layers of Sparse Representation with a sparse-to-dense module in order to enable Sparse Coding on deeper layers. Learning sparse representations at different levels of abstraction leads to building feature hierarchies. The sparse-to-dense module involves a Dimensionality Reduction process, which was implemented with simple and fast methods, such as Random Orthogonal projection or PCA; instead of the computational expensive DrLIM. The performance of the proposed Deep Sparse Coding architecture to the challenging problem of offline signature verification is demonstrated in the popular CEDAR signature dataset, delivering improved state of the art results.

The concept of diffusional screening implies that breath-to-breath variations in CO₂ clearance, when related to the variability of breathing, may contain information on the quality and utilization of the available alveolar surface. We explored the validity of the above hypothesis in a cohort of young infants of comparable post-menstrual age but born at different stages of lung maturity, namely, in term-born infants (N = 128), preterm-born infants without chronic lung disease of infancy (CLDI) (N = 53) and preterm infants with moderate/severe CLDI (N = 87). Exhaled CO₂ volume (V_E,CO2) and concentration (F_E,CO2) were determined by volumetric capnography, while their variance was assessed by linear and non-linear variability metrics. The relationship between relative breath-to-breath change of V_E,CO2 (ΔV_E,CO2) and the corresponding change of tidal volume (V_T), was also analyzed. Non-linear F_E,CO2 variability was lower in CLDI compared to term and non-CLDI preterm group (P<0.001 for both comparisons). In CLDI infants, most of the V_E,CO2 variability was attributed to the variability of V_T (R² 0.749), while in term and healthy preterm infants this relationship was weaker (R² 0.507 and 0.630, respectively). The Δ_VE,CO2-ΔVT slope was less steep in the CLDI group (1.06 ± 0.07) compared to non-CLDI preterm (1.16 ± 0.07; P <0.001) and term infants (1.20 ± 0.10; P <0.001), suggesting that the more dysmature the infant lung the less efficiently it eliminates CO₂ under tidal breathing conditions. We conclude that the temporal variation of CO₂ clearance may be related to the degree of lung dysmaturity in early infancy.

Background: Variability analysis of peak expiratory flow (PEF) and forced expiratory volume at 1 second (FEV1) has been used in research to predict exacerbations in adults with asthma. However, there is a paucity of data regarding PEF and FEV1 variability in healthy children and adolescents and those with asthma. Objective: The objective of this study is the assessment of PEF and FEV1 variability in (1) healthy children and adolescents, to define the normal daily fluctuation of PEF and FEV1 and the parameters that may influence it, and (2) children and adolescents with asthma, to explore the differences from healthy subjects and reveal any specific variability changes prior to exacerbation. Methods: The study will include 100 healthy children and adolescents aged 6-18 years (assessment of normal PEF and FEV1 variability) and 100 children and adolescents of the same age with diagnosed asthma (assessment of PEF and FEV1 variability in subjects with asthma). PEF and FEV1 measurements will be performed using an ultraportable spirometer (Spirobank Smart; MIR Medical International Research) capable of smartphone connection. Measurements will be performed twice a day between 7 AM and 9 AM and between 7 PM and 9 PM and will be dispatched via email to a central database for a period of 3 months. PEF and FEV1 variability will be assessed by detrended fluctuation and sample entropy analysis, aiming to define the normal pattern (healthy controls) and to detect and quantify any deviations among individuals with asthma. The anticipated duration of the study is 24 months. Results: The study is funded by the “C. Caratheodory” Programme of the University of Patras, Greece (PN 47014/24.9.2018). It was approved by the Ethics Committee (decision 218/19-03-2019) and the Scientific Board (decision 329/02-04-2019) of the University Hospital of Patras, Greece. Patient recruitment started in January 2020, and as of June 2020, 100 healthy children have been enrolled (74 of them have completed the measurements). The anticipated duration of the study is 24 months. The first part of the study (assessment of lung function variability in healthy children and adolescents) will be completed in August 2020, and the results will be available for publication by October 2020. Conclusions: Healthy children and adolescents may present normal short- and long-term fluctuations in lung function; the pattern of this variability may be influenced by age, sex, and environmental conditions. Significant lung function variability may also be present in children and adolescents with asthma, but the patterns may differ from those observed in healthy children and adolescents. Such data would improve our understanding regarding the chronobiology of asthma and permit the development of integrated tools for assessing the level of control and risk of future exacerbations. Trial Registration: ClinicalTrials.gov NCT04163146; https://clinicaltrials.gov/ct2/show/NCT04163146 International Registered Report Identifier (IRRID): DERR1-10.2196/20350