Verification Of Model Research Articles

Deep learning based bio-metric authentication system using a high temporal/frequency resolution transform

IntroductionIdentity verification plays a crucial role in modern society, with applications spanning from online services to security systems. As the need for robust automatic authentication systems increases, various methodologies—software, hardware, and biometric—have been developed. Among these, biometric modalities have gained significant attention due to their high accuracy and resistance to falsification. This paper focuses on utilizing electrocardiogram (ECG) signals for identity verification, capitalizing on their unique, individualized characteristics.MethodsIn this study, we propose a novel identity verification framework based on ECG signals. Notable datasets, such as the NSRDB and MITDB, are employed to evaluate the performance of the system. These datasets, however, contain inherent noise, which necessitates preprocessing. The proposed framework involves two main steps: (1) signal cleansing to remove noise and (2) transforming the signals into the frequency domain for feature extraction. This is achieved by applying the Wigner-Ville distribution, which converts ECG signals into image data. Each image captures unique cardiac signal information of the individual, ensuring distinction in a noise-free environment. For recognition, deep learning techniques, particularly convolutional neural networks (CNNs), are applied. The GoogleNet architecture is selected for its effectiveness in processing complex image data, and is used for both training and testing the system.ResultsThe identity verification model achieved impressive results across two benchmark datasets. For the NSRDB dataset, the model achieved an accuracy of 99.3% and an Equal Error Rate (EER) of 0.8%. Similarly, for the MITDB dataset, the model demonstrated an accuracy of 99.004% and an EER of 0.8%. These results indicate that the proposed framework offers superior performance in comparison to alternative biometric authentication methods.DiscussionThe outcomes of this study highlight the effectiveness of using ECG signals for identity verification, particularly in terms of accuracy and robustness against noise. The proposed framework, leveraging the Wigner-Ville distribution and GoogleNet architecture, demonstrates the potential of deep learning techniques in biometric authentication. The results from the NSRDB and MITDB datasets reflect the high reliability of the model, with exceptionally low error rates. This approach could be extended to other biometric modalities or combined with additional layers of security to enhance its practical applications. Furthermore, future research could explore additional preprocessing techniques or alternative deep learning architectures to further improve the performance of ECG-based identity verification systems.

ON THE INITIAL VERIFICATION OF THE CRYSTAL STRUCTURES OF THE ARGYRODITE FAMILY

The crystal structures of the phases belonging to the scientifically and technologically important family of argyrodites of the general chemical formula Am+(12–n–x)/mBn+X2–6–xY–x (where A = Li+; Cu+, Ag+, Cd2+, Hg2+…; B = Ga3+, Si4+, Ge4+, Sn4+, P5+, As5+…; X = O2–; S2–, Se2–, Te2–; Y = Cl–, Br–, I–; 0 ≤ x ≤ 1) are characterized by high mobility and disorder of the cationic sublattice (substructure) A. This feature of argyrodites makes them promising solid-state ionic conductors, but significantly complicates the X-ray analysis of argyrodite phases due to the inability to reliably predict the positions of A ions in the unit cell of the crystal structure of a particular argyrodite sample and the site occupancy factors of these positions. The analysis of the published structures of argyrodites has revealed the fact that the positions of typical B cations and their X ligands in the tetrahedral environment [BX4] are fully occupied by the corresponding ions, which makes it possible to perform an initial verification of the structural models of the argyrodite phases (already published in the scientific literature or newly obtained) within the framework of the bond valence model (BVM) – by calculating the bond valence sums for the B cations from the interatomic distances dBX in the coordination tetrahedra [BX4]. In addition to the initial verification of structural models of argyrodite phases, the use of the BVM with the numerical parameters recommended in this work allows researchers to create reliable starting partial structural models of argyrodite phases for their further refinement by X-ray diffraction analysis, as well as to stabilize the process of refining the crystal structure by imposing soft restraints on the deviation of the calculated interatomic distances dBX from the predicted distances in the [BX4] tetrahedra.

Reverb and Noise as Real-World Effects in Speech Recognition Models: A Study and a Proposal of a Feature Set

Reverberation and background noise are common and unavoidable real-world phenomena that hinder automatic speaker recognition systems, particularly because these systems are typically trained on noise-free data. Most models rely on fixed audio feature sets. To evaluate the dependency of features on reverberation and noise, this study proposes augmenting the commonly used mel-frequency cepstral coefficients (MFCCs) with relative spectral (RASTA) features. The performance of these features was assessed using noisy data generated by applying reverberation and pink noise to the DEMoS dataset, which includes 56 speakers. Verification models were trained on clean data using MFCCs, RASTA features, or their combination as inputs. They validated on augmented data with progressively increasing noise and reverberation levels. The results indicate that MFCCs struggle to identify the main speaker, while the RASTA method has difficulty with the opposite class. The hybrid feature set, derived from their combination, demonstrates the best overall performance as a compromise between the two. Although the MFCC method is the standard and performs well on clean training data, it shows a significant tendency to misclassify the main speaker in real-world scenarios, which is a critical limitation for modern user-centric verification applications. The hybrid feature set, therefore, proves effective as a balanced solution, optimizing both sensitivity and specificity.

Model verification of real-time and distributed stream processing architecture

Model verification of real-time and distributed stream processing architecture

Analysing Rural Development Models Based on Intangible Assets and Socio-Economic Development

Despite the existence of a variety of conceptual approaches to rural development, there is a lack of methods that take into account intangible assets, such as, for example, social capital, leadership, and local identity. A more effective design of the rural development strategy may be achieved by uncovering knowledge regarding the manifestation of various intangible resources. Territorial development policies, both in terms of the level of socio-economic development and the presence of intangible resources in rural areas, are investigated in this study. The main objective is to determine how intangible resources manifest in specific empirical models of development policy for rural settlements. A novel ensemble of indices and indicators of socio-economic development and the manifestation of intangible resources, calculated based on the method of analytical hierarchies and frequency analysis, are provided. These allow for a comprehensive study of the development of rural areas by clustering settlements with a similar level of development. Patterns and deficits of resources in rural settlements are analysed according to empirical models. Verification of the empirical models is carried out by assessing the level of socio-economic development and indicators of intangible resources for 12 rural settlements in the south of Russia. Therefore, several groups of factors of intangible resources splitting the factors related (reflect the current state) and unrelated (reflect the development potential) to the socio-economic development of rural settlements have been specified.

Verification and Validation of Pavement Models

Verification and Validation of Pavement Models

Construction and verification of prediction model for postoperative hypokalemia in patients with oral cancer.

This study aimed to explore the risk factors of postoperative hypokalemia in patients with oral cancer and to provide a basis for preventing and controlling postoperative hypokalemia. We included 366 patients undergoing oral cancer surgery in the Department of Head and Neck Oncology, West China Hospital of Stomatology, Sichuan University from January 2022 to August 2022. Univariate and multivariate analyses were used to determine the risk factors of postoperative hypokalemia. The receiver operation characteristic (ROC) curve was used to quantify the effectiveness of the factors. A nomogram of the risk factors for postoperative hypokalemia in oral cancer patients was developed and validated. A total of 224 patients (61.20%) had postoperative hypokalemia, the lowest serum potassium level (3.50±0.35) mmol/L on the 4th day after surgery, and the highest incidence of hypokalemia (54.68%). Variables with P<0.05 in the univariate analysis were quantified by ROC curve followed by multivariate logistic regression analysis. Results showed an independent correlation with postoperative hypokalemia as follows: preoperative serum potassium<3.87 mmol/L (P=0.008), preoperative serum calcium<2.31 mmol/L (P=0.033), preoperative PNI<49.16 (P=0.032), postoperative drainage volume>264.25 mL (P=0.002). The above variables were constructed into a postoperative hypokalemia risk nomogram and verified, and a good degree of fit was found. The independent risk factors for postoperative hypokalemia in patients with oral cancer were as follows: preoperative serum potassium<3.87 mmol/L, preoperative serum calcium<2.31 mmol/L, preoperative PNI<49.16, and postoperative drainage volume>264.25 mL. Clinical attention should be paid to managing the above high-risk patients. Preventive potassium supplementation should be performed as soon as possible to reduce hypokalemia occurrence.

Network Pharmacology, Molecular Docking and Experimental Verification Revealing the Mechanism of Fule Cream against Childhood Atopic Dermatitis.

The Fule Cream (FLC) is an herbal formula widely used for the treatment of pediatric atopic dermatitis (AD), however, the main active components and functional mechanisms of FLC remain unclear. This study performed an initial exploration of the potential acting mechanisms of FLC in childhood AD treatment through analyses of an AD mouse model using network pharmacology, molecular docking technology, and RNA-seq analysis. The main bioactive ingredients and potential targets of FLC were collected from the Traditional Chinese Medicine Systems Pharmacology Database (TCMSP) and SwissTargetPrediction databases. An herb-compound-target network was built using Cytoscape 3.7.2. The disease targets of pediatric AD were searched in the DisGeNET, Therapeutic Target Database (TTD), OMIM, DrugBank and GeneCards databases. The overlapping targets between the active compounds and the disease were imported into the STRING database for the construction of the protein-protein interaction (PPI) network. Gene Ontology (GO) enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses of the intersection targets were performed, and molecular docking verification of the core compounds and targets was then performed using AutoDock Vina 1.1.2. The AD mouse model for experimental verification was induced by MC903. The herb-compound-target network included 415 nodes and 1990 edges. Quercetin, luteolin, beta-sitosterol, wogonin, ursolic acid, apigenin, stigmasterol, kaempferol, sitogluside and myricetin were key nodes. The targets with higher degree values were IL-4, IL-10, IL-1α, IL-1β, TNFα, CXCL8, CCL2, CXCL10, CSF2, and IL-6. GO enrichment and KEGG analyses illustrated that important biological functions involved response to extracellular stimulus, regulation of cell adhesion and migration, inflammatory response, cellular response to cytokine stimulus, and cytokine receptor binding. The signaling pathways in the FLC treatment of pediatric AD mainly involve the PI3K-Akt signaling pathway, cytokine‒cytokine receptor interaction, chemokine signaling pathway, TNF signaling pathway, and NF-κB signaling pathway. The binding energy scores of the compounds and targets indicate a good binding activity. Luteolin, quercetin, and kaempferol showed a strong binding activity with TNFα and IL-4. This study illustrates the main bioactive components and potential mechanisms of FLC in the treatment of childhood AD, and provides a basis and reference for subsequent exploration.

Analysis of Clinical Characteristics and Risk Factors for Severe Influenza A and Influenza B in Children.

The goal of this study was to develop and validate an online dynamic nomogram system for early differential diagnosis of influenza A and B. Patients with severe influenza A and B admitted to Henan Children's Hospital from January 2019 to January 2022 were used as the modeling group (n = 161), and patients admitted from January to September 2023 were used as the validation group (n = 52). Univariate logistic regression and multivariate logistic regression were used to identify the risk variables of severe influenza A and B in children in the modeling group. The selected variables were used to build the nomogram, and the C-index, decision curve analysis, calibration curves, and receiver operating characteristic curves were used to assess the differentiation, calibration of the models, and external validation of the above models with validation group data. Fever for >3 days, vomiting, lymphocyte count (LY), and duration from onset to hospitalization were independent factors for the identification of severe influenza A and B. We created a dynamic nomogram (https://ertong.shinyapps.io/influenza/) that can be accessed online. The C-index was 0.92. In the modeling group, the AUC of the prediction model was 0.92 (95% CI, 0.87-0.98), the calibration curve showed a good fit between the predicted probability and the actual probability, with high comparability, and the decision curve analysis showed that the nomogram model had significant clinical benefits. The application of this model in external verification predicts that the AUC of the verification group is 0.749 (95% CI, 0.61-0.88), and the validation results were in good agreement with reality. Fever for >3 days, vomiting, lymphocyte count, and duration from onset to hospitalization have an impact on the differentiation of severe influenza A from severe influenza B. The prediction value and clinical benefit of the nomogram model are satisfactory.

Mathematical model and experimental verification of self-centering energy dissipative brace equipped with disc spring and wedge block

The novel self-centering energy dissipation brace composed of disc spring group and wedge block group (DW-SCB) is introduced. The working mechanism of the DW-SCB and the force mechanism of each component are described. The stress analysis of the disc spring group (DSG) and the wedge block group (WBG) were carried out, and the DW-SCB theoretical prediction model was established. Three specimens with different disc spring preload lengths were fabricated, tested, and discussed. Furthermore, the established theoretical model was verified, and the theoretical model correction method considering the processing and assembly errors of the DSG was proposed. The tested data show that the hysteresis curve of DW-SCB is a typical flag shape, and there is almost no residual displacement after multiple loading. An increase in the preload length of the disc spring increases the yield load and bearing capacity of the DW-SCB but has no change on the stiffness of DW-SCB. All the components of the three specimens were not damaged after multiple loadings, which show that the DW-SCB has stable multiple seismic performance and recoverability. Significant, although the machining error of the disc spring leads to a large error between the experimental and theoretical curve of the DSG, the error correction method of the DSG proposed in this study can improve the prediction accuracy of the theoretical model, making the DW-SCB theoretical prediction model more accurate and reliable. The theoretical model considering the error of DSG can better predict the stiffness and load of DW-SCB, which can provide a reference for engineering design and application.

Speaker Verification Model USING LST

Abstract: This project presents a speaker verification model using LSTM networks to detect the authenticity of voices, distinguishing between real and deepfake audio. With the growing threat of AI-generated voices being used for identity theft and misinformation, this model aims to address those risks. The system uses MFCCs (Mel-frequency cepstral coefficients) to capture key speech features and distinguish real voices from altered ones. The dataset includes both real and deepfake samples from well-known public figures like Joe Biden and Donald Trump, with techniques like time-stretching and pitch-shifting used to improve the model’s performance. Built with LSTM layers and trained for 50 epochs using the Adam optimizer, the model achieved an accuracy of 84.62%, proving effective in detecting fake voices. This LSTM-based model offers a valuable solution for enhancing voice authentication systems, especially in critical areas like security systems, online transactions, and biometric authentication. Its robust performance demonstrates the potential to counter the rising threat of deepfake technology

High-fidelity experimental model verification for flow in fractured porous media

Mixed-dimensional mathematical models for flow in fractured media have been prevalent in the modeling community for almost two decades, utilizing the explicit representation of fractures by lower-dimensional manifolds embedded in the surrounding porous media. In this work, for the first time, direct qualitative and quantitative comparisons of mixed-dimensional models are drawn against laboratory experiments. Dedicated displacement experiments of steady-state laminar flow in fractured media are investigated using both high-resolution PET images as well as state-of-the-art numerical simulations.

Formulation and verification of an anisotropic damage plasticity constitutive model for plain concrete

Formulation and verification of an anisotropic damage plasticity constitutive model for plain concrete

Verification of Numerical Models of Steel Bar Coverings Using Experimental Tests—Preliminary Study

In the design of metal bar coverings, the key problem is to correctly determine the numerical model of the analyzed structure. The description of numerical models may differ from the actual, real behavior of the structure. Therefore, there is a need to verify and calibrate them using experimental studies. The aim of this research will be to verify and assess the accuracy of the numerical model of a metal bar roof by conducting experimental studies. A series of repeatable experimental tests will be conducted on the structure model to determine the path of static equilibrium and the form of stability loss of the steel covering. During the test, as the load increases, data will be collected on the displacements of nodes. The displacements of the nodes will be verified using precise triangulation laser sensors and electronic sensors. Based on the results of the tests, conclusions will be drawn regarding the accuracy of the numerical models. Comparison of the results obtained from the numerical models with the experimental data will allow for the identification of possible discrepancies and understanding how the numerical models can be improved. This in turn will contribute to the development of more advanced and more accurate methods for the analysis of metal bar roof structures in the future.

Coupled theoretical modelling for the photoelectric performance by the concave-bent flexible PV module

Flexible PV module can fit with complex building skins and provide electricity for the building users. However, for the concave bent PV module, the special structure will cast shadow on itself, resulting in power loss during the working conditions, which is rarely investigated in previous studies. Combined optical-electrical-thermal model is decoupled to describe the realistic physical field and predict the concave module's electrical power output and working temperature. The beam shading ratio (BSR) and the diffuse shading ratio (DSR) are proposed based on the microfacet subdivision, which describes the real-time solar irradiance distribution and quantify the influence of self-shadow on the photoelectric performance by the concave-bent module under dynamic real-time working conditions. The concave PV module with the longitudinal/lateral layout is constructed and outdoor experiments are conducted to collect the data for the theoretical model verification. The parametric analysis is carried out to investigate the influence of inclination, curvature, and azimuth, demonstrating that increasing inclination and curvature angles raise power loss due to shading. Weather data of four cities are imported into the model to conduct annual performance simulation with longitudinal/lateral installation respectively. The model established in this paper has significant value for performance prediction in complex surface photovoltaic systems.

Development of Analytical Model to Describe Reflectance Spectra in Leaves with Palisade and Spongy Mesophyll.

Remote sensing plays an important role in plant cultivation and ecological monitoring. This sensing is often based on measuring spectra of leaf reflectance, which are dependent on morphological, biochemical, and physiological characteristics of plants. However, interpretation of the reflectance spectra requires the development of new tools to analyze relations between plant characteristics and leaf reflectance. The current study was devoted to the development, parameterization, and verification of the analytical model to describe reflectance spectra of the dicot plant leaf with palisade and spongy mesophyll layers (on the example of pea leaves). Four variables (intensities of forward and backward collimated light and intensities of forward and backward scattered light) were considered. Light reflectance and transmittance on borders of lamina (Snell's and Fresnel's laws), light transmittance in the palisade mesophyll (Beer-Bouguer-Lambert law), and light transmittance and scattering in the spongy mesophyll (Kubelka-Munk theory) were described. The developed model was parameterized based on experimental results (reflectance spectra, contents of chlorophylls and carotenoid, and thicknesses of palisade and spongy mesophyll in pea leaves) and the literature data (final R2 was 0.989 for experimental and model-based reflectance spectra). Further model-based and experimental investigations showed that decreasing palisade and spongy mesophyll thicknesses in pea leaves (from 35.5 to 25.2 µm and from 58.6 to 47.8 µm, respectively) increased reflectance of green light and decreased reflectance of near-infrared light. Similarity between model-based and experimental results verified the developed model. Thus, the model can be used to analyze leaf reflectance spectra and, thereby, to increase efficiency of the plant remote and proximal sensing.

Model Checking and Verification of Synchronisation Properties of Cobot Welding

Model Checking and Verification of Synchronisation Properties of Cobot Welding

Vision-based identification of cable tensions and finite element model verification of a cable-stayed bridge

Vision-based identification of cable tensions and finite element model verification of a cable-stayed bridge

Development and verification of material models in modeling of wave strain hardening and additive synthesis processes

BACKGROUND: The creation of competitive machine parts capable of withstanding standard and increased operational loads is an urgent task in mechanical engineering. Developing additive synthesis technologies together with strengthening technologies make it possible to create such products with high load-bearing capacity. However, to improve the efficiency of these technologies, it is necessary to create theoretical models of the processes taking place. The article presents the results of the first stage of creating complex theoretical models of the combined 3DMP process and wave strain hardening (WSH) required for designing technological processes for manufacturing engine parts and brake systems of automotive equipment. . AIMS: Creation and assessment of the adequacy of material models used in finite element modeling of additive synthesis processes with subsequent hardening. MATERIALS AND METHODS: Theoretical models of the material were created in the ANSYS software package, which allows for multidisciplinary calculations. The experimental data required for preparing the models were obtained by testing tensile samples manufactured using standardized methods. The hardness of materials was studied using a KB 30S automatic hardness tester. The adequacy of additive synthesis modeling was assessed based on the distribution of temperature fields. The adequacy of material models for the VDU process was assessed based on the sizes of individual plastic indentations and the distribution diagrams of the depth and degree of hardening in the surface layer. RESULTS: Theoretical models of the following materials were developed: steel, stainless steel, bronze alloy, titanium alloy, aluminum alloy. The theoretical data obtained from the modeling results have a high level of significance. The studies were conducted for various thermal (in the range from +20ºС to +800ºС) and deformation modes. Graphical results of theoretical and experimental studies allow us to obtain a qualitative assessment of the processes under study with the required accuracy. CONCLUSIONS: As a result of the assessment of the adequacy of the developed models, it was established that the discrepancy between the empirical and theoretical data does not exceed 7.4%. The obtained models of materials are statistically significant and can be correctly applied in further studies.

Development of an FEM for the Combined Electromagnetic and Hydraulic Forming Process Based on Experimental Data

Electrohydraulic forming (EHF) which demonstrates reduced bouncing effect, formation in narrow areas, and no effect on the electrical conductivity of the blank can overcome the shortcomings of deep drawing and electromagnetic forming. However, considerable time is involved in evaluating the possibility of forming a specific part through experiments. Developing an accurate finite element model can reduce the opportunity costs of an experiment by reducing unnecessary trial and error in forming a specific part. In this study, the chamber, die, and blank components of the EHF experimental equipment in our laboratory were reverse-modeled using CATIA V5R18. Subsequently, the IGES format of the components was imported into LS-DYNA R12, and an FEM model to simulate the EHF experiment was constructed. The experimental and simulation results of nine cases, based on the SUS430 material, input voltage, and blank thickness, were compared for model verification. The forming results for all cases in the constructed finite element analysis model nearly matched the experimental results. Moreover, the linear increase in the blank thickness with input voltage and thickness was simultaneously confirmed. In a computing environment using a 4.3 GHz, 24-Core CPU and 64 GB memory, the time required for one finite element analysis was approximately 1 h.