Forecasting of fast fluctuated and high-frequency financial data is always a challenging problem in the field economics modelling. In this study, novel hybrid model with strength fractional order derivative presented their dynamical features deep learning, long-short term memory (LSTM) networks, to predict abrupt stochastic variation market. Stock market prices are dynamic, highly sensitive, nonlinear chaotic. There different techniques for forecast time-variant domain due variability...

Robust modeling of a multimodal dynamic system is challenging and fast-growing area research. In this study, an integrated bi-modal computing paradigm based on Nonlinear Autoregressive Radial Basis Functions (NAR-RBFs) neural network model, new family deep learning with the strength hybrid artificial network, presented for solution nonlinear chaotic dusty (NCDS) tiny ionized gas particles arising in fusion devices, industry, astronomy, space. proposed methodology, special transformations are...

For analysis of physical properties different materials, rectangular porous fins are used to examine the heat transformation through a system. In this paper, metaheuristic is combined with neural computing modelling study effects temperature changes in fin model. Cuckoo search algorithm as an efficient optimization technique find best weights reduce mean squared error required profile. The governing partial differential equation converted into non-linear ordinary subject certain boundary...

In this paper, we have designed a new optimization technique, which is named as the Improved Multi-verse Algorithm with Levy Flights (ILFMVO) algorithm. The quality of population an important factor that can directly or indirectly affect strength algorithm in searching for give n search space optimal solution. Also, having initialization initial randomly generated candidate solutions not effective idea every case, especially when large. Hence, updated flights based Optimizer (LFMVO) by...

In this study, the intelligent computational strength of neural networks (NNs) based on backpropagated Levenberg-Marquardt (BLM) algorithm is utilized to investigate numerical solution nonlinear multiorder fractional differential equations (FDEs). The reference data set for design BLM-NN different examples FDEs are generated by using exact solutions. To obtain solutions, multiple operations training, validation, and testing carried out scheme various orders FDEs. approximate solutions...

The current study delivers a numerical investigation on the performance of heat transfer and flow micropolar fluid in porous Darcy structures with isothermal isoflux walls (boundary conditions) stretching sheet. dynamics mechanism such flows are modelled by nonlinear partial differential equations that reduced to system ordinary utilizing porosity medium similarity functions. Generally, explicit or analytical solutions for problems hard calculate. Therefore, we have designed computer...

In this study, we explore the intricate conduct of gyrotactic microorganisms in a magnetohydrodynamic (MHD) nanofluid flow across Riga plate, using fourth-grade fluid model. The comprehensive investigation encompasses few influential parameters, including non-dimensional viscoelastic parameter α1, cross-viscous α2 third-grade parameters α3, α4, α5, Modified Hartman number M, local Reynolds Re, and inverse Darcy Da⁻¹. Furthermore, effects slip S₁,S₂,S₃ thermophoretic τ on velocity,...

Abstract This paper presents a study investigating the performance of functionally graded material (FGM) annular fins in heat transfer applications. An fin is circular or structure used to improve various systems such as exchangers, electronic cooling systems, and power generation equipment. The main objective this analyze efficiency ring terms temperature distribution. surfaces are exposed convection radiation dissipate heat. A supervised machine learning method was characteristics...

Intrusion Detection System (IDS) plays an effective way to achieve higher security in detecting malicious activities for a couple of years. Anomaly detection is one intrusion system. Current anomaly often associated with high false alarm moderate accuracy and rates when it's unable detect all types attacks correctly. To overcome this problem, we propose hybrid learning approach through combination K-Means clustering Naïve Bayes classification. The proposed will be cluster data into the...

Research community has a growing interest in neural networks because of their practical applications many fields for accurate modeling and prediction the complex behavior systems arising from engineering, economics, business, financial metrological fields. Artificial (ANN) are very flexible function approximations tool used as universal based on separating past dynamics into clusters, which we construct local models to capture potential growth series depends previously known values. In this...

The object of this study was to demonstrate the ability machine learning (ML) methods for segmentation and classification diabetic retinopathy (DR). Two-dimensional (2D) retinal fundus (RF) images were used. datasets DR-that is, mild, moderate, non-proliferative, proliferative, normal human eye ones-were acquired from 500 patients at Bahawal Victoria Hospital (BVH), Bahawalpur, Pakistan. Five hundred RF (sized 256 × 256) each DR stage a total 2500 (500 5) five stages acquired. This research...

In this study, a novel application of neurocomputing technique is presented for solving nonlinear heat transfer and natural convection porous fin problems arising in almost all areas engineering technology, especially mechanical engineering. The mathematical models the are exploited by intelligent strength Euler polynomials based neural networks (ENN’s), optimized with generalized normal distribution optimization (GNDO) algorithm Interior point (IPA). scheme, ENN’s differential equation...

Abstract Biofiltration is a method of pollution management that utilizes bioreactor containing live material to absorb and destroy pollutants biologically. In this paper, we investigate mathematical models biofiltration for mixing volatile organic compounds (VOCs) instance hydrophilic (methanol) hydrophobic ( $$\alpha$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>α</mml:mi> </mml:math> -pinene). The system nonlinear diffusion equations describes the Michaelis-Menten...

Intrusion detection system (IDS) is used to detect various kinds of attacks in interconnected network. Many machine learning methods have also been introduced by researcher recently obtain high accuracy and rate. Unfortunately, a potential drawback all those the rate false alarm. However, our proposed approach shows better results, combining clustering (to identify groups similarly behaved samples, i.e. malicious non-malicious activity) classification techniques classify data into correct...

Intrusion Detection Systems (IDS) have become an important building block of any sound defense network infrastructure.Malicious attacks brought more adverse impacts on the networks than before, increasing need for effective approach to detect and identify such effectively.In this study two learning approaches, K-Means Clustering Naïve Bayes classifier (KMNB) are used perform intrusion detection.K-Means is groups samples that behave similarly dissimilarly as malicious nonmalicious activity in...

Optimisation problems arising in industry are some of the hardest, often because tight specifications products involved. They almost invariably constrained and they involve highly nonlinear, non-convex functions both objective constraints. It is also case that solutions required must be high quality obtained realistic times. Although there already a number well performing optimisation algorithms for such problems, here we consider novel Plant Propagation Algorithm (PPA) which on continuous...

The flow of nanofluid over a bi-directional stretching sheet is quite popular among recent researchers because its industrial and engineering applications. Specifically, such mechanism appears in plastic extrusion, wire drawing, hot rolling, film paper production, fiber glass, cooling metallic plate bath, etc. In this paper, we have studied the effects on for non-Newtonian fluid. Similarity transformations are used to transform governing partial differential equations into system coupled...

In this paper, a mathematical model for wire coating in the presence of pressure type die along with bath Oldroyd 8-constant fluid is presented. The governed by partial differential equation, transformed into nonlinear ordinary equation dimensionless form through similarity transformations. We have designed novel soft computing paradigm to analyze governing defining weighted Legendre polynomials based on neural networks (LeNN). Training design neurons network carried out globally using whale...

In the petroleum reservoir, secondary oil recovery (SOR) process is employed by injecting water into wells to enhance moment of toward production wells. The SOR gives rise instability (fingering) phenomena due force and difference in wettability viscosity at common interface. Since late 1800s, mathematical models reservoirs have been extensively used gas industry. this paper, we investigated saturation two immiscible fluid (oil water) flows through homogeneous porous media during solving...

This paper investigates the mathematical modelling of cybercrime attacks on multiple devices connected to server. model is a very successful way for cybercrime, bio-mathematics, and artificial intelligence investigate comprehend behaviour mannerisms with harmful intentions in computer system. In this computational model, we are studying factors (i.e., viruses, disease infections, cyberattacks) that affect devices. compartmental SEIAR, represents various hardware utilised during cyberattack....

In this study, we introduce an innovative approach for addressing fractional partial differential equations (fPDEs) by combining Monte Carlo-based Physics-Informed Neural Networks (PINNs) with the Cuckoo Search (CS) optimization algorithm, termed PINN-CS. There is a further enhancement in application of quasi-Monte Carlo assessment that comes high efficiency and computational solutions to estimates derivatives. By employing structured sampling nodes comparable techniques used...