Themodel Parameters Research Articles

Classification of Diabetic Retinopathy using Deep Learning

Abstract: Diabetic retinopathy, a potentially fatal retinal disease, occurs in individuals with diabetes, causing vision damage and possible visual impairment traditionally, screening for diabetic retinopathy has been the norm hard by ophthalmologists manually. To facilitate this, we have DR. Our pre-trained model is trained on a large dataset of about 3662 training images, enabling it to automatically detect the DR platform in high-resolution fundus images The dataset used for this is publicly available on kaggle. The DR phases are categorized as 0, 1, 2, 3, and 4. The fundus eye images serve as the input parameters of the model. The pre-trained model then identifies the point of interest in bank eye images, then provides activation function insights By calculating weights, for example patients’ visual intensity levels, it helps classify diabetic retinopathy images into their intensity groups appropriately within the possibility of test- methods Provides variation.

Cross-Domain Aspect-Based Sentiment Classification with a Pre-Training and Fine-Tuning Strategy for Low-Resource Domains

Aspect-based sentiment classification (ABSC) is a crucial sub-task of fine-grained sentiment analysis, which aims to predict the sentiment polarity of the given aspects in a sentence as positive, negative, or neutral. Most existing ABSC methods are based on supervised learning. However, these methods rely heavily on fine-grained labeled training data, which can be scarce in low-resource domains, limiting their effectiveness. To overcome this challenge, we propose a low-resource cross-domain aspect-based sentiment classification (CDABSC) approach based on a pre-training and fine-tuning strategy. This approach applies the pre-training and fine-tuning strategy to an advanced deep learning method designed for ABSC, namely the attention-based encoding graph convolutional network (AEGCN) model. Specifically, a high-resource domain is selected as the source domain, and the AEGCN model is pre-trained using a large amount of fine-grained annotated data from the source domain. The optimal parameters of the model are preserved. Subsequently, a low-resource domain is used as the target domain, and the pre-trained model parameters are used as the initial parameters of the target domain model. The target domain is fine-tuned using a small amount of annotated data to adapt the parameters to the target domain model, improving the accuracy of sentiment classification in the low-resource domain. Finally, experimental validation on two domain benchmark datasets, restaurant and laptop, demonstrates significant outperformance of our approach over the baselines in CDABSC Micro-F1.

Bandgap Energy of Ion‐Doped LaMnO3 Nanoparticles

Based on the s‐d model combined with Green's function technique, the magnetization and the bandgap energy of ion‐doped nanoparticles at La sites are calculated. Due to the change of the valency of Mn ions, from to , as well as the difference between the ionic radii of the doping and host ions, the exchange interaction is modified which allows a tuning of the magnetization and the bandgap energy. For nanoparticles, the bandgap is decreased by Ag and Ba doping, whereas it is increased by K and Sr doping. Macroscopic quantities such as the magnetization and the bandgap energy are directly related to microscopic parameters of the model. The simulations are qualitatively in good agreement with the experimental data.

Analysis of Plastic Deformation of Pipes Due to Deflagration to Detonation Transition Using Static Equivalent Pressure

Abstract Explosions of premixed gases with deflagration to detonation transition (DDT) are a risk in the process industry with potentially catastrophic consequences. Robust and simple design methods are required for industrial use. Such a simplified design method based on finite element analysis is proposed to model the dynamic behavior of pipes loaded by gas explosions of premixed gases including DDT. The focus is on so-called long pipes, where the DDT is not affected by reflections at blind flanges. First, it is reviewed how the pressure load of the gas explosion and the resulting material behavior has been modeled in previous publications. The analytical equations are then extended for describing the pressure load as a function of time and location by considering the leading compression wave as it affects the pressure load of the overdriven detonation. The extended analytical equations are parameterized using Chapman-Jouguet conditions and experimental results from publications for both static equivalent pressure and the location of the DDT. To describe the plastic material behavior at high strain rates, the well-known Johnson-Cook plasticity model is used. The material parameters of the model are derived from simple experiments, which are available in an industrial environment. The comparison of a finite element simulation with experimental data shows that the concept of equivalent static pressure can be extended to an finite element analysis, which in the future will allow the sizing of complete pipe systems including tees, bends, and flanges while considering plastic deformation.

An enhanced EWMA chart with variable sampling interval scheme for monitoring the exponential process with estimated parameter

Control charts have been used to monitor product manufacturing processes for decades. The exponential distribution is commonly used to fit data in research related to healthcare and product lifetime. This study proposes an exponentially weighted moving average control chart with a variable sampling interval scheme to monitor the exponential process, denoted as a VSIEWMA-exp chart. The performance measures are investigated using the Markov chain method. In addition, an algorithm to obtain the optimal parameters of the model is proposed. We compared the proposed control chart with other competitors, and the results showed that our proposed method outperformed other competitors. Finally, an illustrative example with the data concerning urinary tract infections is presented.

Prediction of durability of reinforced concrete based on hybrid-Bp neural network

Mix proportion design has a significant influence on the durability of reinforced concrete (RC). Conventional simple equations encounter challenges in effectively guiding the enhancement of durability in the design process. To address this issue, a backpropagation neural network (BPNN) model with a topological structure of 6–16–2 is devised to build a prediction model for RC durability, offering both forward design and reverse guidance for determining optimal mix proportion. Moreover, the model is optimized by the Bat Algorithm (BA), Ant Colony Optimization Algorithm (ACO), and Particle Swarm Optimization (PSO) Algorithm. The input layer parameters of the model consist the water-binder ratio and the quantity of cement, coarse aggregate, river sand (RS), fly ash (FA), slag, while the output layer parameters include the failure time for corrosion current density of reinforcement (T1) and the failure time for concrete damage degree (T2). The dataset for the model comprises 100*2 sets, which are divided into 70*2 sets for training data, 15*2 sets for validation data, and 15*2 sets for testing data. The relationship between the experimental raw materials and the durability of RC was determined through correlation analysis, and comparative analysis was conducted on the durability evaluation indices for RC. The results indicate a positive correlation between cement content and the durability of RC, whereas the content of RS, coarse aggregate, FA and slag, and water-binder ratio exhibit negative correlation with concrete durability. Among the RC groups, the A3 group demonstrated the highest performance, and the D group stood out as the optimal mineral admixture group. Utilizing the PSO-BPNN model, the following performance indices were predicted for T1: R2=0.850, MAE=38.14, MAPE=0.094, RMSE=47.218, and for T2: R2=0.872, MAE=34.541, MAPE=0.071, RMSE=42.355. Consequently, the PSO-BPNN model demonstrates the highest accuracy in predicting the correlation between concrete mix proportions and the durability of RC, thereby offering valuable guidance for the mix proportion design of RC.

Parsimonious ultrametric Gaussian mixture models

Gaussian mixture models represent a conceptually and mathematically elegant class of models for casting the density of a heterogeneous population where the observed data is collected from a population composed of a finite set of G homogeneous subpopulations with a Gaussian distribution. A limitation of these models is that they suffer from the curse of dimensionality, and the number of parameters becomes easily extremely large in the presence of high-dimensional data. In this paper, we propose a class of parsimonious Gaussian mixture models with constrained extended ultrametric covariance structures that are capable of exploring hierarchical relations among variables. The proposal shows to require a reduced number of parameters to be fit and includes constrained covariance structures across and within components that further reduce the number of parameters of the model.

Insights into Neutron Star Equation of State by Machine Learning

Due to its powerful capability and high efficiency in big data analysis, machine learning has been applied in various fields. We construct a neural network platform to constrain the behaviors of the equation of state of nuclear matter with respect to the properties of nuclear matter at saturation density and the properties of neutron stars. It is found that the neural network is able to give reasonable predictions of parameter space and provide new hints into the constraints of hadron interactions. As a specific example, we take the relativistic mean field approximation in a widely accepted Walecka-type model to illustrate the feasibility and efficiency of the platform. The results show that the neural network can indeed estimate the parameters of the model at a certain precision such that both the properties of nuclear matter around saturation density and global properties of neutron stars can be saturated. The optimization of the present modularly designed neural network and extension to other effective models is straightforward.

High-resolution particle-in-cell simulations of two-dimensional Bernstein–Greene–Kruskal modes

We present two-dimensional (2D) particle-in-cell (PIC) simulations of 2D Bernstein–Greene–Kruskal modes, which are exact nonlinear steady-state solutions of the Vlasov–Poisson equations, on a 2D plane perpendicular to a background magnetic field, with a cylindrically symmetric electric potential localized on the plane. PIC simulations are initialized using analytic electron distributions and electric potentials from the theory. We confirm the validity of such solutions using high-resolutions up to a 20482 grid. We show that the solutions are dynamically stable for a stronger background magnetic field, while keeping other parameters of the model fixed, but become unstable when the field strength is weaker than a certain value. When a mode becomes unstable, we observe that the instability begins with the excitation of azimuthal electrostatic waves that ends with a spiral pattern.

Evolutionary Dual-Stream Transformer.

Vision transformers (ViTs) are rapidly evolving and are widely used in computer vision. However, high-performance ViTs require many computations, which limit their further development in the vision field. In this article, a novel evolutionary dual-stream transformer (E-DST) model is proposed to alleviate the computational resource demand problem. A hybrid attention mechanism structure is proposed for a DST model. The DST model uses a dual-branch structure to fuse convolutional and transformer features. Combining the features learned by the transformer and convolution effectively saves model computational resources. In addition, an evolutionary optimizer is proposed to optimize the parameters of the model. The excellent search ability of the evolutionary algorithm is utilized to optimize the transformer model parameters. The convergence of the evolutionary optimizer is proved in this article. In addition, the proposed E-DST model is experimentally compared with a variety of classic models and their deformations based on three datasets. And, the evolutionary optimizer proves its generality in convolutional and recurrent neural networks. The experimental results show that the E-DST model can effectively reduce computational resources and that the evolutionary optimizer can solve large-scale optimization problems. In conclusion, our proposed method is feasible and effective.

Modeling and signal integrity analysis of silicon interposer channels based on MTL and KBNN

In this paper, the equivalent circuit model of interconnect channels in silicon interposer is developed for three-dimensional integrated circuit (3-D IC) based on the theory of multi-conductor transmission line (MTL). The deep neural network (DNN) is employed to learn the nonlinear mapping relationship between the geometric parameters and the distributed parameters, and it is demonstrated that the DNN has a high prediction accuracy. In the implementation, a coarse model is firstly developed by solving the scattering parameters of the model using the chain parameter matrix. The model is optimized using a knowledge-based neural network (KBNN), and a fine model is then established. The numerical examples demonstrate that the optimized model can achieve high accuracy. Finally, the inner contour of the worst-case eye diagrams of the channel is generated using the peak distortion algorithm (PDA), with the worst eye width and height obtained.

Explicit Representations of Solutions and Parameter Estimations Problems of Time Delay Tumor Cells Model

We consider ordinary differentials of cancerous tumor cells model with time delay that illustrates and represents the interactions of the tumor cells with effector cells include immune response of natural, dendritic and cytotoxic cells. The time delay is incorporated here into the model to justify the time required to stimulate the effector cells. This also help to study the behavior of the system without using all kinds of treatments. We study the stability of the model that confirms a free tumor steady state and displays two equilibrium points. The numerical simulations show that growing of the tumor cells reduces and the effector cells increase after few days for different values of time delay up to , even without considering the treatment strategies in the model. We present an efficient numerical technique that shows how we can first represent the periodic solution of the tumor nonlinear equation and then effectively estimate the unknown parameters of the model.  

Quasinormal modes, temperatures and greybody factors of black holes in a generalized Rastall gravity theory

We introduce a modification in the energy-momentum conservation violating Rastall’s theory of gravity and obtain a Reissner-Nordström-type black hole solution in spacetime surrounded by a cloud of strings and charge fields. We examine the horizons of the black hole along with the influence of the parameters of the model on it. The scalar quasinormal modes (QNMs) of oscillations of the black hole are also computed using the 6th order WKB approximation method. It is seen that the Rastall parameter β and the newly introduced energy-momentum tensor trace parameter α as well as the charge parameter q and strings field parameter a influence the amplitude and damping of the QNMs. From the metric function, we obtain the temperature of the black hole and study the effects of the four model parameters β, α, q and a on the temperature. We then examine the greybody factors associated with the black hole and the corresponding total absorption cross-section for it. It is seen that the modification we introduced in the Rastall theory has a drastic effect on various properties of the black hole and may lead to interesting outcomes in future when better detection techniques will be available with the LISA and the Einstein Telescope.

A flexible generalized XLindley distribution with application to engineering

This paper presents a novel three-parameter distribution called the exponentiated generalized XLindley distribution. The distribution’s probability density function can be positively or negatively skewed, reverse-J or symmetric. Both an increasing and decreasing hazard rate function is conceivable. The hazard rate function, moments, residual and reverse residual life function, reliability function, and Rényi entropy are among the mathematical elements that can be ascertained from the new model. To estimate the parameters of the model, the maximum likelihood method is utilized. A simulation study was carried out to assess maximum likelihood estimators’ effectiveness. Two sets of data related to civil engineering were subjected to the new three-parameter model. The model is shown to suit these two symmetric datasets more closely than comparison models shown in this paper.

A new unit distribution: properties, estimation, and regression analysis

This research commences a unit statistical model named power new power function distribution, exhibiting a thorough analysis of its complementary properties. We investigate the advantages of the new model, and some fundamental distributional properties are derived. The study aims to improve insight and application by presenting quantitative and qualitative perceptions. To estimate the three unknown parameters of the model, we carefully examine various methods: the maximum likelihood, least squares, weighted least squares, Anderson–Darling, and Cramér-von Mises. Through a Monte Carlo simulation experiment, we quantitatively evaluate the effectiveness of these estimation methods, extending a robust evaluation framework. A unique part of this research lies in developing a novel regressive analysis based on the proposed distribution. The application of this analysis reveals new viewpoints and improves the benefit of the model in practical situations. As the emphasis of the study is primarily on practical applications, the viability of the proposed model is assessed through the analysis of real datasets sourced from diverse fields.

On the slow–fast dynamics of a tri‐trophic food chain model with fear and Allee effects

A three‐species food chain model with Allee and fear effects on both prey and predator is investigated in this work. The model consists of ODEs describing the evolution and interaction of prey, predator, and top predator populations in a biological system. We assume that the intrinsic growth rate of the prey is much smaller than a threshold value determined by other biological parameters of the model. Consequently, the model is transformed into a singularly perturbed system that acts on two different time scales, ranging from slow for both prey and predator to fast for the top predator. Positivity and boundedness of the solutions of the model along with the stability for its equilibria are investigated. The model possesses the exact invariant manifold with changing stability (black swan) and exhibits the canard phenomenon. Some numerical simulations are performed to validate our analysis.

Identification of typical district configurations: A two-step global sensitivity analysis framework

The recent geopolitical conflicts in Europe have underscored the vulnerability of the current energy system to the volatility of energy carrier prices. In the prospect of defining robust energy systems ensuring sustainable energy supply in the future, the imperative of leveraging renewable indigenous energy sources becomes evident. However, as such technologies are integrated into the existing system, it is necessary to shift from the current centralized infrastructure to a decentralized production strategy. This paper presents a method to identify a panel of technological solutions at the district level, intended to reduce complexity for the integration of decentralized models into a national-scale model. The framework’s novelty lies in combining a global sensitivity analysis for solution generation with clustering to identify typical configurations. The global sensitivity analysis is performed on a mixed integer linear programming model, which optimally sizes and operates district energy systems. The sensitivity analysis determines the most influential parameters of the model using the Morris method and provides a representative sampling of the solution space by leveraging the Sobol sampling strategy. The latter is then clustered using a density-based algorithm to identify typical solutions. The framework is applied to a suburban and residential Swiss neighborhood. The first outcome of the research is the high sensitivity of the model to energy carrier prices. As a result, Sobol’s sampling space separates itself into two system types: those based on a natural gas boiler and those relying on a combination of electrical heaters and heat pumps. For both types, the electricity demand is either fulfilled by PV panels or electricity imports. The identified configurations showcase that the framework successfully generates a panel of solutions composed of various system configurations and operations being representative of the overall solution space.

Unmanned sailboat with self-balancing rotating sail based on elastic rope: Modeling, optimization, and sea trials

Unmanned sailboats use wind energy to assist in propulsion during navigation and are featured by the advantages of clean energy and long endurance, making a hotspot of research on maritime unmanned vehicles. Sails are a core component of unmanned sailboats, and most existing studies on rotating sail have the shortcomings of high energy consumption and load. Therefore, this article proposes a novel method to achieve self-balancing sail rotation based on elastic rope and reduce the energy consumption and load of unmanned sailboats, and establishes a model for the self-balancing rotating sail. We introduced the sum of angular thrust of spherical surface SL as a performance evaluation index for unmanned sailboats, which considers both thrust and navigable range. Based on this index, the mechanical and positional parameters of the model are optimized to obtain the optimal solutions. The performance is increased by 24% after the optimization, and by 76% compared with the sailboat with the fixed sail angle when the same initial sail angle of 38° is adopted. Following the optimal solutions, we develop a prototype of the unmanned sailboat with self-balancing rotating sail. Subsequently, wind turbine experiments are conducted to preliminarily verify the correctness of the model for self-balancing rotating sail and the optimization results. Finally, sea trials are conducted to further verify the performance and seaworthiness of the unmanned sailboat under realistic sea conditions, successfully achieving a 15-day voyage under harsh sea conditions of levels 2 to 4. This study to some extent compensates for the shortcomings of existing studies on rotating sail and provides guidance for subsequent theoretical and engineering research in the field of unmanned sailboats.

Proposing a novel mathematical model for hospital pneumatic system

Hospital Pneumatic Systems, specializing in pneumatic systems, are among the most essential components for hospitals. It offers efficient and cost-effective solutions to problems related to the transportation of various materials in hospitals. However, in existing systems, the need for compressed air is met without worrying about cost control and without depending on the sample transported, and this not only makes the system inefficient but also may cause sample degradation. The main purpose of this study is to provide speed/pressure control according to the type of material transported to eliminate the disadvantages of existing systems such as energy use and sample degradation. In this study, a new mathematical model is presented that can be used to make more energy-efficient hospital pneumatic systems. Although there are many studies on various pneumatic systems in the literature, there is not enough for the control of hospital pneumatic systems. According to the results obtained in this study, the system parameters were determined and the mathematical model of the system was obtained by using the Multivariate nonlinear regression method. A genetic algorithm was used to test the validity of the obtained mathematical model and to optimize the coefficient of the input parameters of the model. It is expected that this proposed model will contribute to the use of hospital pneumatic systems and provide a scientific and practical solution to the proposed mathematical model. The proposed mathematical model provides up to %43 more efficient transportation over the currently used system that has been tested.

A nonlinear finite viscoelastic formulation relative to the viscous intermediate configuration applied to plants

AbstractIn the contribution at hand, a new formulation for finite strain viscosity relative to the viscous intermediate configuration is presented. The evolution of the viscous deformations is based upon a new numerical approach, which allows for a consistent consideration of anisotropic finite strain viscoelasticity, according to the authors knowledge. A standard Maxwell model is used to describe viscous behaviour at finite deformations. Furthermore, the orthotropic Yeoh material model is extended to include a distinction between behaviour under tensile and compression loading. The proposed formulation is validated, and parameters of the model are identified by material tests on Sorghum bicolor plants. Subsequently, numerical examples are shown to demonstrate the capabilities of the model. In general, the proposed Yeoh material formulation is shown to accurately represent the inability of fibres to carry compression loading. Furthermore, the viscoelastic approach, developed relative to the viscous intermediate configuration, is demonstrated to be capable of producing plausible results. Additionally, the mechanical behaviour of Sorghum bicolor plants is simulated using the introduced formulation. The results show that the contribution at hand describes a novel methodology to simulate the viscoelastic behaviour of plant materials reliably.