Nonlinear Dependence Research Articles

Research on the application of deep learning techniques in stock market prediction and investment decision-making in financial management

Introduction: This paper introduces a deep learning approach based on Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory Networks (BiLSTM), and attention mechanism for stock market prediction and investment decision making in financial management. These methods leverage the advantages of deep learning to capture complex patterns and dependencies in financial time series data. Stock market prediction and investment decision-making have always been important issues in financial management.Methods: Traditional statistical models often struggle to handle nonlinear relationships and complex temporal dependencies, thus necessitating the use of deep learning methods to improve prediction accuracy and decision effectiveness. This paper adopts a hybrid deep learning model incorporating CNN, BiLSTM, and attention mechanism. CNN can extract meaningful features from historical price or trading volume data, while BiLSTM can capture dependencies between past and future sequences. The attention mechanism allows the model to focus on the most relevant parts of the data. These methods are integrated to create a comprehensive stock market prediction model. We validate the effectiveness of the proposed methods through experiments on real stock market data. Compared to traditional models, the deep learning model utilizing CNN, BiLSTM, and attention mechanism demonstrates superior performance in stock market prediction and investment decision-making.Results and Discussion: Through ablation experiments on the dataset, our deep learning model achieves the best performance across all metrics. For example, the Mean Absolute Error (MAE) is 15.20, the Mean Absolute Percentage Error (MAPE) is 4.12%, the Root Mean Square Error (RMSE) is 2.13, and the Mean Squared Error (MSE) is 4.56. This indicates that these methods can predict stock market trends and price fluctuations more accurately, providing financial managers with more reliable decision guidance. This research holds significant implications for the field of financial management. It offers investors and financial institutions an innovative approach to better understand and predict stock market behavior, enabling them to make wiser investment decisions.

Influence of Lifshitz Transition on the Intrinsic Resistivity of Cu2N Monolayer.

The Lifshitz transition (LT), a topological structure transition of Fermi surfaces, can induce various intricate physical properties in metallic materials. In this study, through first-principles calculations, we explore the nontrivial effect of the LT on the intrinsic resistivity of the Cu2N monolayer arising from electron-phonon (el-ph) scattering. We find that when the LT is induced by electron doping, the multibranch Fermi surface simplifies into a single-band profile. Such an LT leads to a decoupling of low-frequency flexural phonons from el-ph scattering due to mirror symmetry. Consequently, the resistivity of the Cu2N monolayer at room temperature significantly decreases, approaching that of slightly doped graphene, and highlighting the Cu2N monolayer as a highly conductive two-dimensional metal. Moreover, this LT can bring about a nonlinear temperature dependence of the intrinsic resistivity at a high temperature.

Method of accumulation of preload loss of bolted joints due to rotational self-loosening caused by cyclic, transversal excitation

This paper presents a new method to experimentally characterize the rotational self-loosening behavior of bolted joints. Furthermore, a method to calculate the preload loss due to certain relative displacements of the clamped parts was developed. The method obtains all required calculation parameters from the experimental tests performed and neither needs further experimental determination of friction coefficients nor numerical simulations to predict the preload loss. The method accumulates the preload loss of load cycles. Thereby, it can be used to estimate the time a machine can operate until a critical amount of preload is lost. Non-linear dependencies of the preload loss to the displacement amplitude and the remaining preload are considered. The calculation method also applies to load cases with variable load amplitudes. This is validated experimentally.

Enhancing agricultural product trade efficiency through machine learning predictions and multi-objective optimization of financial strategies

In the context of global economic development and food safety, agricultural trade plays a vital role in linking agricultural production with market demand, and the efficient formulation of agricultural financial strategies is crucial for enhancing trade efficiency. This study employs advanced machine learning technologies to predict and optimize the efficiency of agricultural trade while seeking to balance the interests of various stakeholders in agricultural finance. By integrating quantile factor models, long short-term memory (LSTM) networks, and attention mechanisms, this paper conducts an in-depth analysis and precise prediction of the key factors affecting trade efficiency. This approach effectively addresses the nonlinearity and long-term dependency issues in time-series data, utilizing attention mechanisms to highlight critical information and improve prediction accuracy. Furthermore, this research establishes a multi-objective optimization model to balance the interests of agricultural finance participants, providing a new quantitative tool for formulating agricultural financial strategies aimed at optimizing decisions to enhance economic and social value. This paper offers new perspectives, methods, and empirical support for improving the efficiency of agricultural trade and the formulation of agricultural financial strategies.

Influence of porosity on the Umov effect in silicate and organic refractory aggregates

This study investigates the influence of porosity on the Umov effect, a phenomenon observed in the scattering of light from celestial objects. The Umov effect describes an inverse relationship between the degree of linear polarization and the object’s reflectance (geometric albedo). To study the dependence of porosity on the Umov effect, a wide range of porosity (i.e., from 0.64 to 0.99) is considered. Four types of aggregates, ballistic cluster-cluster aggregate (BCCA), ballistic particle cluster aggregate (BPCA) or ballistic agglomeration (BA), ballistic agglomeration with one migration (BAM1), and ballistic agglomeration with two migrations (BAM2) each having porosity 0.99, 0.87, 0.74, and 0.64 are considered in this study. The multi-sphere T-matrix code is utilized to calculate the linear polarization and geometric albedo (A) considering silicate and organic refractory compositions for monodisperse aggregates. The results are reported for six different wavelengths, ranging from near-ultraviolet to the visible spectrum. When the polarization maximum (Pmax) is plotted against the geometric albedo (A) on a logarithmic scale, an inverse relation is observed. This relation exhibits non-linear changes, fitted by a second-degree polynomial equation, as the porosity changes from 0.64 to 0.99. This finding constitutes one of the interesting results of our study. In addition, the study explores the effect of porosity (P) on the ratio between log(Pmax) and log(A), showing a non-linear relationship. A comparison is drawn between the results obtained from organic refractory compositions and amorphous silicate compositions, emphasizing the importance of porosity and wavelength in regulating the Umov effect. In addition, the research investigates how mixing affects the results at different wavelengths, assuming the aggregates are blends of organic refractory and amorphous silicate compositions. The computations have also been performed for polydisperse aggregates (considering BCCA, BA, BAM1, and BAM2 structures) at a wavelength of 0.45 μm for silicate compositions, which also showed a non-linear dependence as observed in the case of monodisperse aggregates.

Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes

It has been established that near infrared (NIR) spectroscopy has the potential of estimating sensory traits given the direct spectral responses that these properties have in the near infrared (NIR) region. In sweetpotato, sensory and texture traits are key for improving acceptability of the crop for food security and nutrition. Studies have statistically modelled the levels of near infrared (NIR) spectroscopy sensory characteristics using partial least squares (PLS) regression methods. To improve prediction accuracy, there are many advanced techniques, which could enhance modelling of fresh (wet and un-processed) samples or nonlinear dependence relationships. Performance of different quantitative prediction models for sensory traits developed using different machine learning methods were compared. Overall, results show that linear methods; linear support vector machine (L-SVM), principal component regression (PCR) and PLS exhibited higher mean values than other statistical methods. For all the 27 sensory traits, calibration models using L-SVM and PCR has slightly higher overall R2 (x¯ = 0.33) compared to PLS (x¯ = 0.32) and radial based SVM (NL-SVM; x¯= 0.30). The levels of orange color intensity were the best predicted by all the calibration models (R2 = 0.87 – 0.89). The elastic net linear regression (ENR) and tree-based methods; extreme gradient boost (XGBoost) and random forest (RF) performed worse than would be expected but could possibly be improved with increased sample size. Lower average R2 were observed for calibration models of ENR (x¯ = 0.26), XGBoost (x¯ = 0.26) and RF (x¯ = 0.22). The overall RMSE in calibration models was lower in PCR models (X = 0.82) compared to L-SVM (x¯ = 0.86) and PLS (x¯ = 0.90). ENR, XGBoost and RF also had higher RMSE (x¯ = 0.90 – 0.92). Effective wavelengths selection using the interval partial least-squares regression (iPLS), improved the performance of the models but did not perform as good as the PLS. SNV pre-treatment was useful in improving model performance.

Hierarchically Coupled Ornstein–Uhlenbeck Processes for Transient Anomalous Diffusion

The nonlinear dependence of the mean-squared displacement (MSD) on time is a common characteristic of particle transport in complex environments. Frequently, this anomalous behavior only occurs transiently before the particle reaches a terminal Fickian diffusion. This study shows that a system of hierarchically coupled Ornstein–Uhlenbeck equations is able to describe both transient subdiffusion and transient superdiffusion dynamics, as well as their sequential combinations. To validate the model, five distinct experimental, molecular dynamics simulation, and theoretical studies are successfully described by the model. The comparison includes the transport of particles in random optical fields, supercooled liquids, bedrock, soft colloidal suspensions, and phonons in solids. The model’s broad applicability makes it a convenient tool for interpreting the MSD profiles of particles exhibiting transient anomalous diffusion.

Qualification and Quantification of Porosity at the Top of the Fuel Pins in Metallic Fuels Using Image Processing

Approximately 130,000 metal fuel pins were irradiated in the Experimental Breeder Reactor II (EBR-II) during its 30 years of operation to develop and characterize existing and prospective fuels. For many of the metal fuel irradiation experiments, neutron radiography imaging was performed to characterize fuel behavior, such as fuel axial expansion. While several fuel expansion results obtained from neutron radiography imaging have been published, the analysis of neutron radiography for the purpose of describing statistical properties of porous matter formed on top of the fuel pins, also referred to as fluff in previous publications, is significantly less represented in the literature with just a single paper so far. This study aims to validate and augment results reported in previous publications using automated image processing. The paper describes the statistical properties of the porous matter in terms of nine parameters derived from radiography images and correlates those parameters with such fuel properties as composition, expansion, temperature, and burnup. The reported results are based on 1097 fuel pins of eight different fuel compositions. For three major fuel types, U-10Zr, U-8Pu-10Zr, and U-19Pu-10Zr, a clear negative correlation is found between the Pu content and five parameters describing the amount of porous matter generated. The parameters describing granularity properties, however, showed either negative correlation or nonlinear dependency from fuel composition. The parameters describing the amount showed a positive correlation with fuel axial expansion, while granularity parameters showed a negative correlation with axial expansion. The dependency on cladding temperature was found to be weak. A positive correlation is demonstrated for volume parameters and fuel burnup. In general, reported results confirm and validate findings published in previous studies using a much larger number of pins and automated processing techniques, which easily lend themselves to reproducibility, thus avoiding subjective bias.

R‐Vine Copulas for Data‐Driven Quantification of Descriptor Relationships in Porous Materials

AbstractLocal variations in the 3D microstructure can control the macroscopic behavior of heterogeneous porous materials. For example, the permittivity through porous sheets or membranes is governed by local high‐volume pathways or bottlenecks. Due to local variations, unfeasibly large amounts of microstructure data may be needed to reliably predict such material properties directly from image data. Here it is demonstrated that a vine copula approach provides parametric models for local microstructure descriptors that compactly capture the 3D microstructure including its local variations and efficiently probe it with respect to selected, measurable properties. In contrast to common methods of complexity reduction, the proposed approach creates parametric models for the multivariate probability distribution of high‐dimensional descriptor vectors that inherently contain the complex, nonlinear dependencies between these descriptors. Therein, material properties are offered in physically motivated distributions of microstructure descriptors rather than as normally distributed data. Applied to porous fiber networks (paper) before and after unidirectional compression, it is shown that the copula‐based models reveal material‐characteristic relationships between two or more microstructure descriptors. In this way, the presented modeling approach can provide deeper insight into the microscopic origin of effective macroscopic properties of heterogeneous porous materials.

Convenient Size Analysis of Nanoplastics on a Microelectrode.

Chemical recycling is a promising approach to reduce plastic pollution. Timely and accurate size analysis of produced nanoplastics is necessary to monitor the process and assess the quality of chemical recycling. In this work, a sandwich-type microelectrode sensor was developed for the size assessment of nanoplastics. β-Mercaptoethylamine was modified on the microelectrode to enhance its surface positive charge density. Polystyrene (PS) nanoplastics were captured on the sensor through electrostatic interactions. Ferrocene was used as an electrochemical beacon and attached to PS via hydrophobic interactions. The results show a nonlinear dependence of the sensor's current response on the PS particle size. The size resolving ability of the microelectrode is mainly attributed to the small size of the electrode and the resulting attenuation of the electric field strength. For mixed samples with different particle sizes, this method can provide accurate average particle sizes. Through an effective pretreatment process, the method can be applied to PS nanoplastics with different surface properties, ensuring its application in evaluating different chemical recycling methods.

Data‐Driven Cz–Si Scale‐Up under Conditions of Partial Similarity

AbstractIn Cz–Si growth, the shape of the solid–liquid interface and the v/G ratio significantly impact crystal quality. This study utilizes a data‐driven approach, employing multilayer perceptron (MLP) neural networks and Bayesian optimization, to investigate the scale‐up process of Cz–Si under conditions of partial similarity. The focus is on exploring the influence of various process and furnace geometry parameters, as well as radiation shield material properties, on the critical measures of crystal quality. Axisymmetric CFD modeling produces 340 sets of 18D raw data, from which 14‐dimensionless derived data tuples are generated for the design and training of the MLP. The best MLP obtained demonstrates the ability to accurately assess the complex nonlinear dependencies among dimensionless numbers derived from CFD data and, on the output side, interface deflection and v/G. These relationships, crucial for scale‐up, are successfully generalized across a wide range of parameters.

Improved estimation of semiparametric dynamic copula models with filtered nonstationarity

This paper considers estimation of short-run dynamics in time series that contain a nonstationary component. We assume that appropriate preliminary methods can be applied to the observed time series to separate short-run elements from long-run slowly evolving secular components, and focus on estimation of the short-run dynamics based on the filtered data. We use a flexible copula-generated Markov model to capture the nonlinear temporal dependence in the short-run component and study estimation of the copula model. Using the rescaled empirical distribution of the filtered data as an estimator of the marginal distribution, Chen et al. (2022) proposed a simple, yet flexible, two-step estimation procedure for the copula model. The two-step estimator works well when the tail dependence is small. However, simulations reveal that the two-step estimator may be biased in finite samples in the presence of tail dependence. To improve the performance of short-term dynamic analysis in the presence of tail dependence, we propose in this paper a pseudo sieve maximum likelihood (PSML) procedure to jointly estimate the residual copula parameter and the invariant density of the filtered residuals. We establish the root-n consistency and asymptotic distribution of the PSML estimator of any smooth functional of the residual copula parameter and invariant residual density. We further show that the PSML estimator of the residual copula parameter is asymptotically normal, with the limiting distribution independent of the filtration. Simulations reveal that in the presence of strong tail dependence, compared to the two-step estimates of Chen et al. (2022), the proposed PSML estimates have smaller biases and smaller mean squared errors even in small samples. Applications to nonstationary macro-finance and climate time series are presented.

Is Single Enough? A Joint Spatiotemporal Feature Learning Framework for Multivariate Time Series Prediction.

A fuzzy cognitive map (FCM) is a simple but effective tool for modeling and predicting time series. This article focuses on the problem of multivariate time series prediction (TSP), which is essential and challenging in data mining. Although several FCM-based approaches have been designed to solve this problem, their feature extraction module designed for single mode falls short in capturing the nonlinear spatiotemporal dependencies among variates, thereby resulting in low prediction accuracy in forecasting multivariate time series, which shows that the single mode learning is not enough. Therefore, in this article, we propose a joint spatiotemporal feature learning framework for multivariate TSP, where a mix-resolution spatial module consisting of multiple sparse autoencoders (SAEs) is designed to extract the feature series with different spatial resolutions, and a mix-order spatiotemporal module concluding multiple high-order FCMs (HFCMs) is designed to model the spatiotemporal dynamics of these feature series. Finally, the outputs of the two modules are concatenated to predict future values. We refer to this framework as the spatiotemporal FCM (STFCM). Especially, an efficient learning algorithm is designed to update the integral weights of STFCM based on the batch gradient descent algorithm when it deems necessary. We validate the performance of the STFCM on four real-world datasets. Compared with the existing state-of-the-art (SOTA) methods, the experimental results not only show the advantages of the two designed modules in the STFCM but also show the excellent performance of the STFCM.

Radar-based measurement of solids back-mixing in the freeboard of a circulating fluidized bed

This work investigates solids back-mixing in the freeboard of a circulating fluidized bed based on THz-radar measurements of the concentrations and velocity distributions of the solid particles along the height of the riser. These data allow height-resolved closure of the solids mass balance and, thereby, quantification and further insight of the two main mechanisms for the back-mixing of the solids entrained from the bottom region of the fluidized bed: (i) solids disengagement and backmixing within the core region of the riser cross-section,; and (ii) solids lateral transfer of from the core region to the wall layers. The experiments were carried out in a circulating fluidized bed riser (3.1 m in height and 0.45 m2 in cross-section), which was operated with Geldart B solids fluidized with air at room temperature and for different gas velocities. The experimentally-derived data are expressed in terms of the disengagement rate and a lateral core-to-wall layer mass transfer coefficient. From the results, it is estimated that the presence of disengagement-based solids back-mixing is significant all along the 3-m riser. The disengagement rate shows a non-linear dependency on the solids concentration, with the lateral solids transfer to the walls (which follows a linear dependency on the solids concentration) eventually becoming the dominant form of back-mixing at upper heights.

Modeling of strain hardening behaviors of 6061 aluminum alloy considering strain rate and temperature effects

This paper focuses on the plastic strain hardening behaviors of 6061 aluminum alloy (AA6061), considering its dependence on strain rate and temperature. Quasi-static tensile tests were conducted over a wide temperature range (20 °C-300 °C), and the digital image correlation technique was used to capture the deformation process of specimens. Additionally, the uniaxial compressive mechanical response of AA6061 was tested utilizing quasi-static compression and split Hopkinson pressure bar experiments over a wide range of strain rates (0.001 s−1–6000 s−1). Experimental results showed that the flow stress decreased and increased nonlinearly with temperature and strain rate, respectively. A modified Johnson–Cook (MJC) model was developed by incorporating a temperature-dependent strain softening term, along with corrections to the temperature and strain rate product terms, to reproduce the nonlinear dependence. Furthermore, the MJC model was proven to be able to accurately reproduce the deformation of the specimens tested in Taylor impact experiments (strain rates up to 105 s−1), suggesting its effectiveness for interpolating and extrapolating stress-strain relationships. This model provides applicable modeling for materials with nonlinear rate sensitivity and temperature sensitivity, and it is expected to be applied in engineering problems involving ultra-high strain rates.

DEFORMATIONS OF SOIL MASSES UNDER THE ACTION OF HUMAN-INDUCED FACTORS

Significant changes in the stress-strain state cause a change in the soil profile of the massif, which is affected by various physical and chemical factors. In particular, groundwater filtration, mass transfer, heat transfer, dissolution and leaching of soil masses. This can lead to various types of accidents. Therefore, the study of the stress-strain state of the soil massif is an important topic. Nonlinear dependences in the form of polynomials of the modulus of deformation and Lame coefficients on the concentration of salt solutions and their temperature have been received in this research based on experimental research and their statistical processing. This allowed improving the mathematical model of the stress-strain state of the soil taking into account the nonlinear deformation processes occurring in the soil masses under the presence and filtration of saline solutions in non-isothermal conditions.

Prediction of Rheological Parameters of Polymers by Machine Learning Methods

Introduction. All polymer materials and composites based on them are characterized by pronounced rheological properties, the prediction of which is one of the most critical tasks of polymer mechanics. Machine learning methods open up great opportunities in predicting the rheological parameters of polymers. Previously, studies were conducted on the construction of predictive models using artificial neural networks and the CatBoost algorithm. Along with these methods, due to the capability to process data with highly nonlinear dependences between features, machine learning methods such as the k-nearest neighbor method, and the support vector machine (SVM) method, are widely used in related areas. However, these methods have not been applied to the problem discussed in this article before. The objective of the research was to develop a predictive model for evaluating the rheological parameters of polymers using artificial intelligence methods by the example of polyvinyl chloride.Materials and Methods. This paper used k-nearest neighbor method and the support vector machine to determine the rheological parameters of polymers based on stress relaxation curves. The models were trained on synthetic data generated from theoretical relaxation curves constructed using the nonlinear Maxwell-Gurevich equation. The input parameters of the models were the amount of deformation at which the experiment was performed, the initial stress, the stress at the end of the relaxation process, the relaxation time, and the conditional end time of the process. The output parameters included velocity modulus and initial relaxation viscosity coefficient. The models were developed in the Jupyter Notebook environment in Python.Results. New predictive models were built to determine the rheological parameters of polymers based on artificial intelligence methods. The proposed models provided high quality prediction. The model quality metrics in the SVR algorithm were: MAE – 1.67 and 0.72; MSE – 5.75 and 1.21; RMSE – 1.67 and 1.1; MAPE – 8.92 and 7.3 for the parameters of the initial relaxation viscosity and velocity modulus, respectively, with the coefficient of determination R2 – 0.98. The developed models showed an average absolute percentage error in the range of 5.9 – 8.9%. In addition to synthetic data, the developed models were also tested on real experimental data for polyvinyl chloride in the temperature range from 20° to 60°C.Discussion and Conclusion. The approbation of the developed models on real experimental curves showed a high quality of their approximation, comparable to other methods. Thus, the k-nearest neighbor algorithm and SVM can be used to predict the rheological parameters of polymers as an alternative to artificial neural networks and the CatBoost algorithm, requiring less effort to preset adjustment. At the same time, in this research, the SVM method turned out to be the most preferred method of machine learning, since it is more effective in processing a large number of features

Probabilistic assessment of wind power plant energy potential through a copula-deep learning approach in decision trees

In the face of environmental degradation and diminished energy resources, there is an urgent need for clean, affordable, and sustainable energy solutions, which highlights the importance of wind energy. In the global transition to renewable energy sources, wind power has emerged as a key player that is in line with the Paris Agreement, the Net Zero Target by 2050, and the UN 2030 Goals, especially SDG-7. It is critical to consider the variable and intermittent nature of wind to efficiently harness wind energy and evaluate its potential. Nonetheless, since wind energy is inherently variable and intermittent, a comprehensive assessment of a prospective site's wind power generation potential is required. This analysis is crucial for stakeholders and policymakers to make well-informed decisions because it helps them assess financial risks and choose the best locations for wind power plant installations. In this study, we introduce a framework based on Copula-Deep Learning within the context of decision trees. The main objective is to enhance the assessment of the wind power potential of a site by exploiting the intricate and non-linear dependencies among meteorological variables through the fusion of copulas and deep learning techniques. An empirical study was carried out using wind power plant data from Turkey. This dataset includes hourly power output measurements as well as comprehensive meteorological data for 2021. The results show that acknowledging and addressing the non-independence of variables through innovative frameworks like the Copula-LSTM based decision tree approach can significantly improve the accuracy and reliability of wind power plant potential assessment and analysis in other real-world data scenarios. The implications of this research extend beyond wind energy to inform decision-making processes critical for a sustainable energy future.

On some dynamical features of the complete Moran model for neutral evolution in the presence of mutations

We present a version of the classical Moran model, in which mutations are taken into account; the possibility of mutations was introduced by Moran in his seminal paper, but it is more often overlooked in discussing the Moran model. For this model, fixation is prevented by mutation, and we have an ergodic Markov process; the equilibrium distribution for such a process was determined by Moran. The problems we consider in this paper are those of first hitting either one of the ``pure'' (uniform population) states, depending on the initial state; and that of first hitting times. The presence of mutations leads to a nonlinear dependence of the hitting probabilities on the initial state, and to a larger mean hitting time compared to the mutation-free process (in which case hitting corresponds to fixation of one of the alleles).

Shear Alfvén waves within magnetic islands

We calculate Alfvén eigenmodes within a magnetic island (MiAE) which have been conjectured over a decade ago. Starting from a cylindrical plasma equilibrium, we calculate the complete metric of the island interior assuming an iota profile with a constant shear for Wendelstein 7-X parameters. Then, we solve the resulting Magneto-Hydrodynamic equations inside the island optionally considering Finite Larmor Radius corrections. We find various eigenmodes in the lowest gaps for n = 0. The eigenmode with the lowest frequency shows a weakly non-linear dependence on the island width which deviates considerably from an earlier estimate.