Search

The dense mechanoreceptors in human fingertips enable texture discrimination. Recent advances in flexible electronics have created tactile sensors that effectively replicate slowly adapting (SA) and rapidly adapting (RA) mechanoreceptors. However, the influence of dermatoglyphic structures on tactile signal transmission, such as the effect of fingerprint ridge filtering on friction-induced vibration frequencies, remains unexplored. A novel multi-layer flexible sensor with an artificially synthesized skin surface capable of replicating arbitrary fingerprints is developed. This sensor simultaneously detects pressure (SA response) and vibration (RA response), enabling texture recognition. Fingerprint ridge patterns from notable historical figures - Rosa Parks, Richard Nixon, Martin Luther King Jr., and Ronald Reagan - are fabricated on the sensor surface. Vibration frequency responses to assorted fabric textures are measured and compared between fingerprint replicas. Results demonstrate that fingerprint topography substantially impacts skin-surface vibrational transmission. Specifically, Parks fingerprint structure conveyed higher frequencies more clearly than those of Nixon, King, or Reagan. This work suggests individual fingerprint ridge morphological variation influences tactile perception and can confer adaptive advantages for fine texture discrimination. The flexible bioinspired sensor provides new insights into human vibrotactile processing by modeling fingerprint-filtered mechanical signals at the finger-object interface.

PURPOSE: To assess the accuracy of intraoperative wavefront aberrometry (IWA) versus modern intraocular lens formulas in post-myopic laser vision correction (LVC) patients undergoing cataract surgery with capsular tension ring placement. METHODS: This is a retrospective chart review conducted at an academic outpatient center. All post-myopic LVC eyes undergoing cataract surgery with IWA from a single surgeon from 05/2017 to 12/2019 were included. All patients received a capsular tension ring (CTR). Mean numerical error (MNE), median numerical error (MedNE), and percentages of prediction error within 0.50D, 0.75D, and 1.00D were calculated for the above formulas. RESULTS: Twenty-seven post-myopic LVC eyes from 18 patients were included. In post-myopic LVC, MNE with Optiwave Refractive Analysis (ORA), Barrett True K (BTK), Haigis, Haigis-L, Shammas, SRK/T, Hill-RBF v3.0, and W-K AL-adjusted Holladay 1 were + 0.224, - 0.094, + 0.193, - 0.231, - 0.372, + 1.013, + 0.860, and + 0.630 (F = 8.49, p

Controlling Type 1 error and encouraging reproducible research are important in clinical and translational research. These concepts are frequently discussed in lectures with mathematical language, analytic examples, and probability distributions that demonstrate the issues. However, first‐time learners in biostatistics courses focusing on fundamental topics may benefit from a more interactive demonstration in which learners participate, contribute to the results, and have a personal stake in the outcomes. This article summarizes a simple activity using dice to simulate Type 1 error that requires minimal preparation and cost. The activity may be appropriate for learners enrolled in a first course in statistics, biostatistics, or probability. [ABSTRACT FROM AUTHOR]

In the domain of Extended Reality (XR), particularly Virtual Reality (VR), extensive research has been devoted to harnessing this transformative technology in various real-world applications. However, a critical challenge that must be addressed before unleashing the full potential of XR in practical scenarios is to ensure robust security and safeguard user privacy. This paper presents a systematic survey of the utility of biometric characteristics applied in the XR environment. To this end, we present a comprehensive overview of the different types of biometric modalities used for authentication and representation of users in a virtual environment. We discuss different biometric vulnerability gateways in general XR systems for the first time in the literature along with taxonomy. A comprehensive discussion on generating and authenticating biometric-based photorealistic avatars in XR environments is presented with a stringent taxonomy. We also discuss the availability of different datasets that are widely employed in evaluating biometric authentication in XR environments together with performance evaluation metrics. Finally, we discuss the open challenges and potential future work that need to be addressed in the field of biometrics in XR. [ABSTRACT FROM AUTHOR]

Recently, multimodal authentication methods based on deep learning have been widely explored in biometrics. Nevertheless, the contradiction between the data privacy protection and the requirement of sufficient data when model optimizing has become increasingly prominent. To this end, we proposes a multimodal biometric federated learning framework (FedMB) to realize the multiparty joint training of identity authentication models with different modal data while protecting the users' data privacy. Specifically, a personalized multimodal biometric recognition model fully trained by each participant is first obtained to improve the authentication performance, using modal point clustering with class‐first federated learning methods on the service side with the modal. Then a complementary multimodal biometric recognition strategy is implemented to build a complementary modal model. Finally, the fusion participant local model, with the modal model and complementary modal model, is trained by all participants again to obtain a more personalized modal model. The experimental results have demonstrated that the proposed FedMB can either protect the data privacy or utilize the data from all participants to train the personalized biometric recognition model to improve identity authentication performance. [ABSTRACT FROM AUTHOR]

This study aimed to investigate the short-term variability of ocular biometric measurements and to analyze the factors associated with high variability of biometric values in patients with cataract. This retrospective study included 60 eyes of 60 patients who underwent ocular biometry twice with the IOLMaster 700 (March to November 2023). Ocular surface parameters included tear film break-up time (TBUT), corneal and conjunctival staining scores (CSS/ConSS). Refractive surprise was defined as a mean absolute error exceeding 0.5 diopter (D). Participants included 22 men and 38 women with a mean age of 70.6 ± 8.4 years. The variability of mean keratometric (K) values and astigmatism showed notable variability compared to axial length (mean K: 0.18 ± 0.17D, astigmatism: 0.21 ± 0.26D, axial length: 0.01 ± 0.01 mm). A decreased TBUT and increased CSS were significantly associated with high variability (≥ 0.25D) of mean K (p = 0.040/0.008). The high K variability group (≥ 0.25D) revealed a significantly higher incidence of refractive surprise (> 0.5D) compared with the low K variability group (< 0.25D) (45.5%/17.9%, p = 0.037). Preoperative lower TBUT and higher CSS influenced the variability of K values in ocular biometry and may be related with postoperative refractive surprise due to erroneous K values. [ABSTRACT FROM AUTHOR]

Background: To evaluate the repeatability and agreement of two different ocular biometers and Scheimpflug devices in keratoconus eyes. Methods: This prospective, comparative trial took place at the University hospital, Goethe University, Frankfurt am Main, Germany. We included eyes with keratoconus, one eye per patient, randomly selected. Measurements were taken with Galilei G6 (Ziemer, Switzerland) and Pentacam AXL (Oculus, Germany), three consecutive measurements each. Repeatability and agreement were evaluated for simulated keratometry (simK), astigmatism (simA), maximum keratometry (KMax) and its axis, total keratometry (TCP), axial length (AL), anterior chamber depth (ACD), and thinnest pachymetry (TCT). Results: Both devices showed an excellent repeatability with intra class correlation (ICC) of > 0.97 for all parameters. The 95% limits of repeatability (LoR95%) and agreement (LoA95%) were narrow for all parameters. The Galilei G6 had a narrower LoAR95% for TCT (2.1 μm vs. 4.6 μm), but a wider LoR95% for KMax (0.52D vs. 1.18D). No relevant difference was found for the other parameters. Agreement between the devices was good to moderate, especially for simK and TCP. Conclusions: Both devices show excellent repeatability with narrow LoR95% and high ICC for all parameters. The only relevant difference was found for KMax and TCT in favor of Pentacam AXL and Galilei G6, respectively. Agreement was good to moderate, and most parameters should not be considered interchangeable. [ABSTRACT FROM AUTHOR]

The bryophyte genus Ulota has its main diversification area in Patagonia, with 18 currently accepted species, all of which are endemic to the area. Despite this richness, ongoing studies indicate the existence of hitherto unknown species in this territory. However, the strong resemblance between species often complicates the discrimination of new taxa, making the use of integrative taxonomy approaches compulsory. During surveys conducted in past decades, a morphotype of a Ulota , closely resembling Ulota macrodontia , was discovered coexisting with this species. Ulota macrodontia is characterized by unique peristomial features within the genus, and the variant morphotype shares these characteristics while displaying some distinct gametophytic and sporophytic features. Biometric analyses demonstrate that the differences are stable, and without intermediate states. The results obtained from the analyses of one nuclear and four plastid loci reveal a close relationship between both morphotypes, with the samples of U. macrodontia forming a well-supported monophyletic group. We propose to treat the new morphotype at species level (Ulota brachypoda sp. nov.), discussing why this is the most appropriate taxonomic rank, and we provide a detailed and illustrated description. Additionally, a distribution map of the two endemics is included. [ABSTRACT FROM AUTHOR]

Background: To assess changes in ocular biometry of the phakic eye after pars‐plana‐vitrectomy (PPV) and silicone oil (SO) endotamponade in eyes with a retinal detachment. Methods: This retrospective, consecutive case series included 72 eyes of 72 patients who underwent PPV with 5000‐centistokes SO endotamponade between July 2018 and June 2023. Pseudophakic eyes and eyes with a combined phacovitrectomy were excluded. Primary endpoints were keratometry values, anterior chamber depth (ACD), lens thickness (LT), horizontal corneal diameter (HCD), and axial length (AL) measured by swept‐source optical coherence tomography‐based biometry (IOLMaster 700) preoperatively and six weeks postoperatively. A recently described formula was used to adjust the AL (aAL) in eyes with SO endotamponade and a theoretical intraocular lens (IOL) calculation was performed. Results: The mean age was 62.1 ± 8.3 years (range: 37–85). After PPV with SO fill, there was an increase in Kmean (0.19 ± 0.51D), while ACD (0.05 ± 0.13 mm), LT (0.03 ± 0.14 mm), and HCD (0.02 ± 0.24 mm) decreased. Preoperatively, the mean AL was 25.22 ± 1.78 mm, while postoperatively the AL was overestimated by 0.12 ± 0.42 mm on average (p = 0.04). By adjusting the AL, the mean difference could be reduced to −0.002 ± 0.41 mm. The aAL resulted in a difference in the refractive outcome in eyes with an AL > 25 mm of 0.34 ± 0.10D in the IOL calculation. Conclusions: While changes in biometry after PPV with SO endotamponade in the anterior segment are clinically less relevant, a considerable overestimation of AL with IOLMaster 700 was found. We recommend the use of a recently introduced formula for adjusting AL in eyes with SO, allowing overestimation to be minimised considerably. [ABSTRACT FROM AUTHOR]

Iris is one of the most widely used biometric modalities because of its uniqueness, high matching performance, and inherently secure nature. Iris segmentation is an essential preliminary step for iris-based biometric authentication. The authentication accuracy is directly connected with the iris segmentation accuracy. In the last few years, deep-learning-based iris segmentation methodologies have increasingly been adopted because of their ability to handle challenging segmentation tasks and their advantages over traditional segmentation techniques. However, the biggest challenge to the biometric community is the scarcity of open-source resources for adoption for application and reproducibility. This review provides a comprehensive examination of available open-source iris segmentation resources, including datasets, algorithms, and tools. In the process, we designed three U-Net and U-Net++ architecture-influenced segmentation algorithms as standard benchmarks, trained them on a large composite dataset (>45K samples), and created 1K manually segmented ground truth masks. Overall, eleven state-of-the-art algorithms were benchmarked against five datasets encompassing multiple sensors, environmental conditions, demography, and illumination. This assessment highlights the strengths, limitations, and practical implications of each method and identifies gaps that future studies should address to improve segmentation accuracy and robustness. To foster future research, all resources developed during this work would be made publicly available. [ABSTRACT FROM AUTHOR]

Background/Objectives: This study's aim was to compare the precision, agreement, and accuracy in axial length (AL) measurements of Argos® (Alcon Healthcare, US) and Eyestar 900® (Haag-Streit, Switzerland) swept-source optical coherence tomography (SS-OCT) biometers. Methods: We performed a prospective evaluation of two diagnostic devices. Three consecutive measurements of AL with the Argos® and the Eyestar® 900 SS-OCT biometers were conducted in random order in eyes undergoing cataract surgery in Barcelona, Spain. The main endpoint was the median difference in AL between devices. Secondary endpoints included agreement on Bland–Altman plots and 95% limits of agreement (LoAs), repeatability as measured within-subject standard deviation (SW), percent of failed AL measurements, percent of eyes within ±0.50 D and ±1.00 D one month after surgery, and median and mean prediction error. Results: We included 107 eyes of 107 patients (60.8% females, mean age of 73.1 years). The median difference in AL (Argos®-Eyestar 900®) was −0.01 mm (interquartile range [IQR], 0.06), p = 0.01. The 95% LoAs were −0.11 to +0.08 mm, with a trend towards less extreme measurements with Argos® for very short and long eyes. The median (IQR) Sw was 0.0058 (0.0058) and 0.0000 (0.0058) for Argos® and Eyestar 900®, respectively. There were no failed AL measurements with either device (0%, 95% CI = 0% to 3.4%). Overall, 96.1% of eyes were within ±0.50 D and 100% were within ±1.00 D. Conclusions: Argos® and Eyestar 900® provided statistically different but clinically negligible differences in AL. However, they are not interchangeable in very long or short eyes, due to the different principles used to determine AL. [ABSTRACT FROM AUTHOR]

This paper proposes a disentangled representation transformer network (DRTN) for 3D dense face alignment and reconstruction. Unlike traditional 3DMM-based approaches, the target parameters, such as shape, expression, and pose, are individually estimated without considering their direct influences on one another and then jointly optimized. Hence, DRTN aims to enhance the representation of facial attributes in a semantic sense by learning the correlation of different 3D facial attribute parameters. To achieve this, we present a novel strategy to design disentangled 3D face attribute representation, which decomposes the given facial attributes into identity, expression, and poses. Specifically, the 3D face parameter estimation in the regression network depends on the correlation of other face attribute parameters rather than being independent. The branching of the identity component aims to reinforce learning the expression and pose attributes by preserving the overall face geometry structure and identity. Accordingly, the expression and pose parts of the branch preserve the consistency of expression and pose attributes, respectively. Moreover, DRTN helps refine the reconstruction and alignment of facial details in large poses, mainly by coupling other facial attribute parameters. Extensive qualitative and quantitative experimental results on widely evaluated benchmarking datasets demonstrate that our approach achieves competitive performance compared to state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Purpose: To estimate the astigmatic power of the crystalline lens and the whole eye without phakometry using a set of linear equations and to provide estimates for the astigmatic powers of the crystalline lens surfaces. Methods: Linear optics expresses astigmatic powers in the form of matrices and uses paraxial optics and a 4 × 4 ray transfer matrix to generalise Bennett's method comprehensively to include astigmatic elements. Once this is established, the method is expanded to estimate the contributions of the front and back lens surfaces. The method is illustrated using two examples. The first example is of an astigmatic model eye and compares the calculated results to the original powers. In the second example, the method is applied to the biometry of a real eye with large lenticular astigmatism. Results: When the calculated powers for the astigmatic model eye were compared to the actual powers, the difference in the power of the eye was 0.030.130.04TD (where T represents the matrix transpose) and for the crystalline lens, the difference was 0.080.290.08TD (power vector format). A second example applies the method to a real eye, obtaining lenticular astigmatism of −5.84 × 175. Conclusions: The method provides an easy‐to‐code way of estimating the astigmatic powers of the crystalline lens and the eye. [ABSTRACT FROM AUTHOR]

Purpose: To present a set of closed‐form analytical equations to create a consistent eye model balance based on clinically measured input parameters in a single step. These models complement the existing iterative approaches in the literature. Methods: Two different approaches are presented, both considering the cornea and lens as equivalent thin lenses. The first, called the Gaussian model, starts by defining the refractive error as the difference between the axial power (or dioptric distance) and the whole eye power, which can be expanded by filling in the formulas for each power. The resulting equation can be solved for either the refractive error, axial length, corneal power, lens power or the distance between the cornea and the lens as a function of the other four parameters. The second approach uses vergence calculations to provide alternative expressions, assuming that the refractive error is located at the corneal plane. Both models are explored for a biometric range typically found in adult human eyes. Results: The Gaussian and vergence models each instantly balance the input data into a working eye model over the human physiological range and far beyond as demonstrated in various examples. The equations of the Gaussian model are more complicated, while the vergence model experiences more singularities, albeit in trivial or highly unlikely parameter combinations. Conclusions: The proposed equations form a flexible and robust platform to create eye models from clinical data. Possible applications lie in creating animal eye models or providing a generic reference for real biometric data and the relationships between the ocular dimensions. [ABSTRACT FROM AUTHOR]

Objective Error in birthweight prediction by sonographic estimated fetal weight (EFW) has clinical implications, such as avoidable cesarean or misclassification of fetal risk in labor. We aimed to evaluate optimal timing of ultrasound and which fetal measurements contribute to error in fetal ultrasound estimations of birth size at the extremes of birthweight. Study Design We compared differences in head circumference (HC), abdominal circumference (AC), femur length, and EFW between ultrasound and corresponding birth measurements within 14 (n = 1,290) and 7 (n = 617) days of birth for small- (SGA, <10th percentile), appropriate- (AGA, 10th–90th), and large-for-gestational age (LGA, >90th) newborns. Results Average differences between EFW and birthweight for SGA neonates were: −40.2 g (confidence interval [CI]: −82.1, 1.6) at 14 days versus 13.6 g (CI: −52.4, 79.7) at 7 days; for AGA, −122.4 g (−139.6, −105.1) at 14 days versus −27.2 g (−50.4, −4.0) at 7 days; and for LGA, −242.8 g (−306.5, −179.1) at 14 days versus −72.1 g (−152.0, 7.9) at 7 days. Differences between fetal and neonatal HC were larger at 14 versus 7 days, and similar to patterns for EFW and birthweight, differences were the largest for LGA at both intervals. In contrast, differences between fetal and neonatal AC were larger at 7 versus 14 days, suggesting larger error in AC estimation closer to birth. Conclusion Using a standardized ultrasound protocol, SGA neonates had ultrasound measurements closer to actual birth measurements compared with AGA or LGA neonates. LGA neonates had the largest differences between fetal and neonatal size, with measurements 14 days from delivery showing 3- to 4-fold greater differences from birthweight. Differences in EFW and birthweight may not be explained by a single fetal measurement; whether estimation may be improved by incorporation of other knowable factors should be evaluated in future research. Key Points Ultrasound measurements may be inadequate to predict neonatal size at birth. Birthweight estimation error is higher for neonates >90th percentile. There is higher error in AC closer to birth. [ABSTRACT FROM AUTHOR]

Sharing facial pictures through online services, especially on social networks, has become a common habit for thousands of users. This practice hides a possible threat to privacy: the owners of such services, as well as malicious users, could automatically extract information from faces using modern and effective neural networks. In this article, we propose the harmless use of adversarial attacks, i.e., variations of images that are almost imperceptible to the human eye and that are typically generated with the malicious purpose to mislead Convolutional Neural Networks (CNNs). Such attacks have been instead adopted to (1) obfuscate soft biometrics (gender, age, ethnicity) but (2) without degrading the quality of the face images posted online. We achieve the above-mentioned two conflicting goals by modifying the implementations of four of the most popular adversarial attacks, namely FGSM, PGD, DeepFool, and C&W, in order to constrain the average amount of noise they generate on the image and the maximum perturbation they add on the single pixel. We demonstrate, in an experimental framework including three popular CNNs, namely VGG16, SENet, and MobileNetV3, that the considered obfuscation method, which requires at most 4 seconds for each image, is effective not only when we have a complete knowledge of the neural network that extracts the soft biometrics (white box attacks) but also when the adversarial attacks are generated in a more realistic black box scenario. Finally, we prove that an opponent can implement defense techniques to partially reduce the effect of the obfuscation, but substantially paying in terms of accuracy over clean images; this result, confirmed by the experiments carried out with three popular defense methods, namely adversarial training, denoising autoencoder, and Kullback-Leibler autoencoder, shows that it is not convenient for the opponent to defend himself and that the proposed approach is robust to defenses. [ABSTRACT FROM AUTHOR]

This study presents a novel approach to electroencephalography (EEG) biometric authentication using eye blink artifacts. Unlike traditional methods that rely on imagination and mental tasks, which are susceptible to emotional and physical variations, this approach leverages the consistent effects of eye blinks on brainwaves for authentication. Brainwaves were recorded using the NeuroSky Mindwave Mobile 2 headset, and eye blinks were extracted via NeuroSky's blink detection algorithm. An authentication algorithm was developed based on blink strength, time, and frequency. The proposed method demonstrated high performance with an accuracy (ACC) of 97%, a false acceptance rate (FAR) of 5%, and a false rejection rate (FRR) of 1%. This study also explored the impact of emotions and physical exercise on the authentication process, confirming the method's robustness under varying conditions. These findings suggest that eye blink artifacts offer a reliable and practical biometric trait for EEG-based authentication systems, providing a secure alternative to traditional biometric methods. The substantial contribution of this research lies in demonstrating the superior stability and usability of eye blink-based EEG authentication under diverse conditions, compared to existing EEG authentication methods that often require mental tasks or multi-channel recordings. [ABSTRACT FROM AUTHOR]

BACKGROUND: Prolonged periods of sitting have been linked to negative health outcomes. Implementation of sit-stand desks in the workplace has been one strategy to reduce prolonged sitting. OBJECTIVE: To assess the effectiveness of sit-stand workstations on reducing sitting time and improving other health outcomes of office-based workers. METHODS: 39 Portuguese office workers were randomized into a 6-month parallel-group cluster RCT consisting by the implementation of sit-stand desks in the workplace. The primary outcome of sitting time was assessed using ActivPAL. Secondary outcomes included biometric, psychological, and diet-related variables. All outcomes were assessed at baseline and 6 months for the whole sample and at 3 months for a sub-sample of the intervention group (n = 11). RESULTS: No significant time*group interaction was found for the primary or secondary outcomes, apart from waist circumference favoring the control group (Δ–1.81 cm, pinteraction = 0.04). There were significant changes within the intervention group for sitting time (–44.0 min/day), prolonged sitting (>30 min) (–45.3 min/day) and standing time (51.7 min/day) at 3 months in the sub-sample and in prolonged sitting (>30 min) (–26 min/day) in the full intervention group (p < 0.05). Changes were also observed within the intervention group for percent body fat (Δ–3.7%) and ratings of quality of life (Δ2.2), musculoskeletal discomfort (Δ–4.9), overall fatigue (Δ–2.2), and the need for recovery after work (Δ–1.7) at 6-month follow-up (p < 0.05). CONCLUSION: Although not being effective for reducing sitting time, the implementation of sit-stand desks in the Portuguese workspace was shown to be feasible over the long term, received well by users, and may offer other health benefits. TRIAL REGISTRATION: OSF Registration, OSF.IO/JHGPW. Registered 15 November 2022. https://doi.org/10.17605/OSF.IO/JHGPW. [ABSTRACT FROM AUTHOR]

Human gait recognition (HGR) is the mechanism of biometrics that authors extensively employ to recognize an individuals based on their walking traits. HGR has been prominent for the past few years due to its surveillance capability. In HGR, an individual's walking attributes are utilized for identification. HGR is considered a very effective technique for recognition but faces different problematic factors that degrade its performance. The major factors are variations in clothing, carrying, walking, etc. In this paper, a new hybrid method for the classification of HGR is designed called Stacked-Gait. The system is based on six major steps; initially, image resizing is performed to overcome computation problems. In the second step, these images are converted into grey-scale to extract better features. After that, the dataset division is performed into train and test set. In the next step, the training of the autoencoders and feature extraction of the dataset are performed using training data. In the next step, the stacking of two autoencoders is also performed. After that, the stacked encoders are employed to extract features from the test data. Finally, the feature vectors are given as input to various machine learning classifiers for final classification. The method assessment is performed using the CASIA-B dataset and achieved the accuracy of 99.90, 98.10, 97.20, 97.20, 96.70, and 100 percent on 000, 180, 360, 540, 720, and 900 angles. It is pragmatic that the system gives promising results compared to recent schemes. [ABSTRACT FROM AUTHOR]

The goal of information security is to prevent unauthorized access to data. There are several conventional ways to confirm user identity, such as using a password, user name, and keys. These conventional methods are rather limited; they can be stolen, lost, copied, or cracked. Because multimodal biometric identification systems are more secure and have higher recognition efficiency than unimodal biometric systems, they get attention. Single-modal biometric recognition systems perform poorly in real-world public security operations because of poor biometric data quality. Some of the drawbacks of current multimodal fusion methods include low generalization and single-level fusion. This study presents a novel multimodal biometric fusion model that significantly enhances accuracy and generalization through the power of artificial intelligence. Various fusion methods, encompassing pixel-level, feature-level, and score-level fusion, are seamlessly integrated through deep neural networks. At the pixel level, we employ spatial, channel, and intensity fusion strategies to optimize the fusion process. On the feature level, modality-specific branches and jointly optimized representation layers establish robust dependencies between modalities through backpropagation. Finally, intelligent fusion techniques, such as Rank-1 and modality evaluation, are harnessed to blend matching scores on the score level. To validate the model's effectiveness, we construct a virtual homogeneous multimodal dataset using simulated operational data. Experimental results showcase significant improvements compared to single-modal algorithms, with a remarkable 2.2 percentage point increase in accuracy achieved through multimodal feature fusion. The score fusion method surpasses single-modal algorithms by 3.5 percentage points, reaching an impressive retrieval accuracy of 99.6%. [ABSTRACT FROM AUTHOR]

Background: To analyze the difference and agreement between measurements obtained by a new fully automatic optical biometer, the SW-9000 μm Plus, based on optical low-coherence reflectometry (OLCR) and a commonly used optical biometer (Pentacam AXL) based on Scheimpflug imaging with partial coherence interferometry (PCI). Methods: The central corneal thickness (CCT), anterior chamber depth (ACD, from epithelium to anterior lens surface), lens thickness (LT), mean keratometry (Km), corneal astigmatism, corneal diameter (CD), pupil diameter (PD), and axial length (AL) of 74 eyes (from 74 healthy subjects) were measured using the SW-9000 μm Plus and the Pentacam AXL to determine the agreement. Double angle plots were used for astigmatism vector analysis. Bland–Altman and 95% limits of agreement (LoA) were calculated. Results: Statistically significant differences were detected for all parameters but J0 vector. The Bland–Altman analysis of AL, CCT, ACD, Km, CD, J0 and J45 indicated a high level of agreement between the two devices. Among AL, CCT, ACD, Km, J0, J45, CD, and PD, the 95% LoA ranged from -0.07 to 0.05 mm, -9.67 to 7.34 mm, -0.11 to 0.04 mm, -0.25 to 0.50 D, -0.22 to 0.20 D, -0.15 to 0.20 D, -0.23 to 0.35 mm and 1.55 to 3.77 mm, respectively. Conclusions: The measurements of AL, CCT, ACD, Km, corneal astigmatism, and CD showed a narrow LoA and may be used interchangeably in healthy subjects between the new OLCR optical biometer and the Scheimpflug/PCI biometer; however, a poor agreement was noted for PD values. [ABSTRACT FROM AUTHOR]

The Internet of Medical Things (IoMT) has revolutionized healthcare with remote patient monitoring and real-time diagnosis, but securing patient data remains a critical challenge due to sophisticated cyber threats and the sensitivity of medical information. Traditional machine learning methods struggle to capture the complex patterns in IoMT data, and conventional intrusion detection systems often fail to identify unknown attacks, leading to high false positive rates and compromised patient data security. To address these issues, we propose RCLNet, an effective Anomaly-based Intrusion Detection System (A-IDS) for IoMT. RCLNet employs a multi-faceted approach, including Random Forest (RF) for feature selection, the integration of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models to enhance pattern recognition, and a Self-Adaptive Attention Layer Mechanism (SAALM) designed specifically for the unique challenges of IoMT. Additionally, RCLNet utilizes focal loss (FL) to manage imbalanced data distributions, a common challenge in IoMT datasets. Evaluation using the WUSTL-EHMS-2020 healthcare dataset demonstrates that RCLNet outperforms recent state-of-the-art methods, achieving a remarkable accuracy of 99.78%, highlighting its potential to significantly improve the security and confidentiality of patient data in IoMT healthcare systems. [ABSTRACT FROM AUTHOR]

Various healthcare domains have witnessed successful preliminary implementation of artificial intelligence (AI) solutions, including radiology, though limited generalizability hinders their widespread adoption. Currently, most research groups and industry have limited access to the data needed for external validation studies. The creation and accessibility of benchmark datasets to validate such solutions represents a critical step towards generalizability, for which an array of aspects ranging from preprocessing to regulatory issues and biostatistical principles come into play. In this article, the authors provide recommendations for the creation of benchmark datasets in radiology, explain current limitations in this realm, and explore potential new approaches. Clinical relevance statement: Benchmark datasets, facilitating validation of AI software performance can contribute to the adoption of AI in clinical practice. Key Points: Benchmark datasets are essential for the validation of AI software performance. Factors like image quality and representativeness of cases should be considered. Benchmark datasets can help adoption by increasing the trustworthiness and robustness of AI. [ABSTRACT FROM AUTHOR]

Background Methods Results Conclusions The purpose of this study was to simulate the impact of biometric measure uncertainties, lens equivalent and toric power labelling tolerances and axis alignment errors on the refractive outcome after cataract surgery with toric lens implantation.In this retrospective non‐randomised cross sectional Monte‐Carlo simulation study we evaluated a dataset containing 7458 LenStar 900 preoperative biometric measurements. The biometric uncertainties from literature, lens power labelling according to ISO 11979, and axis alignment tolerances of a modern toric lens (Hoya Vivinex) were taken to be normally distributed and used in a Monte‐Carlo simulation with 100 000 samples per eye. The target variable was the defocus equivalent (DEQ) derived using the Castrop (DEQC) and the Haigis (DEQH) formulae.Mean/median / 90% quantile DEQC was 0.22/0.21/0.36 D and DEQH was 0.20/0.19/0.32 D. Ignoring the variation in lens power labelling and toric axis alignment the respective DEQC was 0.20/0.19/0.32 D and DEQH was 0.18/0.17/0.29 D. DEQC and DEQH increased with shorter eyes, steeper corneas, equivalent lens power and highly with toric lens power.According to our simulation results, uncertainties in biometric measures, lens power labelling tolerances, and axis alignment errors are responsible for a significant part of the refraction prediction error after cataract surgery with toric lens implantation. Additional labelling of the exact equivalent and toric power on the lens package could be a step to improve postoperative results. [ABSTRACT FROM AUTHOR]

The broad usage of mobile devices nowadays, the sensitiveness of the information contained in them, and the shortcomings of current mobile user authentication methods are calling for novel, secure, and unobtrusive solutions to verify the users' identity. In this article, we propose TypeFormer, a novel transformer architecture to model free-text keystroke dynamics performed on mobile devices for the purpose of user authentication. The proposed model consists in temporal and channel modules enclosing two long short-term memory recurrent layers, Gaussian range encoding, a multi-head self-attention mechanism, and a block-recurrent transformer layer. Experimenting on one of the largest public databases to date, the Aalto mobile keystroke database, TypeFormer outperforms current state-of-the-art systems achieving equal error rate values of 3.25% using only five enrolment sessions of 50 keystrokes each. In such way, we contribute to reducing the traditional performance gap of the challenging mobile free-text scenario with respect to its desktop and fixed-text counterparts. To highlight the design rationale, an analysis of the experimental results of the different modules implemented in the development of TypeFormer is carried out. Additionally, we analyse the behaviour of the model with different experimental configurations such as the length of the keystroke sequences and the amount of enrolment sessions, showing margin for improvement. [ABSTRACT FROM AUTHOR]

In this research paper, we propose an unsupervised framework for feature learning based on an autoencoder to learn sparse feature representations for EEG-based person identification. Autoencoder and CNN do the person identification task for signal reconstruction and recognition. Electroencephalography (EEG) based biometric system is vesting humans to recognize, identify and communicate with the outer world using brain signals for interactions. EEG-based biometrics are putting forward solutions because of their high-safety capabilities and handy transportable instruments. Motor imagery EEG (MI-EEG) is a maximum broadly centered EEG signal that exhibits a subject's motion intentions without real actions. The Proposed framework proved to be a practical approach to managing the massive volume of EEG data and identifying the person based on their different task with resting states. The experiments have been conducted on the standard publicly available motor imagery EEG dataset with 109 subjects. The highest recognition rate of 87.60% for task-based identification and 99.89% recognition rate for resting-state has been recorded using the Autoencoder-CNN model. The outcomes imply that the overall performance of our proposed framework is similar or advanced to that of the state-of-the-art method. The shape is a realistic technique to control the full-size extent of EEG data and to pick out the individual based totally on their specific task. [ABSTRACT FROM AUTHOR]

Gait recognition is a biometric approach used to identify people based on their walking patterns at long distances and low resolutions. Most advanced gait recognition methods based on silhouettes employ the focal convolution module. However, experiments have demonstrated that the horizontal segmentation method used in this module causes information loss at the feature map demarcation line. In this paper, we propose an adaptive feature fusion block (AFFB) for feature extraction that utilizes comprehensive global features to compensate for the lost local features, significantly reducing feature loss caused by local convolution. Additionally, we introduce a feature expansion module (FEM) to enrich the temporal information of gait features and adaptively balance the body detail information extracted by the model with the overall body information. We evaluated our model on CASIA-B and OU-MVLP datasets and compared it to other gait models using RANK-1 accuracy. The experimental results show that our model can represent gait features better than other models and achieved high accuracy in gait recognition across perspectives and various walking conditions.The source code will be available on https://github.com/Lentia/AdaptiveGait. [ABSTRACT FROM AUTHOR]

Cancelable template protection techniques are indispensable to provide essential security and privacy privileges in biometric systems. This paper introduces an efficient cancelable palmprint recognition technique based on multi-level transformations. Gabor filtering with feature remapping is introduced for extracting highly discriminative features. Histogram remapping is applied to nonlinearly transform the downsampled Gabor features to be normally distributed. This feature-remapping step is proposed to enhance the discriminatory power and alleviate the effect of feature variability and image artifacts. Comb filtering is applied to the mapped features as a first protection layer. To provide security guarantees against linkability attacks, index-based locality-sensitive hashing (LSH) is introduced as a second protection layer to transform the comb-filtered mapped real-valued features into maximum-ranked indices. Recognition is performed in the secured domain to accelerate matching and to preserve the user's privacy. Results show that the proposed scheme provides a large re-issuance ability, protects templates from being inverted, and demonstrates strong unlinkability across different databases. In addition, favorable verification/identification accuracy is obtained and the system satisfies the needs for real-time applications. A global measure D ↔ sys value of 0.01 is obtained, and thus, correlation attacks are mitigated. The recognition results for the legitimate scenario are 100% identification accuracy and 0% EER. For the worst case (same token scenario), the corresponding results are 99.752% and 0.31%, respectively. Highlights: • Multi-level transformations are proposed for efficient cancelable palmprints. • Histogram-remapped downsampled Gabor features are subjected to comb filtering. • Locality-sensitive hashing follows comb filtering to obtain maximum-ranked indices. • The algorithm provides significant capability for re-issuance. • The system protects templates from inversion and ensures unlinkability across databases. [ABSTRACT FROM AUTHOR]

Research on multi‐biometric authentication systems using multiple biometric modalities to defend against adversarial attacks is actively being pursued. These systems authenticate users by combining two or more biometric modalities using score or feature‐level fusion. However, research on adversarial attacks and defences against each biometric modality within these authentication systems has not been actively conducted. In this study, we constructed a multi‐biometric authentication system using fingerprint, palmprint, and iris information from CASIA‐BIT by employing score and feature‐level fusion. We verified the system's vulnerability by deploying adversarial attacks on single and multiple biometric modalities based on the FGSM, with epsilon values ranging from 0 to 0.5. The experimental results show that when the epsilon value is 0.5, the accuracy of the multi‐biometric authentication system against adversarial attacks on the palmprint and iris information decreases from 0.995 to 0.018 and 0.003, respectively, and the f1‐score decreases from 0.995 to 0.007 and 0.000, respectively, demonstrating susceptibility to adversarial attacks. In the case of fingerprint data, however, the accuracy and f1‐score decreased from 0.995 to 0.731 and from 0.995 to 0.741, respectively, indicating resilience against adversarial attacks. [ABSTRACT FROM AUTHOR]

Current evidence suggests moderate heritability of music phenotypes, such as music listening and achievement. However, other fundamental traits underlying people's interest in music and its relevance for their lives have been largely neglected, and little is known about the genetic and environmental etiology of what we refer to as musical sensibility—the tendency to be emotionally and aesthetically engaged by music. This study investigated the latent structure, as well as the genetic and environmental factors influencing individual variability in multiple domains of musical sensibility, and the etiological architecture of the relationship between the dimensions. To this end, we used phenotypic confirmatory factor analytic and biometric twin modeling to analyze self‐reported ratings on four dimensions of musical sensibility in a sample of Norwegian twins (N = 2600). The results indicate a phenotypic higher‐order structure, whereby both the resulting general musical sensibility factor and the conceptually narrower domains were strongly heritable (49–65%). Multivariate analyses of the genetic and environmental covariance further revealed substantial overlap in genetic variance across domains. [ABSTRACT FROM AUTHOR]

Carefully standardized facial images of 591 participants were taken in the laboratory while controlling for self-presentation, facial expression, head orientation, and image properties. They were presented to human raters and a facial recognition algorithm: both humans (r =.21) and the algorithm (r =.22) could predict participants' scores on a political orientation scale (Cronbach's α =.94) decorrelated with age, gender, and ethnicity. These effects are on par with how well job interviews predict job success, or alcohol drives aggressiveness. The algorithm's predictive accuracy was even higher (r =.31) when it leveraged information on participants' age, gender, and ethnicity. Moreover, the associations between facial appearance and political orientation seem to generalize beyond our sample: The predictive model derived from standardized images (while controlling for age, gender, and ethnicity) could predict political orientation (r ≈.13) from naturalistic images of 3,401 politicians from the United States, the United Kingdom, and Canada. The analysis of facial features associated with political orientation revealed that conservatives tended to have larger lower faces. The predictability of political orientation from standardized images has critical implications for privacy, the regulation of facial recognition technology, and understanding the origins and consequences of political orientation. Public Significance Statement: We demonstrate that political orientation can be predicted from neutral facial images by both humans and algorithms, even when factors like age, gender, and ethnicity are accounted for. This indicates a connection between political leanings and inherent facial characteristics, which are largely beyond an individual's control. Our findings underscore the urgency for scholars, the public, and policymakers to recognize and address the potential risks of facial recognition technology to personal privacy. [ABSTRACT FROM AUTHOR]

Generating human images from open-vocabulary text descriptions is an exciting but challenging task. Previous methods (i.e., Text2Human) face two challenging problems: (1) they cannot well handle the open-vocabulary setting by arbitrary text inputs (i.e., unseen clothing appearances) and heavily rely on limited preset words (i.e., pattern styles of clothing appearances); (2) the generated human image is inaccuracy in open-vocabulary settings. To alleviate these drawbacks, we propose a flexible diffusion-based framework, namely HumanDiffusion, for open-vocabulary text-driven human image generation (HIG). The proposed framework mainly consists of two novel modules: the Stylized Memory Retrieval (SMR) module and the Multi-scale Feature Mapping (MFM) module. Encoded by the vision-language pretrained CLIP model, we obtain coarse features of the local human appearance. Then, the SMR module utilizes an external database that contains clothing texture details to refine the initial coarse features. Through SMR refreshing, we can achieve the HIG task with arbitrary text inputs, and the range of expression styles is greatly expanded. Later, the MFM module embedding in the diffusion backbone can learn fine-grained appearance features, which effectively achieves precise semantic-coherence alignment of different body parts with appearance features and realizes the accurate expression of desired human appearance. The seamless combination of the proposed novel modules in HumanDiffusion realizes the freestyle and high accuracy of text-guided HIG and editing tasks. Extensive experiments demonstrate that the proposed method can achieve state-of-the-art (SOTA) performance, especially in the open-vocabulary setting. [ABSTRACT FROM AUTHOR]

Palmprint as biometrics has gained increasing attention recently due to its discriminative ability and robustness. However, existing methods mainly improve palmprint verification within one spectrum, which is challenging to verify across different spectrums. Additionally, in distributed server-client-based deployment, palmprint verification systems predominantly necessitate clients to transmit private data for model training on the centralized server, thereby engendering privacy apprehensions. To alleviate the above issues, in this paper, we propose a physics-driven spectrum-consistent federated learning method for palmprint verification, dubbed as PSFed-Palm. PSFed-Palm draws upon the inherent physical properties of distinct wavelength spectrums, wherein images acquired under similar wavelengths display heightened resemblances. Our approach first partitions clients into short- and long-spectrum groups according to the wavelength range of their local spectrum images. Subsequently, we introduce anchor models for short- and long-spectrum, which constrain the optimization directions of local models associated with long- and short-spectrum images. Specifically, a spectrum-consistent loss that enforces the model parameters and feature representation to align with their corresponding anchor models is designed. Finally, we impose constraints on the local models to ensure their consistency with the global model, effectively preventing model drift. This measure guarantees spectrum consistency while protecting data privacy, as there is no need to share local data. Extensive experiments are conducted to validate the efficacy of our proposed PSFed-Palm approach. The proposed PSFed-Palm demonstrates compelling performance despite only a limited number of training data. The codes have been released at https://github.com/Zi-YuanYang/PSFed-Palm. [ABSTRACT FROM AUTHOR]

Palmprint is a promising biometric modality and has several advantages. However, many serious challenges severely restrict the development of palmprint recognition in mobile environments. Double-line-single-point (DLSP), as a state-of-the-art assisting graph, can be free from pre-processing, and effectively reduce the errors of pre-processing; however, its accuracy heavily depends on users' cooperation and operation proficiency. This paper proposes boundary line calibration (BLC) and finger valley calibration (FVC) to suppress the translational dislocations in DLSP. Firstly, the samples acquired according to DLSP are rotated around the center so that the assisting lines are horizontal. Secondly, a rectangular area is cropped as the region of line detection (RLD) with the assisting line as the reference; while a rectangular area is cropped as the region of point detection (RPD) with the assisting point as the reference. The cropped rectangular regions are convolved with Gabor filters along an optimized direction to enhance edges. The accurate palm boundary is localized in RLD to reduce the vertical dislocation; and the accurate inter-finger valley point (IFVP) is localized in RPD to reduce the horizontal dislocation. The sufficient experiments show that the proposed algorithm can calibrate the translational dislocations caused by users' imperfect cooperation, and accordingly remarkably improve the accuracy and users' comfort. [ABSTRACT FROM AUTHOR]

Hand vein identification stands out to be an increasingly popular approach for biometric identification due to its distinctiveness and convenience. While state-of-the-art techniques are able to achieve good performance, they share two common drawbacks: (1) complex preprocessing procedures, e.g., vein enhancement and Region of Interest (ROI) extraction, and (2) vein information loss due to hand ROI partition. To address these issues, we propose VeinTr, an end-to-end full-hand vein identification approach. In particular, our VeinTr consists of three components: a local feature extractor, a lightweight transformer, and a global feature decoder. We first obtain local features via convolution-based ResNet-like blocks. Then the attention mechanism is employed to aggregate global features from local features, which can be then decoded as global hand vein features. Finally, a global feature decoder is applied to generate robust hand features. By doing so, VeinTr is capable of directly extracting robust hand vein features from raw hand vein images. We evaluate our method on CASIA, TPV, and PLUSVein hand vein datasets. Experimental results show that our approach outperforms the state-of-the-art methods and has strong inter-dataset generalization abilities. [ABSTRACT FROM AUTHOR]

Likelihood ratios compare two values (i.e., case rates) in order to illustrate the magnitude of the difference between the two. This ratio increases the confidence one can have in a diagnostic test from a different vantage point than that of sensitivity and specificity. The calculations of likelihood ratios are presented along with a simplified approach. Likelihood ratios are another tool the toxicologist should employ in their understanding of statistics and probability. [ABSTRACT FROM AUTHOR]

Predicting video virality is the holy grail of marketing today. Previous video virality prediction research has relied upon two processes that may lead to incomplete data or incomplete analyses: non-subconscious data collection and self-reporting. This exploratory study evaluates the potential of using a physiological manifestation of emotions captured through facial expressions and skin conductance to predict video viewer engagement across the viewing experience. In the context of video virality and user-focused emotional response, an experiment with 64 subjects viewing 13 videos collected facial expression and galvanic skin response data during the entire viewing experience. XGBoost classifier was deployed using 42 collected features (physiological data and socio-behavioural responses). The selected classifier could predict user engagement with over 80% accuracy. In addition to socio-demographic data and behavioural features, the predictive model identified several facial expression-based features, including action units (mouth open, cheek raise, eye closure, lip raise, and smile), emotions (joy), engagement and positive valence along with head movement (attention) and arousal (GSR peaks) as the most impactful. This study confirms the predictive capability of physiological data and elevates the value and need to understand further the role of viewers' physiological and subconscious responses to video content across the viewing experience. [ABSTRACT FROM AUTHOR]

Existing data reveals prevalent performance and image-enhancing drug (PIED) use in specific global regions and higher rates among athletes, however, research on performance-enhancement experiences among elite untested athletes is lacking. Drawing on conceptual frameworks that emphasize the intersection of context and practice, this research aims to gain insights into the subjective perspectives, motivations, and challenges faced by athletes in managing and optimizing their performance while using PIEDs. In-depth interviews were conducted with seventeen strength sports athletes, including powerlifters and bodybuilders, who had competed at national and/or international levels within untested federations. Thematic analysis was employed to examine the interview data within a social constructivist ontology. Findings revealed that PIEDs have dual roles as tools for enhanced recovery and heightened training stress, a delicate balance that aligns with Foucault's notion of self-transformation through technological advancements. These substances exerted power beyond consumption events with long-term psychological effects such as anxiety and irrational behavior emerging as key concerns. Peers with lived experience were key actors in the relationship between responsible drug management, however, the need for informed guidance was acknowledged. Non-human actors, notably biometric data tracking, played a pivotal role in guiding substance consumption. The study underscores the need for further research and tailored frameworks to support the health and well-being of athletes in this domain while addressing the broader implications of PIED use in public health discourse. Specifically, this study highlights the significance of integrating lived experiences and social contexts, emphasizing the need for nuanced harm-reduction strategies in this space. [ABSTRACT FROM AUTHOR]

Objectives: Estimated fetal weight (EFW) is an important metric at delivery as neonates with abnormal birthweight and their mothers are at higher risk of birth complications. Data regarding optimal EFW assessment in gravidas with obesity is inconsistent, and with the increasing incidence of obesity, clarification of this question is crucial. We aimed to compare accuracy of ultrasound (US)‐derived EFW and clinical assessments of EFW in predicting neonatal birthweight among gravidas with obesity. Methods: This prospective cohort study enrolled gravidas with obesity and a singleton pregnancy admitted for delivery at term. EFW was determined using either US biometry or clinical assessment (Leopold's maneuvers, Johnson's formula, and Insler's formula) at time of admission. Our primary outcome was accurate EFW, defined as EFW within 500 g of birthweight. Secondary outcomes included ability to predict small‐for‐gestational age (SGA) and large‐for‐gestational age (LGA) birthweights. These outcomes were compared between all EFW methods. Results: A total of 250 gravidas with a median body mass index of 36.4 kg/m2 were enrolled. Admission US outperformed Leopold's maneuvers in obtaining accurate EFW (81.6% versus 74.5%, P =.03). When comparing all methods, Johnson's and Insler's formulae performed the worst, accurately predicting EFW in only 27.4% and 14.3% of cases, respectively. Likewise, US‐derived EFW outperformed Leopold's maneuvers and fundal height in the prediction of SGA and LGA neonates. Conclusions: US is more accurate than clinical assessment of EFW in gravidas with obesity both for estimation of actual birthweight and prediction of abnormal birthweight. Universal late third‐trimester or peripartum US for EFW should be considered in gravidas with obesity. [ABSTRACT FROM AUTHOR]

Advancements in multimodal biometrics, which integrate multiple biometric traits, promise to enhance the accuracy and robustness of identification systems. This study focuses on improving multimodal biometric identification by using fingerprint and finger vein images as the primary traits. We utilized the "NUPT-FPV" dataset, which contains a substantial number of finger vein and fingerprint images, which significantly aided our research. Convolutional neural networks (CNNs), renowned for their efficacy in computer vision tasks, are used in our model to extract distinct discriminative features. Specifically, we incorporate three popular CNN architectures: ResNet, VGGNet, and DenseNet. We explore three fusion strategies used in security applications: early fusion, late fusion, and score-level fusion. Early fusion integrates raw images at the input layer of a single CNN, combining information at the initial stages. Late fusion, in contrast, merges features after individual learning from each CNN model. Score-level fusion employs weighted aggregation to combine scores from each modality, leveraging the complementary information they provide. We also use contrast limited adaptive histogram equalization (CLAHE) to enhance fingerprint contrast and vein pattern features, improving feature visibility and extraction. Our evaluation metrics include accuracy, equal error rate (EER), and ROC curves. The fusion of CNN architectures and enhancement methods shows promising performance in identifying multimodal biometrics, aiming to increase identification accuracy. The proposed model offers a reliable authentication system using multiple biometrics to verify identity. [ABSTRACT FROM AUTHOR]

Copyright of Scientific Research / Elmi Tədqiqat is the property of Azerbaijan Science Center and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In recent years, there has been a growing interest in biometric recognition based on finger dorsal patterns, making it a significant area of research. This paper introduces a biometric classification system that utilizes dorsal finger middle creases. The viability of this trait is assessed through the implementation of a new method known as multi block circular shift combination local binary pattern (MBCSC-LBP). The MBCSC-LBP approach involves dividing the image into multiple blocks to enhance robustness and capture both local and global information, thereby extracting discriminative features. These features from each block are then concatenated to form a comprehensive feature vector. To evaluate the accuracy of the proposed MBCSC-LBP feature extractor, a support vector machine (SVM) with a linear kernel is utilized. The classification accuracy achieved by this method is 96.22% indicating a promising performance. [ABSTRACT FROM AUTHOR]

In today's digital era, ensuring robust and secure authentication mechanisms is crucial. Multi-fusion biometric authentication systems have emerged as a powerful solution to enhance security and reliability by integrating multiple biometric traits. This paper presents a novel Multi-Fusion Biometric Authentication approach using Minutiae-Driven Fixed-Size Template Matching (MFTM). The proposed method leverages the unique features of minutiae points in fingerprints and combines them with other biometric modalities, such as iris and facial recognition, to create a fixed-size template for matching. The fusion process involves extracting and normalizing minutiae points from the fingerprint, followed by their integration with iris and facial features using a robust feature fusion algorithm. The fixed-size template ensures consistency and efficiency in the matching process, addressing challenges related to template size variability and computational overhead. Extensive experiments conducted on standard biometric datasets demonstrate that the proposed MFTM approach significantly enhances authentication accuracy, reduces false acceptance and rejection rates, and provides a highly secure and scalable authentication solution suitable for various applications, including access control and identity verification. The results show an authentication accuracy of 98.7%, a false acceptance rate (FAR) of 0.2%, and a false rejection rate (FRR) of 0.5%. Additionally, the computational time for matching is reduced by 25% compared to traditional methods, highlighting the efficiency and practicality of the proposed approach. [ABSTRACT FROM AUTHOR]

Background: To date, there have been numerous metataxonomic studies on gut microbiota (GM) profiling based on the analyses of data from public repositories. However, differences in study population and wet and dry pipelines have produced discordant results. Herein, we propose a biostatistical approach to remove these batch effects for the GM characterization in the case of autism spectrum disorders (ASDs). Methods: An original dataset of GM profiles from patients with ASD was ecologically characterized and compared with GM public digital profiles of age-matched neurotypical controls (NCs). Also, GM data from seven case–control studies on ASD were retrieved from the NCBI platform and exploited for analysis. Hence, on each dataset, conditional quantile regression (CQR) was performed to reduce the batch effects originating from both technical and geographical confounders affecting the GM-related data. This method was further applied to the whole dataset matrix, obtained by merging all datasets. The ASD GM markers were identified by the random forest (RF) model. Results: We observed a different GM profile in patients with ASD compared with NC subjects. Moreover, a significant reduction of technical- and geographical-dependent batch effects in all datasets was achieved. We identified Bacteroides_H, Faecalibacterium, Gemmiger_A_73129, Blautia_A_141781, Bifidobacterium_388775, and Phocaeicola_A_858004 as robust GM bacterial biomarkers of ASD. Finally, our validation approach provided evidence of the validity of the QCR method, showing high values of accuracy, specificity, sensitivity, and AUC-ROC. Conclusions: Herein, we proposed an updated biostatistical approach to reduce the technical and geographical batch effects that may negatively affect the description of bacterial composition in microbiota studies. [ABSTRACT FROM AUTHOR]

Next-generation identity verification using biometric features is nearly foolproof with the right classifier. However, selecting the correct classifier poses a key challenge, particularly in the recognition of biometric patterns. High-potential projects may face delays due to a lack of the right recognition mechanism or the malfunction of the selected classifier. This could also result from not choosing the appropriate classifier that aligns with the project's patterns. This study aims to evaluate various classifiers with potential in biometric research and the capabilities of different machine learning algorithms. Several classifiers were experimentally evaluated in combination with dynamic algorithms. The ultimate objective was to identify a standard classifier suitable for general biometric pattern recognition. Using well-known biometric pattern datasets, multivariate algorithms, such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), were applied. These methods were combined with different classifiers, including SVM-L, MLP, KNN, etc. After analyzing the results obtained, the combination of LDA with MLP outperformed other approaches in terms of accuracy. [ABSTRACT FROM AUTHOR]

A signature is a biometric attribute commonly used for identity verification. It can be represented by a shape created with a classic pen, but it can also contain dynamic information. This information is acquired using a digital input device, such as a graphic tablet or a digital screen and stylus. Information about the dynamics of the signing process is stored in the form of signals that change over time, including pen velocity, pressure, and more. These dynamics are characteristic of an individual and are difficult for a human to forge. However, it is an interesting research issue whether the values of signals describing a dynamic signature can be predicted using artificial intelligence methods. Predicting the dynamics of the signals describing a signature would benefit various scientific problems, including improving the quality of reference signals by detecting anomalies, creating signature templates better suited to individuals, and more effectively detecting potential forgeries by identity verification systems. In this paper, we propose a method for predicting dynamic signature signals using an artificial neural network. The method was evaluated using samples collected in the DeepSignDB database, distributed by BiDA Lab. [ABSTRACT FROM AUTHOR]

This article provides the foundation for employing nonparametric testing in dental clinical research. To make wise judgments in their research, investigators should learn more about the main nonparametric tests and their particular uses. Biostatistical analysis is essential in dental research; dental research frequently deviates from the assumptions that underpin traditional parametric statistics. Nonparametric statistics are useful for studies with small sample sizes, nominal- or ordinal-level data, and non-normally distributed variables. These statistical tests make no assumptions about the sampled population. Nonparametric tests are statistical methods based on signs and ranks. For dental research to be conducted effectively and accurately, statistical approaches must be applied correctly. Therefore, dental researchers must understand the many statistical methods at their disposal and know when to use them. [ABSTRACT FROM AUTHOR]

This study highlights the necessity for efficient database management in continuous authentication systems, which rely on large-scale behavioral biometric data such as keystroke patterns. A benchmarking framework was developed to evaluate the PostgreSQL and MySQL databases, minimizing repetitive coding through configurable functions and variables. The methodology involved experiments assessing select and insert queries under primary and complex conditions, simulating real-world scenarios. Our quantified results show PostgreSQL's superior performance in select operations. In primary tests, PostgreSQL's execution time for 1 million records ranged from 0.6 ms to 0.8 ms, while MySQL's ranged from 9 ms to 12 ms, indicating that PostgreSQL is about 13 times faster. For select queries with a where clause, PostgreSQL required 0.09 ms to 0.13 ms compared to MySQL's 0.9 ms to 1 ms, making it roughly 9 times more efficient. Insert operations were similar, with PostgreSQL at 0.0007 ms to 0.0014 ms and MySQL at 0.0010 ms to 0.0030 ms. In complex experiments with simultaneous operations, PostgreSQL maintained stable performance (0.7 ms to 0.9 ms for select queries during inserts), while MySQL's performance degraded significantly (7 ms to 13 ms). These findings underscore PostgreSQL's suitability for environments requiring low data latency and robust concurrent processing capabilities, making it ideal for continuous authentication systems. [ABSTRACT FROM AUTHOR]

Background/Objectives: In paediatric liver transplantation, donor–recipient compatibility depends on graft size. We explored whether the graft weight can be predicted using the donor's biometric parameters. Methods: We used seven easily available biometric variables in 142 anonymised paediatric and adult donors, with data collected between 2016 and 2022. The whole or partial liver was transplanted in our hospital from these donors. We identified the variables that had the strongest correlation to our response variable: whole liver graft weight. Results: In child donors, we determined two linear models: using donor weight and height on the one hand and using donor weight and right liver span on the other hand. Both models had a coefficient of determination R2 = 0.86 and p-value < 10−5. We also determined two models in adult donors using donor weight and height (R2 = 0.33, p < 10−4) and donor weight and sternal height (R2 = 0.38, p < 10−4). The models proved valid based on our external dataset of 245 patients from two institutions. Conclusions: In clinical practise, our models could provide rapidly accessible estimates to determine whole graft dimension compatibility in liver transplantation in children and adults. Determining similar models predicting the left lobe and lateral segment weight could prove invaluable in paediatric transplantation. [ABSTRACT FROM AUTHOR]

Skin scarring can result from burns, injuries, stretch marks and acne, leading to cosmetic and functional difficulties. Treatments for burn scars encompass a range of options, such as lasers, corticosteroid injections, surgery and regenerative techniques such as platelet‐rich plasma (PRP). Hyaluronic acid‐based products offer skin hydration and shield against aging effects. A study is being conducted to evaluate how effective PRP injection, hyaluronic acid and their combination improve burn scars and their effects on quality of life and potential disabilities. In our study, PRP and non‐cross‐linked hyaluronic acid treatments were compared in 10 individuals with burn scars between 2022 and 2023. Patients received CO2 fractional laser treatment followed by injections in scar areas. Evaluations included the Vancouver scar scale (VSS), biometric assessments, ultrasounds and satisfaction ratings. Two therapy sessions were conducted at 1‐month interval, and assessments were done before treatment, 1 month after the first session, and 3 months after the first session. Biometric assessments showed significant improvements in various parameters (tewametry, corneometry, erythema index, melanin index, cutometry, thickness and density) in the intervention groups compared to the placebo group (p <0.05). PRP‐non‐cross‐linked hyaluronic acid, PRP and non‐cross‐linked hyaluronic acid treatments exhibited the best clinical responses with significant differences between groups (p <0.05). Dermal thickness did not show significant improvement during treatment sessions, and changes among subjects were not significantly different. The colorimetry parameter improved in all groups except the placebo group, with no significant difference between intervention groups. The VSS significantly decreased in all treatment groups except the placebo group. PRP, non‐cross‐linked hyaluronic acid and especially the combination of these two treatment options are very effective in treating burn scars. [ABSTRACT FROM AUTHOR]