Particle Swarm Optimization for exploring Darcy-Forchheimer flow of Casson fluid between co-axial rotating disks with the Cattaneo-Christov model.

In this paper, we carried out a numerical analysis of the fluid dynamics and heat transfer occurring between two parallel disks. The study accounts for the impact of temperature-dependent fluid viscosity and thermal conductivity. We systematically investigated various parameters, including viscosity, thermal conductivity, rotational behavior (rotation or counter-rotation), and the presence of stretching, aiming to comprehend their effects on fluid velocity, temperature profiles, and pressure distributions. Our research constructs a mathematical model that intricately couples fluid heat transfer and pressure distribution within the rotating system. To solve this model, we employed the 'Particle Swarm Optimization' method in tandem with the finite difference approach. The results are presented through visual representations of fluid flow profiles, temperature, and pressure distributions along the rotational axis. The findings revealed that the change in Casson factor from 2.5 to 1.5 resulted in a reduction of skin friction by up to 65%, while the change in local Nusselt number was minimal. Furthermore, both the viscosity variation parameter and thermal conductivity parameters were found to play significant roles in regulating both skin friction and local Nusselt number. These findings will have practical relevance to scientists and engineers working in fields related to heat management, such as those involved in rotating gas turbines, computer storage devices, medical equipment, space vehicles, and various other applications.

Nonlinear convection stagnation point flow of Oldroyd-B nanofluid with non-Fourier heat and non-Fick's mass flux over a spinning sphere.

The current paper concerned with a non-linear convection flow of the Oldroyd-B nanofluid at a point of stagnation across a rotating sphere under the influence of convective heat and passive control conditions. The analysis of energy and concentration transition has been scrutinized based on the Cattaneo-Christov diffusion model. The formulated coupled mathematical problem involving boundary requirements can be alerted to a set of highly nonlinear ordinary differential equations by employing similarity analysis. The numerical solution for the governing problem was computed by utilizing bvp4c solver method. The performance of velocity fields, skin friction drag, energy, heat transfer rate, and concentration for various control parameters has been analyzed using diagrams and tables. The findings stipulated that velocity, temperature, and nanoparticle are enhanced for the relaxation time constant while they decay for the retardation time parameter. The upshots also confirmed that enlarging magnetic parameters leads to improve both linear velocity and coefficient of skin friction. The velocity profiles are enhanced as a function of the rotation constant. But, normal velocity declines for buoyancy force ratio, and the same trend is being noted for magnetic and relaxation time parameters on angular velocity. The fluid temperature declines for the Prandtl number and augments for thermal convective parameter. The coefficient of skin friction decreases for larger thermal relaxation and rotation parameters, whereas an analogous effect is being noticed for Brownian parameter on the concentration field. Further, the thermophoresis parameter displays an enhancing tendency on temperature as well as concentration profile while bringing down the Nusselt number. The Lewis number and solutal relaxation parameter filter the concentration field. The graph of the streamline is sketched for identical values of the magnetic parameter and noticed that the contour lines increased as magnified. Confirmation of the current outcomes with former studies is presented.

Stability analysis of dual solutions for mixed convection and thermal radiation with hybrid nanofluid flow past shrinking/stretching curved surface.

This study portrays the stability analysis and dual solutions of mixed convection and thermal radiation of hybrid nano-fluid flow past stretching/shrinking a curved surface in the presence of injection/suction conditions. A hybrid nano-fluid, in which water is used as the base fluid, copper and alumina are used as nano-particles, and the magnetic field is taken into account. The present study's findings will provide fruitful implications for future research in the field of fluid dynamics. The bvp4c method using Matlab software is implemented to get the numerical solution of the nonlinear partial differential equation transformed into the ordinary differential equation. The behavior of the first and second solutions under the governing parameters on the curved surface of dimensionless velocity [Formula: see text], shear stress profile [Formula: see text], temperature profile [Formula: see text], skin friction coefficient Cfs, and local Nusselt's number Nus were visualized in figurative and tabular form. From this the following are investigated: as the values of [Formula: see text] increase, the velocity profile for the second solution decreases, and the opposite trend is observed for the first solution. For the values of K and [Formula: see text], the shear stress profile increased for the first solution, and the opposite trend was observed for the second solution, though after some interval points, the inverse of this statement was observed.For the values of [Formula: see text], the upwind thermal boundary layer of the first solution is larger than the second solution.For the value of M uphill, the estimation of the absolute value of [Formula: see text] increases for both the skin friction coefficient and the local Nusselt number. In the second solution, increasing the values of [Formula: see text], Pr, S, Ec, and M has a similar effect on [Formula: see text], Cfs, -[Formula: see text], and Nus. In the first solution, increasing the values of Ec, S, and Pr on [Formula: see text] and Cfs results in a decrease. The first solution has a positive eigenvalue, whereas the second solution has a negative eigenvalue. Agreement between the present analysis and literature is acceptable.

Wavelets based physics informed neural networks to solve non-linear differential equations.

In this study, the applicability of physics informed neural networks using wavelets as an activation function is discussed to solve non-linear differential equations. One of the prominent equations arising in fluid dynamics namely Blasius viscous flow problem is solved. A linear coupled differential equation, a non-linear coupled differential equation, and partial differential equations are also solved in order to demonstrate the method's versatility. As the neural network's optimum design is important and is problem-specific, the influence of some of the key factors on the model's accuracy is also investigated. To confirm the approach's efficacy, the outcomes of the suggested method were compared with those of the existing approaches. The suggested method was observed to be both efficient and accurate.

Entropy generation in radiative magneto-hydrodynamic mixed convective flow of viscoelastic hybrid nanofluid over a spinning disk.

The heat and mass relocation properties of magneto-hydrodynamic mixed convective viscoelastic hybrid nanofluid flow induced by an extending spinning disk under the effect of entropy generation, thermal radiation, convective condition, velocity, and concentration slips has been investigated in this study. For hybrid nanofluid, the amalgamation of aluminum nitride and alumina nanoparticles embedded in carboxymethyl cellulose with a volume mass concentration of 0.0%-0.4% is considered for the study. The acquired system of partial differential equations from the intended problem is translated into ordinary differential equations employing resemblance conversion and solved by the Galerkin finite element approach. The main effects of the governing constraints on the velocity field, temperature dispersion, concentration, Bejan number, entropy production, skin friction, Nusselt number, and Sherwood number were detailed and depicted in graphs and tables. The results show that snowballing in viscoelastic constraint and volume fraction of solid non-sized particles of Al 2 O 3 and AlN can be used to control fluid flow speed. Also, it is observed from the result that an increment in the magnetic field parameter causes a decline in the velocity field. However, the increase in magnetic field constraint and volume fraction of solid non-sized particles of Al 2 O 3 and AlN causes an upsurge in temperature distribution. Entropy generation in the system can also be regulated by using a higher volume fraction of aluminum nitride and alumina nanoparticles. This numerical and theoretical investigation is more useful in bio-viscoelastic fluids, advanced technology, and industry.

Optimization of Pesticides Spray on Crops in Agriculture using Machine Learning.

Pesticides are chemicals used to eradicate pests. Not only are they used for plant protection and livestock in agriculture, but they are also used in public areas to kill mosquitoes, cockroaches, and other pests. Approximately 95% of the pesticides produced are only used in agriculture for crop protection. Every country wants to increase crop production. To protect their crops from pests, farmers must use pesticides. Exposure to pesticides is increasing day by day, whether occupationally or environmentally. This has resulted in an increase in crop production, but it has numerous adverse effects on human health, animal health, and the environment. Farmers repeatedly use the same pesticides on their crops, which is detrimental to human health and the environment. In this research, according to authors, the repetition of pesticides in agriculture is controlled using adjuvant and machine learning algorithms. An adjuvant is a chemical agent that is inserted within the pesticide product for enhanced pesticide performance. By utilizing an algorithm for machine learning, it is no longer necessary to repeatedly spray the same pesticide over the entire crop field in order to determine which sections of the crop field still require repeated pesticide spraying. In this research, the authors predict that 72.5% of insecticides are used in India. Logical regression classification, polynomial regression, and K-nearest neighbor algorithm (KNN) are applied to detect this required field.

Soft computing and statistical approach for sensitivity analysis of heat transfer through the hybrid nanoliquid film in rotating heat pipe.

In this paper, the numerical solution for heat transfer through a rotating heat pipe is studied and a sensitivity analysis is presented by using statistical experimental design technique. Graphene oxide-molybdenum disulfide (GO-MoS2) hybrid nanofluid is taken as working fluid inside the pipe. The impact of the heat pipe parameters (rotation speed, initial mass, temperature difference) on the heat transfer and liquid film thickness is investigated. The mathematical model coupling the fluid mass flow rate and liquid film evolution equations in evaporator, adiabatic, and condenser zones of the heat pipe is constructed. The mathematical model is solved by implementation of "Particle Swarm Optimization" along with the finite difference method. The outcomes demonstrate that hybrid nanoparticles help to improve the heat transfer through the heat pipe and reduce liquid film thickness. The heat transfer rises with increasing temperature difference and reducing inlet mass, and it reduces slightly with rising rotation speed. The difference in liquid film thickness between the evaporator and condenser zones increases with increasing temperature difference and decreasing rotation speed. The impact of increasing the volume fraction of GO on the liquid film thickness is higher than that in the case of the MoS2 nanoparticles. However, an increase of the heat transfer is noticed in case of increasing the volume fraction of GO relative to increasing MoS2 concentration. Statistical analysis of the computed numerical data and the identification of significant parameters for total heat transfer are found using the response surface method. At 95% level of significance, the GO concentration in the hybrid nanofluid, inlet mass of the hybrid nanofluid and the temperature difference inside the evaporator zone of the pipe are found to be significant linear parameters for increasing heat transfer.

A Machine Learning and Deep Learning Approach for Recognizing Handwritten Digits.

Optical character recognition (OCR) can be a subcategory of graphic design that involves extracting text from images or scanned documents. We have chosen to make unique handwritten digits available on the Modified National Institute of Standards and Technology website for this project. The Machine Learning and Depp Learning algorithms are used in this project to measure the accuracy of handwritten displays of letters and numbers. Also, we show the classification accuracy comparison between them. The results showed that the CNN classifier achieved the highest classification accuracy of 98.83%.

Tree-Based and Machine Learning Algorithm Analysis for Breast Cancer Classification.

Breast cancer (BC) is the second leading cause of death in developed and developing nations, accounting for 8% of deaths after lung cancer. Gene mutation, constant pain, size fluctuations, colour (roughness), and breast skin texture are all characteristics of BC. The University of Wisconsin Hospital donated the WDBC dataset, which was created via fine-needle aspiration (biopsies) of the breast. We have implemented multilayer perceptron (MLP), K-nearest neighbor (KNN), genetic programming (GP), and random forest (RF) on the WBCD dataset to classify the benign and malignant patients. The results show that RF has a classification accuracy of 96.24%, which outperforms all the other classifiers.

Personality Prediction with Hybrid Genetic Programming using Portable EEG Device.

This work suggests a method to identify personality traits regarding the targeted film clips in real-time. Such film clips elicit feelings in people while capturing their brain impulses using the electroencephalogram (EEG) devices and examining personality traits. The Myers-Briggs Type Indicator (MBTI) paradigm for determining personality is employed in this study. The fast Fourier transform (FFT) approach is used for feature extraction, and we have used hybrid genetic programming (HGP) for EEG data classification. We used a single-channel NeuroSky MindWave 2 dry electrode unit to obtain the EEG data. In order to collect the data, thirty Hindi and English video clips were placed in a conventional database. Fifty people volunteered to participate in this study and willingly provided brain signals. Using this dataset, we have generated four two-class HGP classifiers (HGP1, HGP2, HGP3, and HGP4), one for each group of MBTI traits overall classification accuracy of the HGP classifier as 82.25% for 10-fold cross-validation partition.

Genetic Programming-Based Feature Selection for Emotion Classification Using EEG Signal.

The COVID-19 has resulted in one of the world's most significant worldwide lock-downs, affecting human mental health. Therefore, emotion recognition is becoming one of the essential research areas among various world researchers. Treatment that is efficacious and diagnosed early for negative emotions is the only way to save people from mental health problems. Genetic programming, a very important research area of artificial intelligence, proves its potential in almost every field. Therefore, in this study, a genetic program-based feature selection (FSGP) technique is proposed. A fourteen-channel EEG device gives 70 features for the input brain signal; with the help of GP, all the irrelevant and redundant features are separated, and 32 relevant features are selected. The proposed model achieves a classification accuracy of 85% that outmatches other prior works.

EEG-Based Personality Prediction Using Fast Fourier Transform and DeepLSTM Model.

In this paper, a deep long short term memory (DeepLSTM) network to classify personality traits using the electroencephalogram (EEG) signals is implemented. For this research, the Myers-Briggs Type Indicator (MBTI) model for predicting personality is used. There are four groups in MBTI, and each group consists of two traits versus each other; i.e., out of these two traits, every individual will have one personality trait in them. We have collected EEG data using a single NeuroSky MindWave Mobile 2 dry electrode unit. For data collection, 40 Hindi and English video clips were included in a standard database. All clips provoke various emotions, and data collection is focused on these emotions, as the clips include targeted, inductive scenes of personality. Fifty participants engaged in this research and willingly agreed to provide brain signals. We compared the performance of our deep learning DeepLSTM model with other state-of-the-art-based machine learning classifiers such as artificial neural network (ANN), K-nearest neighbors (KNN), LibSVM, and hybrid genetic programming (HGP). The analysis shows that, for the 10-fold partitioning method, the DeepLSTM model surpasses the other state-of-the-art models and offers a maximum classification accuracy of 96.94%. The proposed DeepLSTM model was also applied to the publicly available ASCERTAIN EEG dataset and showed an improvement over the state-of-the-art methods.

Dynamics of flow in trapezoidal enclosure having a heated inner circular cylinder containing Casson nanofluid.

In this article, simulation of the two-dimensional flow of natural convective transport in the partially heated lid-driven trapezoidal cavity was presented with finite element method using software called COMSOL Multiphysics®. Inside the cavity a stationary circular cylinder with a high temperature has been placed. The enclosure was filled with C u - H 2 O nanofluid. The flow is assumed to be two-dimensional and has been examined when the parallel sides of the cavity are adiabatic. The temperature on non-parallel sides is assumed to be cold. The top wall of the cavity moves with a velocity η 0 in the positive x-direction, and the considered fluid is a non-Newtonian Casson nanofluid. Computation has been done for the Rayleigh numbers 10 4 , 10 5 and 106, the Casson fluid parameter 0.1 , 0.5 , and 1, and the nanofluid solid volume fraction 0 and 0.15. Prandtl number is kept fixed at P r = 6.2 throughout the calculations. Isotherms and streamlines were sketched to visualize the distribution of temperature and flow field in the cavity. The impacts of governing parameters such as Casson parameter, solid volume fraction, Rayleigh number on heat transfer, and flow field were numerically computed and analyzed. Average Nusselt number also exhibited in a tabular and graphical form to signify the rate of heat transfer in the cavity. It was found that the centers of the two larger circulations were observed to migrate towards the top wall of the cavity as the Rayleigh number increased. Furthermore, heat transport was enhanced as the concentration of nanoparticles increased.

Finite element analysis of mixed convection flow in a trapezoidal cavity with non-uniform temperature.

A two dimensional flow analysis in a cavity shaped isosceles trapezium is carried out. Non-parallel sides of a trapezium are adiabatic. A varying sinusoidal temperature is applied to the lower wall while the upper wall is at constant temperature. Upper wall of the cavity moves with a velocity η 0 in the positive x-direction. Also, B 0 is constant magnetic field of strength aligned in the same x-direction and Newtonian fluid is considered. The values of magnetic field parameter used are H a = 0 , 50 , the Richardson number is R i = 0.1 , 1 , 10 , R e = 100 is Reynolds number used for the analysis, the amplitude of sinusoidal temperature is m = 0.25 , 0.5 , 1 . The impacts of different leading parameters are analyzed by plotting streamlines for flow fields and isotherm contours for temperature of the flow dynamics. The graphs that signify the variation of average Nusselt number and local Nusselt number are sketched for both lower and upper walls of the cavity. Result indicated that with constant temperature the top wall of the boundary layer thickness decreases as Richardson number Ri increases and for bottom wall with variable temperature. The Nusselt number gets higher with an increment in the amplitude of the oscillation of temperature function. Furthermore, the study revealed that the average Nusselt number gets reduced as the intensity of magnetic field is enhanced. The variation in transit of heat at the bottom wall is similar but the maximum value of heat transfer at the bottom wall shows a variation from 3.8 to 20 when H a = 0 and from 3 to 18 when H a = 50 . The accuracy of the present numerical algorithms is also established.