Biometric Data Research Articles

An improved biometric stress monitoring solution for working employees using heart rate variability data and Capsule Network model.

Biometric stress monitoring has become a critical area of research in understanding and managing health problems resulting from stress. One of the fields that emerged in this area is biometric stress monitoring, which provides continuous or real-time information about different anxiety levels among people by analyzing physiological signals and behavioral data. In this paper, we propose a new approach based on the CapsNets model for continuously monitoring psychophysiological stress. In the new model, streams of biometric data, including physiological signals and behavioral patterns, are taken up for analysis. In testing using the Swell multiclass dataset, it performed with an accuracy of 92.76%. Further testing of the WESAD dataset reveals an even better accuracy at 96.76%. The accuracy obtained for binary classification of stress and no stress class is applied to the Swell dataset, where this model obtained an outstanding accuracy of 98.52% in this study and on WESAD, 99.82%. Comparative analysis with other state-of-the-art models underlines the superior performance; it achieves better results than all of its competitors. The developed model is then rigorously subjected to 5-fold cross-validation, which proved very significant and proved that the proposed model could be effective and efficient in biometric stress monitoring.

Directions of emerging structural changes in the use of biometric data in Russia

Objective: to identify the emerging structural changes in the use of biometrics in Russia, namely the multiple growth of market participants and brands, the multiple growth of the number of biometrics samples in a single biometric system, and the multiple growth of market volume and institutional design of biometrics use in Russia. Methods: general scientific, abstract-logical, dialectical, phenomenological methods, observation, description. Results: the article describes approaches to the use of biometric data in some regions of the world, identifies the risks and potential benefits of wider use of biometric data, summarizes the main trends in the use of biometric personal data in Russia, presents a comprehensive author’s approach to the analysis of structural changes in the economy, taking as an example thedevelopment of solutions using biometric personal data for the identification of individuals. Scientific novelty: the author proposes to consider the formation of structural shift by identifying its four components and qualitatively assessing their level of formation (low, medium, and high); shows the formation of macro-shifts from micro-level initiatives and sequential passage of the stages of specific structural changes, complex micro-shifts, institutionalization andconsolidation of new practices. In addition, the process of implementation of structural shifts from the macro- to the micro-level is traced, which consists in the changes more widely covering economic agents compared to the stage of a structural shift formation. All this constitutes a comprehensive author’s approach to the regularities of the structural shifts developmentin the economy. Practical significance: clarification of interrelations between the processes of structural change will improve the programs of socio-economic development of regions, industrial policy for medium- and high-tech industries through the use of modern technological methods of identification and authentication of customers and employees with biometrics. It may also create a basis for deepening the existing knowledge in the development of biometric technologies in Russia and expanding the practice of their application.

Accuracy of new intraocular lens calculation formulas in primary angle closure glaucoma patients who underwent phacoemulsification combined with goniosynechialysis.

This study aims to evaluate the accuracy of intraocular lens (IOL) power calculation formulas-including Kane, Emmetropia Verifying Optical (EVO) 2.0, SRK/T, Hoffer Q, Haigis standard, Haigis optimized, Holladay 1, Olsen, Barrett Universal II-in primary angle-closure glaucoma (PACG) eyes undergoing cataract surgery combined with goniosynechialysis (GSL). Preoperative biometric data were obtained using the OA-2000. The preoperative anterior chamber depth (ACD) was categorized into two subgroups: < 2.50mm and 2.50 to 3.50mm. The predictive accuracy of the formulas was assessed using the mean prediction error (PE), mean absolute error (MAE), median absolute error (MedAE), and proportions of eyes within ± 0.25D, ± 0.50D, ± 0.75D, and ± 1.00D. Differences in absolute error among the various formulas were examined utilizing the Friedman test. In the case of a significant result, post hoc analysis was conducted employing the Wilcoxon test with Bonferroni correction. A total of 141 eyes of 141 PACG patients were included in the analysis. The standard deviations of the PE, ranked from lowest to highest, were as follows: Holladay 1 (0.67), Kane (0.69), EVO 2.0 (0.71), SRK/T (0.71), Hoffer Q (0.72), Haigis standard (0.74), Haigis optimized (0.76), Olsen (0.77), Barrett Universal II (0.79). Statistically significant differences in absolute refractive errors among the formulas were observed (P = 0.001). Kane formula demonstrated the lowest MedAE (0.34), and the highest percentages of eyes within ± 0.25D (35.46%) and ± 1.00D (89.36%), while EVO 2.0 had the highest percentages within ± 0.50D (65.25%). In the ACD < 2.50mm subgroup, MedAE differed significantly among formulas (P = 0.001). The Holladay 1 formula had the lowest MedAE (0.33), followed by Kane (0.34), EVO 2.0 (0.37). In the 2.50 ≤ ACD < 3.50mm subgroup, refractive errors showed no statistically significant differences. Additionally, the percentages within ± 0.25D, ± 0.50D, ± 0.75D, and ± 1.00D demonstrated no significant differences in both subgroups (all P > 0.05). Among the nine formulas, Kane, Holladay 1, and EVO 2.0 demonstrated superior refractive outcomes in PACG eyes.

Personality Prediction System Using Machine Learning

A personality prediction system leverages advanced data analysis techniques to assess and predict an individual's personality traits based on diverse inputs such as text, voice, behaviour, and biometric data. These systems typically utilize psychological models, like the Big Five Personality Traits or Myers-Briggs Type Indicator (MBTI), to derive insights from patterns in the data. Text-based prediction systems use natural language processing (NLP) to analyze written or spoken communication, while voice- based systems analyze vocal attributes such as tone and pitch. Behavioral and biometric data further enhance the accuracy of these systems, with applications spanning areas like human- computer interaction, marketing, recruitment, and mental health. With the aid of artificial intelligence (AI) and machine learning, these systems are increasingly capable of delivering personalized insights, offering the potential for a wide range of applications from customer engagement to psychological well-being. This abstract outline the core mechanisms, applications, and future directions of personality prediction systems, highlighting their potential to transform how individuals are understood and interacted with in both digital and real-world contexts.

Personality Prediction System Using Machine Learning

A personality prediction system leverages advanced data analysis techniques to assess and predict an individual's personality traits based on diverse inputs such as text, voice, behaviour, and biometric data. These systems typically utilize psychological models, like the Big Five Personality Traits or Myers-Briggs Type Indicator (MBTI), to derive insights from patterns in the data. Text-based prediction systems use natural language processing (NLP) to analyze written or spoken communication, while voice-based systems analyze vocal attributes such as tone and pitch. Behavioral and biometric data further enhance the accuracy of these systems, with applications spanning areas like human-computer interaction, marketing, recruitment, and mental health. With the aid of artificial intelligence (AI) and machine learning, these systems are increasingly capable of delivering personalized insights, offering the potential for a wide range of applications from customer engagement to psychological well-being. This abstract outline the core mechanisms, applications, and future directions of personality prediction systems, highlighting their potential to transform how individuals are understood and interacted with in both digital and real-world contexts.

Facial recognition technology in law enforcement: Regulating data analysis of another kind

Facial recognition technology (FRT) has emerged as a powerful tool for law enforcement, enabling the automated identification of individuals based on their unique facial features. Authorities have more and more made use of the technology to enhance criminal investigations through the analysis of images and video footage. In view of its increased use in Europe, this paper explores the legal implications of FRT in law enforcement under EU law and evaluates approaches to regulation. FRT use constitutes biometric data processing and comes with a particularly sensitive analysis of data. Its specific nature is grounded in the creation of a new (biometric) quality of data in order to subsequently compare for matches. Due to its impact on fundamental rights, this approach differs from conventional forensic analyses and must be appropriately regulated. Such regulation should consider the multiple data processing steps and reflect each step's impact on fundamental rights. From this procedural stance, the shortcomings of the EU Artificial Intelligence Act (AI Act) become evident. The AI Act contains specific rules for biometric AI systems but does not provide the necessary legal bases to justify FRT use by law enforcement. Without a comprehensive legal framework, such use is not permitted. This article provides concrete guidelines for addressing such regulation.

Exploring Emotional Transitions Triggered by Color Changes: A Multidimensional Analysis

This study investigates the emotional responses triggered by color changes, utilizing both discrete and continuous video stimuli to explore the theory that color influences emotional states. Nineteen participants from the IHHSJF-30201 class were exposed to color pairs derived from the Berkeley Color Project 37 (BCP-37), specifically examining transitions between saturated and medium hues of red, blue, yellow, and purple. Through Spearmans Rho correlation analysis and differential emotion intensity measurements, the study evaluates how sudden versus gradual color changes affect emotional perception. Results demonstrate significant differences in emotional responses between the discrete and continuous color transition groups, highlighting the impact of transition mode on emotional dynamics. The findings support existing theories on the relationship between color and emotion and suggest the potential for personalized color applications to enhance user experience in digital interfaces. Future research directions include integrating machine learning techniques and expanding biometric data collection to further refine the understanding of color-emotion interactions and their practical applications.

Physical Demand Assessment of Volunteer Firefighters During Wildland Firefighting

Wildland firefighting is physically and mentally demanding. The aerobic capacity of firefighters is important due to the demands of the activity and the associated occupational risks. The main objectives of this study were to identify and characterise the physically demanding tasks undertaken by volunteer firefighters during wildland fires (real work conditions). A total of 125 firefighters replied to a survey about sociodemographic, biometric data, and work fitness assessment. A group of 23 was evaluated in a physical stress test using a VO2peak protocol to determine maximum oxygen consumption and ventilatory thresholds. The physical demands and physiological responses were collected during the operations at the firefront (n = 21). The results revealed that wildland firefighting entails physical demands that exceed established reference values, with maximum oxygen uptake exceeding 40%. The cardiovascular strain is particularly notable in tasks performed near the firefront, reflecting fatigue. The physical and cardiac demands associated with forest fire fighting have been demonstrated to contribute to occupational illnesses with prolonged exposure. This study underscores the imperative for interventions to enhance the identification and real-time monitoring of physiological parameters to enhance firefighters’ overall health and well-being.

A residual deep learning network for smartwatch-based user identification using activity patterns in daily living

User identification is a critical aspect of smartwatch security, ensuring that only authorized individuals gain access to sensitive information stored on the device. Conventional methods like passwords and biometrics have limitations, such as the risk of forgetting passwords or the potential for biometric data to be compromised. This research proposes a novel approach for user identification on smartwatches by analyzing activity patterns using a hybrid residual neural network called Att-ResBiLSTM. The proposed method leverages unique patterns of user interactions with their smartwatches, including application usage, typing behavior, and motion sensor data, to create an individualized user profile. Employing a deep learning network specifically designed for wearable devices, the system can reliably and promptly identify users by analyzing their activity patterns. The Att-ResBiLSTM architecture comprises three key components: convolutional layers, ResBiLSTM, and an attention layer. The convolutional layers extract spatial features from the pre-processed data. At the same time, the ResBiLSTM component captures long-term dependencies in the time-series data by combining the advantages of bidirectional long short-term memory (BiLSTM) and residual connections. The attention mechanism enhances the final recognition features by selectively prioritizing the most informative elements of the input data. The Att-ResBiLSTM model is trained and evaluated using a diverse dataset of user activity patterns. Experimental results demonstrate that the proposed approach achieves remarkable accuracy in user identification, with an accuracy rate of 98.29% and the highest F1-score of 98.24%. The research also conducts a comparative analysis to assess the efficacy of accelerometer data versus gyroscope data, revealing that combining both sensor modalities improves user identification performance. The proposed methodology provides a reliable and user-friendly alternative to conventional user authentication techniques for smartwatches. This approach leverages activity patterns and a hybrid residual deep learning network to offer a robust and efficient solution for user identification based on smartwatch data, thereby enhancing the overall security of wearable devices.

THE GENETIC VARIABILITY IN TOMATO GENOTYPES L-11/53 AND V 5 GROWN IN PROTECTED SPACES

The tomato genotypes (L-11/53 and V 5) were subjected to an analysis regarding the variability of the main quantitative fruit characters (fruit weight, fruit height, pericarp thickness). The registered biometric data were statistically processed, calculating for each analyzed character the mean (x̄), the standard deviation (s), the coefficient of variability (s%) and the range of variability (k = x̄ ± s).The calculation and analysis of the variability of the characters studied in the tomato genotypes L-11/53 and V 5, revealed on average in the two years of the study a small variability for the height of the fruit (s% = 9.37% for L-11/53 and 7.52% for V 5) and medium for pericarp thickness (s% =16.59% for L-11/53 and 15.47% for V 5).The values of the calculated statistical indices, of the characters taken in the study, require the continuation of the selection process in order to maintain them within the specific limits of variability.

Evolving dementia care: An explorative study on the lived experience of older adults living with dementia in nursing homes using observational and biometric sensor data.

This study explores the lived experiences of older adults with dementia in Dutch nursing homes, focusing on daily activities and emotional responses. With a growing number of older adults with dementia, gaining a deeper understanding of their lived experience is imperative. Using a mixed-method narrative approach involving observations, informal interviews, and physiological monitoring through wearable sensors, the study engaged eight participants in psychogeriatric wards across two Dutch nursing homes. Observations and interviews aimed to provide context to daily activities, while wearable sensors tracked emotional responses through heart rate (HR) and heart rate variability (HRV). Key activities included eating, drinking, communication, mobility, and inactivity. Positive experiences were consistently observed during eating and drinking and communication, respectively influenced by the nursing home's social and organizational structures and social and personal contexts. In contrast, mobility and inactivity exhibited diverse physiological responses, reflecting a range of stress, concentration, or relaxation. This study offers valuable insights into the lived experiences of older adults with dementia in nursing homes. It highlights the generally positive nature of eating and drinking, shaped by social and organizational factors. Communication's impact varies with individual context. The study also reveals a complex interplay of emotions during activities related to mobility and inactivity, as evidenced by diverse physiological responses. Regarding implications for dementia care, the study emphasizes the need to redefine 'inactivity' as 'under-stimulation,' assess appropriate (in)activity levels, and acknowledge the significance of the nursing home's physical and organizational context. This redefinition should distinguish between 'physical' and 'mental' inactivity, address concerns related to under-stimulation, and cater to individual preferences. Recognizing the residents' restricted environment and reliance on care professionals and volunteers underscores the urgency of tailored approaches. Addressing these implications can provide fresh perspectives for evolving dementia care, creating a more supportive environment that promotes well-being.

Integrated Health Monitoring System using Fingerprint and Disease Risk Prediction

Recent developments in machine learning and biometric systems have had a big influence on healthcare applications. In order to provide a holistic approach to health monitoring, this research introduces a unique method that combines disease risk prediction with fingerprint-based blood group recognition. Based on user-provided health data, the system uses machine learning algorithms to determine the risk of common illnesses including diabetes, cardiovascular disease, and chronic kidney disease (CKD) and convolutional neural networks (CNNs) to identify blood type from fingerprint photos. Through the integration of fingerprint biometric data with health risk modelling, the suggested approach seeks to increase the precision and usability of health forecasts. The system's effectiveness is demonstrated by the evaluation's excellent classification accuracy for blood groups and trustworthy estimates of illness risk.This work demonstrates the possibility of integrating biometric data with predictive health models and offers a promising step toward customized healthcare solutions

Multimodal Biometric Authentication System for Military Weapon Access: Face and ECG Authentication

Unimodal or Single factor biometric systems refer to biometric systems that employ only one form of biometric data to authenticate an individual’s identity. These kinds of biometrics are susceptible to higher error rates and security vulnerabilities because it relays on a single trait for authentication. To overcome this, multimodal biometrics method is proposed. Multi-modal biometric system can authenticate more than once and some advantages include; highaccuracy, low error rate, and large population coverage. These biometrics systems increase integrity and privacy since it will contain several biometric features of every customer. So, here designed a multimodal biometrics project utilizing deep learning to enhance authentication security by combining face and Electrocardiogram(ECG) signals. VGG-16 model, a deep learning architecture used to capture complex patterns in accurate individual identification with both ECG and Facial data. The high-resolution convolutional filters capture the intricate details of the face and ECG waveform, ensuring high accuracy in distinguishing different individuals.

Exploring the influence of intensive management practices on recreational hunter satisfaction: a case study of red deer trophy hunting in Spain

ABSTRACT Recreational hunting, especially big game trophy hunting, has a significant impact on large areas and requires specific wildlife management strategies. However, because the pursuit of maximum hunter satisfaction can jeopardize species conservation, it is crucial to identify the factors that determine recreational trophy hunter satisfaction. We investigated these factors in southern Spain by attending 21 dog-driven Iberian red deer hunts over seven hunting seasons. We collected geographic and biometric data from 556 hunted specimens and conducted 159 face-to-face surveys with hunters. Based on partial least squares path models, our findings indicate that overall satisfaction is positively related to the dimensions of achievement, appreciation, and service. Contextual variables, including hunter experience, hunting scenarios, and individual and group hunting bags, showed varying effects on these satisfaction dimensions. Management decisions significantly influenced multiple dimensions of hunter satisfaction, with potential implications for conservation in our study system and broader considerations for natural game management versus canned hunting practices.

Big Data Methods and Analytics for Text, Audio, Video, and Social Media Data Concepts: Methods and Analytics for Text, Audio, Video, and Social Media Data

This paper provides a unified description of big data by integrating ideas from academics and practitioners. The primary focus of the paper is the analytical methods applied to big data. The focus this study places on analytics for unstructured data—which accounts for 95% of big data—makes it particularly noteworthy. The massive volumes of data produced by various machine-driven automated systems, including statistical, text, audio, video, sensor, and biometric data, are collectively referred to as "big data." In this essay, we consider the dimensions of various types of large data while addressing their challenges, applications, and problems. In this section, we'll cover social media data analytics along with content-based, text, audio, and video analytics.

Synthesis and application of Ho³⁺ doped BaGd₂ZnO₅ nanophosphors for enhanced latent fingerprint development and poroscopy

In this study, Ho³⁺-doped BaGd₂ZnO₅ (1–11 mol%) nanophosphors (BGZO:Ho3+ NPs) were synthesized through combustion synthesis, utilizing Spirulina leaf extract as a natural green fuel. Luminescence studies revealed that the BGZO:Ho³⁺ phosphors exhibit a strong green emission primarily resulting from the 5S2→5I8 transition of Ho³⁺ ions. The optimal doping concentration was found to be 7 mol % Ho³⁺, which yielded the highest luminescence efficiency. Furthermore, the CIE chromaticity coordinates for BGZO:7Ho³⁺ were accurately determined to be (0.2595, 0.7290), with a color purity (CP) of 99.98 %. These results indicate the potential of this material for producing high-quality green emissions suitable for solid-state lighting and display applications. Optimized BGZO:Ho3+ NPs were utilized for latent fingerprints (LFPs) development via the powder dusting method. Under 365 nm UV light, the NPs effectively revealed Level I-III fingerprints (FPs) details, including ridge patterns, minutiae, and sweat pore features, on various substrates such as glass, plastic, and metal. The high luminescence of BGZO:Ho3+ NPs under UV illumination offers a sensitive and non-destructive method for enhancing FPs visibility, making it a promising tool for forensic applications. In addition, this study focuses on FPs poroscopy, examining the detailed pore structure of LFPs for forensic identification. Using advanced imaging techniques, we analyzed sweat pore distribution, size, and shape across various substrates and conditions. A detailed poroscopic analysis of LFPs, focusing on key parameters such as pore interspacing (165–332 μm), pore size (4140–9956 μm2), shapes (elliptical, rhomboid, triangular, square and rectangular) and pore angle (167°–179°). Further, a mathematical model was developed using Python-based software to enable precise and accurate analysis of FPs, enhancing clarity and identification accuracy, supporting the uniqueness of FPs beyond ridge patterns. The results demonstrate the potential of poroscopy for enhancing FPs analysis by offering an additional layer of precise biometric data.

A kinematic dataset of locomotion with gait and sit-to-stand movements of young adults

Kinematic data is a valuable source of movement information that provides insights into the health status, mental state, and motor skills of individuals. Additionally, kinematic data can serve as biometric data, enabling the identification of personal characteristics such as height, weight, and sex. In CeTI-Locomotion, four types of walking tasks and the 5 times sit-to-stand test (5RSTST) were recorded from 50 young adults wearing motion capture (mocap) suits equipped with Inertia-Measurement-Units (IMU). Our dataset is unique in that it allows the study of both intra- and inter-participant variability with high quality kinematic motion data for different motion tasks. Along with the raw kinematic data, we provide the source code for phase segmentation and the processed data, which has been segmented into a total of 4672 individual motion repetitions. To validate the data, we conducted visual inspection as well as machine-learning based identity and action recognition tests, achieving 97% and 84% accuracy, respectively. The data can serve as a normative reference of gait and sit-to-stand movements in healthy young adults and as training data for biometric recognition.

Bus Network Adjustment Pre-Evaluation Based on Biometric Recognition and Travel Spatio-Temporal Deduction

A critical component of bus network adjustment is the accurate prediction of potential risks, such as the likelihood of complaints from passengers. Traditional simulation methods, however, face limitations in identifying passengers and understanding how their travel patterns may change. To address this issue, a pre-evaluation method has been developed, leveraging the spatial distribution of bus networks and the spatio-temporal behavior of passengers. The method includes stage of travel demand analysis, accessible path set calculation, passenger assignment, and evaluation of key indicators. First, we explore the actual passengers’ origin and destination (OD) stop from bus card (or passenger Code) payment data and biometric recognition data, with the OD as one of the main input parameters. Second, a digital bus network model is constructed to represent the logical and spatial relationships between routes and stops. Upon inputting bus line adjustment parameters, these relationships allow for the precise and automatic identification of the affected areas, as well as the calculation of accessible paths of each OD pair. Third, the factors influencing passengers’ path selection are analyzed, and a predictive model is built to estimate post-adjustment path choices. A genetic algorithm is employed to optimize the model’s weights. Finally, various metrics, such as changes in travel routes and ride times, are analyzed by integrating passenger profiles. The proposed method was tested on the case of the Guangzhou 543 route adjustment. Results show that the accuracy of the number of predicted trips after adjustment is 89.6%, and the predicted flow of each associated bus line is also consistent with the actual situation. The main reason for the error is that the path selection has a certain level of irrationality, which stems from the fact that the proportion of passengers who choose the minimum cost path for direct travel is about 65%, while the proportion of one-transfer passengers is only about 50%. Overall, the proposed algorithm can quantitatively analyze the impact of rigid travel groups, occasional travel groups, elderly groups, and other groups that are prone to making complaints in response to bus line adjustment.

Rethinking Contemporary Deep Learning Techniques for Error Correction in Biometric Data

Rethinking Contemporary Deep Learning Techniques for Error Correction in Biometric Data

Mympnvoice - a Novel Smartphone App for Monitoring Patient Reported Outcomes and Biometric Data in Patients with Myeloproliferative Neoplasms

Mympnvoice - a Novel Smartphone App for Monitoring Patient Reported Outcomes and Biometric Data in Patients with Myeloproliferative Neoplasms