Correctness Of Model Research Articles

Implementation of stacking regressor model on the flow induced by TiO2‐H2O and Ti6Al4V‐H2O nanofluid with waste discharge concentration

AbstractThe present investigation examines the circulation of and based nanofluids while considering the concentration of waste discharge. An innovative stacking regressor model is used to increase prediction accuracy. Using Shooting and Runge Kutta Fehlberg's fourth and fifth‐order schemes, the governing equations are converted into ordinary differential equations using similarity transformation and then numerically solved. The findings are represented graphically, and the model's correctness is assessed using Gaussian Process Regression, Categorical Boost, Extreme Gradient Boosting, and Random Forest, with linear regression acting as a meta‐model. The closely related testing and training data show the model's consistency and stability. Magnetic field and inclination angle will decline the velocity, space, and temperature‐dependent internal heat generation factors will enhance the temperature. Raising the pollutant external source parameter raises concentration. In all the cases, shows better performance than based nanofluid. The work's application ranges from fluid dynamics to waste management. By offering precise forecasts of nanofluid concentration, the proposed prediction model may aid in designing and optimizing waste discharge systems.

Research on the impact of overflow well shut-in on wellbore integrity and safety

If an overflow occurs, the well must be closed immediately. To ensure the safety of the drilling wellbore in ultra-deep wells, it is critical to analyze the transient flow process and pressure fluctuations of the fluid in the annular space of the overflow well shut-in. This paper investigates the pressure fluctuation model of multi-phase fluid in the annular space after overflow occurs during gas well drilling, analyzes the influence factors of multi-phase fluid's pressure wave velocity, and simulates and analyses pressure fluctuation changes in the annular space in light of the impact of overflow well shut-in on wellbore safety. The model's correctness is verified by comparing it to experimental data published in the literature. The model is developed and examined using the example of a genuine gas well in western China. According to the study, as soon as the BOP closes, pressure rapidly increases to a high of 6.09 MPa at 5.89 s before falling to a valley of 4.68 MPa at 35.36 s. When the mild shut-in time lasts 20 s, the wellhead annular pressure reaches a maximum of 5.8 MPa. If the wellhead equipment can withstand the annular space's first pressure wave, a hard shut-in is recommended. To optimize the overflow well shut-in system and ensure wellbore safety, the change in pressure in the wellhead annular space as a result of varied shut-in timings and drilling fluid displacement is studied.

CENN: Capsule-enhanced neural network with innovative metrics for robust speech emotion recognition

Speech emotion recognition (SER) plays a pivotal role in enhancing Human-computer interaction (HCI) systems. This paper introduces a groundbreaking Capsule-enhanced neural network (CENN) that significantly advances the state of SER through a robust and reproducible deep learning framework. The CENN architecture seamlessly integrates advanced components, including Multi-head attention (MHA), residual module, and capsule module, which collectively enhance the model's capacity to capture both global and local features essential for precise emotion classification. A key contribution of this work is the development of a comprehensive reproducibility framework, featuring novel metrics: General learning reproducibility (GLR) and Correct learning reproducibility (CLR). These metrics, alongside their fractional and perfect variants, offer a multi-dimensional evaluation of the model's consistency and correctness across multiple executions, thereby ensuring the reliability and credibility of the results. To tackle the persistent challenge of overfitting in deep learning models, we propose an innovative overfitting metric that considers the intricate relationship between training and testing errors, model complexity, and data complexity. This metric, in conjunction with the newly introduced generalization and robustness metrics, provides a holistic assessment of the model's performance, guiding the application of regularization techniques to maintain generalizability and resilience. Extensive experiments conducted on benchmark SER datasets demonstrate that the CENN model not only surpasses existing approaches in terms of accuracy but also sets a new benchmark in reproducibility. This work establishes a new paradigm for deep learning model development in SER, underscoring the vital importance of reproducibility and offering a rigorous framework for future research.

Development of an Economic Cost Model for Gold and Associated Minerals Using Economic Analysis and Artificial Intelligence Approach

Limited accuracy due to complex geological processes, insufficient data granularity, and challenges in predicting market dynamics impact mineral forecast models. In order to develop a cost-based model for gold and related minerals in Birnin Gwari (Kaduna State) and Kagara (Niger State), this study is being carried out in Nigeria. The created concept aims to increase the profitability and economic viability of open-pit mines operated by craftsmen and mining investors. By maximizing mine life cycles and preventing the early closure of mining sites, this was intended to encourage the best recovery rates. This study used economic and artificial neural network (ANN) modeling methods to create a cost-based model for ten gold-associated minerals. The coefficient of correlation (R2), root mean square error (RSME), and variance accounting factor (VAF) were used to assess the created model's correctness. The model evaluator demonstrates that the proposed cost-based models are economically viable and the quantitative results are as presented in Equations (14-23). The cost-benefit connection between gold and the ten related minerals was also determined using a least-squares regression analysis. According to geochemical results, the average values of gold and related minerals in the study region range from 4.87 g/t of gold (Au), 1.501 g/t of copper (Cu), and 187.13 g/t of iron (Fe) in Birni Gwari to 2.29 g/t of gold (Au), 1.358 g/t of copper (Cu), and 173.75 g/t of iron (Fe) in Kagara. In Birnin Gwari, the equivalent financial estimations are N876,600 for Au, N60,040,000 for Cu, and N1,129,375 for Fe, and N5,780,000 for Au, N49,500 for Cu, and N363,060,000 for Fe in Kagara. The model's scope demonstrates that running a single mineral can result in low recovery rates and a loss of profit margin; thus, the model's application to all open pit mines is relevant as a reference for profit margin cash flow.

Creation of a machine learning-based prognostic prediction model for various subtypes of laryngeal cancer.

Depending on the source of the blastophore, there are various subtypes of laryngeal cancer, each with a unique metastatic risk and prognosis. The forecasting of their prognosis is a pressing issue that needs to be resolved. This study comprised 5953 patients with glottic carcinoma and 4465 individuals with non-glottic type (supraglottic and subglottic). Five clinicopathological characteristics of glottic and non-glottic carcinoma were screened using univariate and multivariate regression for CoxPH (Cox proportional hazards); for other models, 10 (glottic) and 11 (non-glottic) clinicopathological characteristics were selected using least absolute shrinkage and selection operator (LASSO) regression analysis, respectively; the corresponding survival models were established; and the best model was evaluated. We discovered that RSF (Random survival forest) was a superior model for both glottic and non-glottic carcinoma, with a projected concordance index (C-index) of 0.687 for glottic and 0.657 for non-glottic, respectively. The integrated Brier score (IBS) of their 1-year, 3-year, and 5-year time points is, respectively, 0.116, 0.182, 0.195 (glottic), and 0.130, 0.215, 0.220 (non-glottic), demonstrating the model's effective correction. We represented significant variables in a Shapley Additive Explanations (SHAP) plot. The two models are then combined to predict the prognosis for two distinct individuals, which has some effectiveness in predicting prognosis. For our investigation, we established separate models for glottic carcinoma and non-glottic carcinoma that were most effective at predicting survival. RSF is used to evaluate both glottic and non-glottic cancer, and it has a considerable impact on patient prognosis and risk factor prediction.

The rainstorm influence on ecological restoration: A novel response ecological model for an urban shallow lake

AbstractEnvironmental processes in cities and suburbs are significantly impacted by climate change. The development of reliable ecological models may successfully direct agricultural activities. Numerous models have been put forth as of late; however, because to the complexity of environmental microorganisms, their use in complex systems is still restricted. For a better understanding of the ecological restoration of an urban lake system that had been disturbed by rainfall, an improved ecological dynamic model that took into account inundation plants, phytoplankton and microorganisms was proposed based on the field survey. Observed data from a shallow urban lake with a surface area of approximately 66 600 m2 in the heart of Shunde district, Foshan, in South China, was used to validate the model. In this model, five hypotheses—phytoplankton, microorganisms, NH3‐N, COD and TP in water—were selected as experimental variables. To assess the model's correctness and dependability, the correlation coefficients (R) and root mean square error‐observations standard deviation ratio (RSR) were computed. The results from the establish model (0.446 < R < 0.985, RSR < 0.7) are very similar to those of actual observations. In addition, four microbe species (Aquabacium, Bradyrhizobium japonicum, Curvibacter and Cyanobacteria) multiplied when pollutant concentration dropped. Our model provides a useful tool for managing urban shallow water lakes by properly simulating the dynamic changes of aquatic species and microbes in urban shallow water lakes.

Effects of temperature and cathode humidity on performance of PEM full cell

The performance of proton exchange membrane fuel cells (PEMFCs) is significantly influenced by their temperature and cathode humidity, as they affect power density and internal water distribution. The interdependent nature of these two parameters necessitates their simultaneous consideration in practical engineering to achieve high efficiency and reliable PEMFC operation. Therefore, this study proposes a synergistic analysis of the dual-parameter effect of working temperature and cathode humidity on PEMFC performance, using a three-dimensional steady-state model for counter-flow single-channel PEMFCs. The model's correctness is verified through comparison with experimental results, and the resulting power density and internal water distribution characteristics of PEMFCs are studied based on voltage changes. The findings indicate that the sensitivity of the proton exchange membrane (PEM) to temperature and cathode humidity varies at different voltage stages. Coupling analysis of these two factors enhances proton exchange membrane conductivity and expands the range of power density adjustment. Consequently, this study provides crucial insights into the interplay between temperature and cathode humidity in PEMFCs, facilitating the design and optimization of PEMFC systems for practical engineering applications.

Damage constitutive model of lunar soil simulant geopolymer under impact loading

Lunar base construction is a crucial component of the lunar exploration program, and considering the dynamic characteristics of lunar soil is important for moon construction. Therefore, investigating the dynamic properties of lunar soil by establishing a constitutive relationship is critical for providing a theoretical basis for its damage evolution. In this paper, a split Hopkinson pressure bar (SHPB) device was used to perform three sets of impact tests under different pressures on a lunar soil simulant geopolymer (LSSG) with sodium silicate (Na2SiO3) contents of 1%, 3%, 5% and 7%. The dynamic stress–strain curves, failure modes, and energy variation rules of LSSG under different pressures were obtained. The equation was modified based on the ZWT viscoelastic constitutive model and was combined with the damage variable. The damage element obeys the Weibull distribution and the constitutive equation that can describe the mechanical properties of LSSG under dynamic loading was obtained. The results demonstrate that the dynamic compressive strength of LSSG has a marked strain-rate strengthening effect. Na2SiO3 has both strengthening and deterioration effects on the dynamic compressive strength of LSSG. As Na2SiO3 grows, the dynamic compressive strength of LSSG first increases and then decreases. At a fixed air pressure, 5% Na2SiO3 had the largest dynamic compressive strength, the largest incident energy, the smallest absorbed energy, and the lightest damage. The ZWT equation was modified according to the stress response properties of LSSG and the range of the SHPB strain rate to obtain the constitutive equation of the LSSG, and the model's correctness was confirmed.

A formal approach for the correct deployment of cloud applications

The deployment of cloud applications is a complex task. It refers to the enablement of SaaS, PaaS or IaaS solutions that may be accessed on demand by end users. It encompasses all the activities from installation to uninstallation, including reconfiguration, etc. To facilitate the deployment of cloud applications, it is essential to design them as component-based applications in order to favor the design by reusing and reducing the development cost. However, assembling components can be a tedious and error-prone task if sufficient precautions are not taken regarding different constraints, dependencies, and conflicts between components. In this paper, we introduce a formal Event-B-based approach for the modeling and the verification of component-based applications deployment. Our goal is to build correct by-construction systems that fulfill the different constraints regarding the components, the cloud infrastructure, and the deployment process. Basically, our approach starts with an abstract model describing the main concepts of the system. Then different details are gradually introduced through refinement. For each refinement step, proof obligations are produced to ensure the model's correctness. The obtained formal model consists of a precise specification on which mathematical reasoning can be carried out to prove the correctness of our component-based application model and validate its deployment in a cloud environment by using ProB. The presented approach is illustrated through a case study.

Oral cancer detection using convolutional neural network optimized by combined seagull optimization algorithm

Early diagnosis of oral cancer is crucial for improving patient outcomes and saving lives. However, inaccurate and improper diagnosis can hinder effective treatment. This paper presents a novel method for detecting oral cancer using an optimized version of Convolutional Neural Network (CNN). While basic CNNs have been widely used for image classification tasks, the incorporation of the Seagull Optimization Algorithm and Particle Swarm Optimization Algorithm in optimizing the CNN architecture specifically for oral cancer detection is a unique approach that is provided in this study. By combining these algorithms, the proposed method optimizes the CNN's architecture, parameters, and training process specifically for oral cancer detection. This optimization enhances the performance and accuracy of the CNN in identifying cancerous regions in oral images. Unlike previous approaches, our method incorporates advanced image processing techniques, including noise reduction, contrast enhancement, and data augmentation, to enhance the quality of input data extracted from the Oral Cancer (Lips and Tongue) images (OCI) dataset. The optimized CNN architecture uses its ability to learn intricate patterns and features from the enhanced images, enabling more accurate identification of cancerous regions. To evaluate the effectiveness of our approach, we compare it against Textural analysis, FCM, CNN, R-CNN, and ResNet-101 using four measurement indices. Results demonstrate that our proposed CSOA-based CNN system achieves the highest accuracy rate (96.94%) compared to other methods, indicating its superior performance in oral cancer detection. Furthermore, our precision rate of 94.65% and recall rate of 91.60% highlight the model's high correctness and positive classification ability. Finally, our proposed method achieves the highest F1-score (88.55%), emphasizing its superiority over other comparative methods. Through our innovative integration of the Seagull Optimization Algorithm and Particle Swarm Optimization Algorithm with CNN, coupled with advanced image processing techniques, we provide a reliable and effective solution for early detection of oral cancer.

Numerical and experimental investigation on tensile fatigue performance of reinforced thermoplastic pipes

With the rapid development of offshore drilling for harvesting oil and gas from the deep sea, the fatigue performance of offshore risers is increasingly demanding. This study investigated the tensile fatigue performance of reinforced thermoplastic pipes (RTPs). The theory of three-dimensional (3D) anisotropic elastic mechanics was combined with a strain potential-energy density function to construct the 3D constitutive relation of RTPs. The stiffness degradation law of RTPs was predicted by introducing a modified 3D Hashin failure criterion and the residual stiffness model. A user-defined material (UMAT) subroutine was developed to evaluate the progressive fatigue failure process of RTPs. A uniaxial tensile fatigue experiment of RTPs was designed to validate the numerical model's correctness. The analysis examined the damage failure modes of RTPs under cyclic loading conditions and revealed the stiffness degradation mechanism. Results suggested that the matrix fatigue damage of the reinforced layer of RTPs is the primary cause of the rapid stiffness degradation, which was observed to be faster with increasing cyclic load stress levels.

Applying LQR to control cross vortex-induced vibration of cylinders based on wake oscillators

Active control of a cylinder's vortex-induced vibration is a research hotspot, and proposing a theoretical model for real-time control of a cylinder's vortex-induced vibration is the foundation of engineering applications. Therefore, this article studies applying the LQR method to control the cross vortex-induced vibration of a single cylinder based on wake oscillators. Firstly, a theoretical control model of the LQR method and wake oscillator was established, and then the model's correctness and numerical solution were verified. Finally, numerical analysis was conducted to investigate the influence of different control parameters on the control of a cylinder's vortex-induced vibration. During the control process, there was no nonlinear bifurcation frequency doubling phenomenon caused by the wake oscillator. Controlling the displacement of a cylinder is more effective than controlling its speed, and the controlled displacement of the cylinder is close to a stationary state, with a lift force close to 2.0. The maximum displacement and lift suppression efficiency is 98.64% and 55.16%. In some cases, the maximum value of hydrodynamic energy at the original system is around 43.85 times that of control systems.

Effect of clearance on the dynamic characteristics of high-speed rolling bearings with multiple defects

Clearance is a pivotal factor in determining the fatigue life of high-speed rolling bearings (HSRBs). As HSRBs naturally experience various defects, their clearance levels tend to rise. However, a clear understanding of the vibration caused by clearance is still lacking. To address this gap, a five-degree-of-freedom dynamics model for HSRBs is proposed. This model accounts for centrifugal force, gyroscopic moment, and time-varying contact angle. In addition, the proposed model incorporates asymptotic theory to describe the defect process and the time-varying contact force derived from the Hertzian point contact theory between rolling elements and raceways. Furthermore, the model considers the variations in load zone and rolling element velocity that arise due to clearance. Applying this model, the dynamic response of HSRBs with different level clearances is calculated. The model's correctness is verified by comparing the dynamic response with the finite element model results and data measured using a test rig built for aero-engine spindle bearing. The results demonstrate that the extent of the load zone shrinks as the clearance increases, although the reduction rate gradually slows down. Since the bearing is loaded only in the load zone, aggravated clearance causes rolling elements to slip in the non-load zone. The effect of clearance on contact force is significantly weaker pronounced than that of defects. These research findings provide a theoretical foundation for the analysis and performance prediction of HSRBs and have important reference values for their optimal design.

Cutter design and the machining strategy to resolve the tooth wear issue for both paired components of single-screw compressors

A single screw compressor consists of paired components of the primary screw rotor and two star-wheel. It is widely applied in enormous industrial applications and is growing continuously. However, the manufacturing for both paired components, including the tooth surface wear issue, must be solved. This paper proposes geometric modeling of cutter design and the analytical cutting for both paired components, in addition to optimizing the contact area to resolve the tooth wear issue. The geometric modeling of the components was determined in LEMP and CEMP models. The cutter profile designs were designed according to gear enveloping theory and pair meshing conditions. The contact area on the tooth flank was successfully enhanced by applying a uniform design and RBF pseudo model. The virtual machining was accomplished in VERICUT, and the machining strategy for both paired components was verified and suitable for actual CNC machining. In addition, the geometric model's correctness for both cutters was confirmed since the profile deviation on both components satisfied the ISO-3650 standard.

Prediction of Diabetes using Machine Learning

Abstract: Diabetes is a chronic condition that could lead to a catastrophe in the world's healthcare system. 537 million people worldwide have diabetes, according to the International Diabetes Federation. By 2045, this number is anticipated to reach 783 million. A rise in blood glucose levels can result in diabetes. Numerous symptoms, which includes frequent urination, increased thirst, and increased appetite, are brought on by this raised blood glucose level. It is a significant contributor to heart failure, stroke, kidney failure, blindness, and amputations. The objective of the given study mainly is to develop the single collective system that combines result of many different types machine learning techniques, including Logistic Regression, Linear Regression, Support Vector Machine, and Random Forest, to more accurately predict diabetes in a patient. It collects the patient's records based on their pregnancy, blood sugar levels, blood pressure, insulin levels, body mass index, and many other factors. Each of the strategies will be used to determine the model's correctness, however, we found that the Support vector machine method had the highest accuracy (77%). The diabetes forecast is then made using the model with the highest accuracy.

Study of the numerical model and humidification strategy of wet-membrane humidifier

Despite the fact that wet-membrane humidifiers are commonly used, their designs and forecasts of humid air are generally based on very simple experimental data, which has resulted in certain design errors. Though some numerical models have been developed in the literature, these models make some idealized assumptions about the fluid flow inside the wet-membrane medium in order to solve the momentum conservation equation. Besides, these models had not been validated using accurate experimental data. Thus, based on a thorough examination of the physical procedure of wet-membrane humidification, a new numerical model for the wet-membrane humidification process is developed that can precisely predict the outlet air temperature and Relative Humidity (RH) under a variety of conditions. To verify the model's correctness, the authors built a wet-membrane humidification test-bed and carried out orthogonal experiments with various inlet factors. The numerical model was validated using the experimental data, and it was then utilized to compare various humidifier design strategies. It is found that the ability of the wet-membrane humidifier to humidify the air under the same heat gain increases when the inlet water is heated rather than the inlet air. While using this method, the inlet water parameters and wet-membrane size must be properly set in order to prevent humid air supersaturation.

Evaluation of Height Correction on Loran Signal's Groundwave Transmission Delay Model

With the ongoing construction and development of enhanced long-range navigation (eLoran) system, people's needs for the accuracy of positioning navigation and timing (PNT) service provided by Loran system are increasing. Due to the high altitude at which the new eLoran transmit station will be constructed, the effects of elevation cannot be discounted. Since the existing Loran propagation model (LPM) hasn't systematically taken the impact of elevation into account, new factors have to be added to existing model for users at high-altitude areas. In this letter, the groundwave transmission delay model's (GTDM) height correction factor is provided. Also, by using a modified ellipsoid expansion technique, it is possible to investigate the impact of elevation on the calculation of geodetic line length, a crucial step in the PNT solution of the Loran system. The findings indicate that, in comparison to the built-in algorithm of the current receiver, taking elevation into consideration will result in unavoidable correction for users who are 250 km or less from the transmitter or for users who are more than 500 km away.

Nonlinear Thermomechanical Static and Dynamic Responses of Bidirectional Porous Functionally Graded Shell Panels and Experimental Verifications

AbstractThe present article examines the nonlinear static/dynamic behavior of the functionally graded porous shell panel with variable geometrical shapes exposed to thermomechanical load. The higher-order shear deformation theory (HSDT) is employed to develop a finite element (FE)-based mathematical model. The geometric nonlinearity is incorporated using Green–Lagrange nonlinear strains (GLNS). Voigt's micromechanical model, in association with power-law (GT-I), sigmoid (GT-II) and exponential (GT-III) kinds of material grading patterns, is adopted to calculate the graded panel's effective properties. Also, even (PRT-I) and uneven (PRT-II) distributions of porosity are considered in the present work. The temperature-dependent (TD) properties are adopted in association with variable temperature fields, i.e., uniform (TD-I), linear (TD-II), and nonlinear (TD-III) for the computation of flexural responses. To compute the desired nonlinear responses, the direct iterative technique is utilized. Convergence is used to validate the established model's stability and correctness is further verified by comparing the current numerical data to published and experimental results. The experiment was carried out by fabricating a few natural fiber-reinforced linearly varying layerwise panels for the test run. The study is further extended to investigate the influence of design parameters on nonlinear static and transient data (flexural/stress) of the functionally graded curved/flat panel considering thermal environmental conditions.

Pressuredrop Response Characteristics for Multi-Injection Well Interfered Vertical Well in Heterogeneous Fractured Anticline Reservoirs

AbstractFractured anticline reservoirs are mostly developed by a line production well located at the top position and a line injecting well located at the bottom position. The production well is often interference with by multiple injecting wells, but there is little related research about multiple injecting well interferences. To solve this problem, an extended bottom-hole pressuredrop (BHPD) response model for production well interfered with by multiple injection wells was presented to capture the injection interference and gravity effect. The proposed model's correctness is validated by the software numerical simulation, and low regimes were identified by the BHPD and its derivative curve. Research results show that: (i) the BHPD derivative curve has a one-half slope line, V-shape, and one slope line in reservoir linear flow regime, inter-porosity flow regime, and interference flow regime, respectively; (ii) the drop rate of pressure increases with the increase of formation transmissibility and storability. The bigger the fracture storability, the more obvious the V-shape feature in the derivative curve of BHPD. As the inter-porosity flow coefficient increases, the V-shape feature emerges later; (iii) the beginning time of the interference flow becomes later when the interference distance increases. When the injection rate trends to the production rate, the BHPD curve shows a slight drop and its derivative curve has an intermittent rupture; (iv) the influence of the gravity effect is not ignored. Due to the gravity effect, the BHPD interfered by constant injection well like the BHPD's behavior interfered by the closed boundary. This work provides technical support for capturing the source and degree of interference from well group in the heterogeneous fractured anticline reservoir.

The big data analytical capability and firm performance: mediating role of supply chain performance

As a method of strengthening overall performance, the capacity to apply big data analytics is becoming increasingly vital in the current business environment. This study aims to examine whether and how supply chain performance mediates the relationship between a company's big data analytical proficiency and its bottom line. The study collects data from two hundred Asian manufacturing companies using a quantitative methodology. Combining structural equation modeling (SEM) and partial least squares analysis, we were able to confirm the central model's correctness (PLS). The results reveal a statistically significant and favorable correlation between big data analytical skills and business success. According to the study, supply chain performance is also a partial mediator of this relationship. According to the findings, supply chain efficiency is essential to a company's success since it promotes the application of big data analytical skills. The outcomes of this study have significant consequences for Asian manufacturing. They emphasize the significance of boosting an organization's analytical capabilities by utilizing big data. The performance of the supply chain is vital in mediating the relationship between the two concepts.