Simple Computer Research Articles

Using ChatGPT as a tool during occupational therapy intervention: A case report in mild cognitive impairment

ABSTRACT This case report examined the impact of computer programmed assistive technology developed, using ChatGPT as a tool when designing an occupational therapy intervention on a client’s independence in activities of daily living. A 66-year-old female client with mild cognitive impairment consulted an occupational therapist due to difficulties with activities of daily living. The occupational therapist developed two activity assistance computer programs using ChatGPT as a resource. The client did not interact directly with ChatGPT; instead, the occupational therapist used the technology to design and implement the intervention. A computer programmed assistive technology-based occupational therapy intervention was completed for eight weeks. The occupational therapist trained the client to use these programs in the clinical setting and at home. As a result of the intervention, the client’s performance and independence in daily activities improved. The results of this study emphasize that ChatGPT may help occupational therapists as a tool to design simple computer programmed assistive technology interventions without requiring additional professional input.

Trends in High Performance Computing and Quantum Computing

High Performance Computing (HPC) applies different techniques to complex or large-volume applications, relying on both parallel software and hardware, to reduce their execution time compared to running them on a simple computer. On the other hand, Quantum Computing (QC) emerges as a new paradigm that leverages the properties of Quantum Mechanics for computation. QC has an inherently parallel nature and it is expected to solve some problems faster than classical computing. This paper carries out a bibliographic review to examine the point of view of different authors regarding the relationship between HPC and QC. The objective is to determine the trend of this relationship: Will QC replace classical HPC computing?or Will they complement each other? Also, if they were complementary tools, the aim is to answer: How could they be integrated? How will users access these resources?

Design of retrofit flue gas (CO2) scrubber for dependable clean energy at the Duvha Coal Power Plant

The coal-fired power sector is facing unprecedented pressure due to the shift to low-carbon energy sources and the need to prevent climate change. It is imperative to incorporate advanced technologies into conventional coal-fired power plants to enhance their efficiency, flexibility, and environmental sustainability. One advantage of post-combustion CCS methods is that they may be retrofitted into power plants that are already in place. The goal of this work is to design a CO2 flue gas cleaning retrofit system that will meet the most stringent air quality regulations in an operational coal power station in Southern Africa. It will operate and expedite the removal of undesired gas (CO2) in order to attain ideal requirements for air quality in one of Southern Africa's current coal-fired power plants, the Duvha Coal Power Plant. This study is based on chemical absorption, and explores the mechanistic design of the scrubber, which was accomplished through simple computations and Ansys simulations. The approach for developing a wet CO2 scrubber and LSTG system is based on chemical absorption and is integrated with a pilot plant. The results of the parametric study provide a foundation for a comprehensive industrial system design for South Africa's coal-powered industry. The results show that the scrubber's cylinder height and diameter can be used for an LSTG system and are appropriate for CO2 gas flow and capture. The application of the suggested scrubber design and the LTSG's contributions will allow the coal power station to operate with minimal GHG emissions released into the atmosphere. Instead of shutting down coal power facilities, this cleaning system that completely absorbs CO2 emissions can be used to maintain a robust power infrastructure, rather than being phased out. This will boost the power plant's efficiency over its initial operating efficiency and benefit the nation's economy and the power industry.

On the Cover: Accounting for Localized Deformation: A Simple Computation of True Stress in Micropillar Compression Experiments

On the Cover: Accounting for Localized Deformation: A Simple Computation of True Stress in Micropillar Compression Experiments

A New Hybrid Descent Algorithm for Large-Scale Nonconvex Optimization and Application to Some Image Restoration Problems

Conjugate gradient methods are widely used and attractive for large-scale unconstrained smooth optimization problems, with simple computation, low memory requirements, and interesting theoretical information on the features of curvature. Based on the strongly convergent property of the Dai–Yuan method and attractive numerical performance of the Hestenes–Stiefel method, a new hybrid descent conjugate gradient method is proposed in this paper. The proposed method satisfies the sufficient descent property independent of the accuracy of the line search strategies. Under the standard conditions, the trust region property and the global convergence are established, respectively. Numerical results of 61 problems with 9 large-scale dimensions and 46 ill-conditioned matrix problems reveal that the proposed method is more effective, robust, and reliable than the other methods. Additionally, the hybrid method also demonstrates reliable results for some image restoration problems.

A Multi-Sensor Fusion Underwater Localization Method Based on Unscented Kalman Filter on Manifolds.

In recent years, the simplified computation of position and velocity changes in nonlinear systems using Lie groups and Lie algebra has been widely used in the study of robot localization systems. The unscented Kalman filter (UKF) can effectively deal with nonlinear systems through the unscented transformation, and in order to more accurately describe the robot localization system, the UKF method based on Lie groups has been studied successively. The computational complexity of the UKF on Lie groups is high, and in order to simplify its computation, the Lie groups are applied to the manifold, which efficiently handles the state and uncertainty and ensures that the system maintains the geometric constraints and computational simplicity during the updating process. In this paper, a multi-sensor fusion localization method based on an unscented Kalman filter on manifolds (UKF-M) is investigated. Firstly, a system model and a multi-sensor model are established based on an Autonomous Underwater Vehicle (AUV), and a corresponding UKF-M is designed for the system. Secondly, the multi-sensor fusion method is designed, and the fusion method is applied to the UKF-M. Finally, the proposed method is validated using an underwater cave dataset. The experiments demonstrate that the proposed method is suitable for underwater environments and can significantly correct the cumulative error in the trajectory estimation to achieve accurate underwater localization.

Practical Approach to Studying Evolutionary Methods for Setting Weight Coefficients of Artificial Neural Networks

The article describes the problems of developing neurocontrollers for controlling dynamic objects, including the complexity of forming training data sets. It is indicated that one of the known methods for training an artificial neural network controlling an object is the neuroevolutionary approach, which involves using a genetic algorithm to adjust the synaptic weighting coefficients of an artificial neural network. The idea of using a means of demonstrating the evolutionary approach to adjusting the weighting coefficients of an artificial neural network for practical training of students in the basics of the neuroevolutionary approach is proposed. Software has been developed to demonstrate the neuroevolutionary approach using the example of the evolution of an artificial neural network of a given structure intended to control a simplified computer model of an autonomous vehicle. A method for resolving the problem of stagnation when using the evolutionary approach to training an artificial neural network is described. Options for using the developed software in teaching students the basics of artificial intelligence technologies and evolutionary methods of multicriteria optimization are proposed.

USING HOT POTATOES APP AS TEACHING METHOD FOR VOCABULARY SUBJECT

To learn to read, write, talk, and listen, students must master vocabulary. To get good at the four basic English skills, you need to learn new words. Learners can easily access the Hot Potatoes app from anywhere with an internet connection and a simple computer browser. There are exercise templates in the Hot Potatoes programs that can be used to make web-based tasks that can be uploaded to servers and made available to students. There are six different kinds of web-based workouts that Hot Potatoes can make. These can be used on their own or connected to other workouts or activities to make a number of tasks. The app Hot Potatoes is helpful because it lets students revise and change their work by giving them hints and then giving them comments in the target language. Teachers can also choose which email address will receive student grades by using the Hot Potatoes program. The purpose of this study is to find out what happens to tenth-grade students at SMKN 2 Palangka Raya when they use Hot Potato-based learning materials to improve their language. This study examines how Hot Potatoes used in SMKN 2 Palangka Raya tenth graders. This research topic is whether Hot Potatoes improve students' vocabularies before and after teaching. The research utilizes a pre-experimental design, the one-group pretest-posttest approach, because consists of only one group serving as both the control and experimental groups. In the one-group pretest-posttest design, a single group is monitored both before and after receiving therapy.To address the study topic, the researcher calculates pre- and post-test scores using paired sample t-test. H0 is rejected by paired sample t-test. The 2-tailed Sig. value is 0.000 < 0.05. Students' vocabulary scores changed significantly between pre- and post-test. Paired Sample Statistic showed that the mean before teaching with Hot Potatoes was 52.73 and after was 82.42. Hot Potatoes is alternative for the students in learning English especially in vocabulary. This reason is based on the result of test after getting treatment. The activity using the Hot Potatoes makes the students are easy to understand the material. In addition, this activity invites the students to be active and creative. Active here means that the students participate in studying of English and they feel fun. Meanwhile, creative here means that the students do the gap-fill exercise and matching exercise. The implementation Hot Potatoes in teaching and learning gives positive effect on the students’ achievement. It can be done because by fun learning, information can be understood and maintained well Teachers are suggested to use the media as one of the variations in teaching English and they can use technology as integrated media at school. The other researchers can do the similar research with other media or authoring tool besides Hot Potatoes such as Quizlet, Notion, Kahoot and so on

An automatic approach for the stability analysis of multi-relaxation-time lattice Boltzmann models

This paper is concerned with the weighted L2-stability of the lattice Boltzmann method (LBM) for the incompressible Navier-Stokes equations. Such stability is formulated for the linearized LBM and can lead to convergence proof of the nonlinear problem. A key step in this stability analysis is to find an appropriate decomposition for the Jacobian matrix of the collision term. For multi-relaxation-time (MRT) models, it is very difficult to analytically obtain such a decomposition and how to overcome this difficulty for MRT models is still a challenge. In this paper, we propose an automatic approach to prove the weighted L2-stability of the LBM with general collision models. Instead of exploring the decomposition for each specific model, we partially fix the decomposition and turn to show the symmetry and semi-negative definiteness of the other part of the decomposition, which can be automatically examined by a simple computer code. We apply our automatic approach to ten MRT models and stability conditions are generated by the code immediately. In particular, for the popular D2Q9 orthogonal MRT model, the stability condition we obtained has one less constraint than that given in previous work. As verifications, we also provide some analytical proofs for the stability of orthogonal and weighted-orthogonal MRT models. The proofs are much more complicated than the automatic approach, not to mention that those for nonorthogonal models are unavailable. These demonstrate the efficiency and superiority of the proposed automatic approach. With this approach, proving the weighted L2-stability and thereby the convergence of general MRT models becomes straightforward.

Hybrid Ising Machine and Reinforcement Learning Approach to Folding Lattice Proteins

The hydrophobic polarity (HP) protein folding model is a simplified computation model utilized to study the folding of proteins into their three-dimensional structures. Understanding how proteins fold and misfold is fundamental to designing effective, safe drugs, allowing for targeted therapies and better patient outcomes. The amino acids of a protein can be categorized as either hydrophobic or polar, where the hydrophobic beads tend to cluster together in a properly folded protein to minimize exposure to the surrounding environment. Determining the lowest energy configurations of the HP model is a non-deterministic polynomial (NP) hard problem. One method is formulating the HP model as a quadratic unconstrained binary optimization (QUBO) problem which can be mapped to an Ising machine. In the Ising model, the lowest energy state of the system represents the correct lattice configuration of the folded protein. The Ising machine technique utilized of simulated annealing allows for future application of the work on an integrated silicon photonic chip. Alternatively, reinforcement learning designed with an energy-based reward function can optimize the HP model by adapting to the environment without the consequence of remaining in local minima like that of the Ising machine. A hybrid pipeline combining the Ising machine and reinforcement learning sequentially was designed to determine the two-dimensional lattice configurations of various protein chain lengths and sequences, combining the parallel optimization of the Ising machine on an integrated photonic platform and the adaptability of the reinforcement learning algorithm. Results found that this hybrid model improved the accuracy and ability of determining the lowest energy state in contrast to the Ising machine alone as well as improved the efficiency by reducing the number of iterations required when compared solely to reinforcement learning. Future work focuses on implementing a parallel pipeline approach as well as adapting to a three-dimensional model.

Optimized WAVEWATCH Ⅲ for significant wave height computation using machine learning

This paper addresses the improvement of the skill of a wave generation model in calculating the significant wave height of sea states by proposing a wave correction model based on machine learning techniques. The model corrects the simulated significant wave heights(Hs) by fitting the discrepancies between numerical simulation results and buoy measurement data. We consider the effects of boundaries and the simplified computation of source terms in the wave model, employing a wave correction model to optimize wave results. The research results demonstrate that the integration of the correction model with the physical calculation model can significantly enhance both accuracy and efficiency in wave computations. The MAPE for Hs decreased from 48.38% to 7.14% and from 20.68% to 5.09%. Simultaneously, computational efficiency improved by factors of 1 and 133.2, respectively. Furthermore, the model demonstrated good generalization capabilities, enabling high-precision wave simulations for other locations within the sea area.

An Approach to Near-Optimal Continuous-Thrust Solution for Plane Constellation Deployment

Paving the way in satellite constellation deployment, this article presents the Comprehensive Program (GCP) for planning constellation deployment missions by introducing a near-optimal solution for continuous-thrust maneuvers. The GCP establishes time constraints, enabling appropriate time scheduling and eliminating reconfiguration phases. It considers various cases of satellite departure and arrival sequences, collision avoidance constraints, and time limitations. A near-optimal solution for the continuous-thrust trajectory of each satellite is introduced, relying on the Fourier series approximation of the thrust pointing angle. The Fourier series with constant coefficients replaces the thrust angle in the satellite’s orbital motion equations in polar coordinates. The primary advantage of this near-optimal approach lies in its simplicity in accommodating space perturbations, posing no challenges in problem-solving. Additionally, the approach is beneficial due to its straightforward implementation and simple mathematical computations. This approach does not require pre-determining the revolution number of the transfer trajectory, unlike shape-based methods. The proposed method’s flexibility allows it to adapt and optimize the trajectory without prior assumptions about the number of revolutions required for the mission. Analyses demonstrate the proposed algorithm’s versatility and precision across various scenarios involving different orbital eccentricities, thrust forces, and thrust pointing angles. The constant coefficients of the Fourier series are determined by defining a set of objective functions and minimizing them using the Multi-Objective Particle Swarm Optimization algorithm (MOPSO). The first and second objective functions ensure that the transfer orbit reaches the desired deployment point, while the third and fourth ones guarantee the tangential conditions between the transfer orbit and the final orbit. An additional objective function minimizes the trajectory time. As a perturbation of interest, the effect of Earth’s oblateness is considered.

Simple Inverse Kinematics Computation Considering Joint Motion Efficiency.

Inverse kinematics (IK) is an important and challenging problem in the operation of industrial manipulators. This study proposes a simple IK calculation scheme for an industrial serial manipulator. The proposed technique can calculate appropriate values of the joint variables to realize the desired end-effector position and orientation while considering the motion costs of each joint. Two scalar functions are defined for the joint variables: one is to evaluate the end-effector position and orientation, whereas the other is to evaluate the motion efficiency of the joints. By combining the two scalar functions, the IK calculation of the manipulator is formulated as a numerical optimization problem. Furthermore, a simple algorithm for solving the IK via the aforementioned optimization is constructed on the basis of the simultaneous perturbation stochastic approximation with a norm-limited update vector (NLSPSA). The proposed scheme considers not only the accuracy of the position and orientation of the end-effector but also the efficiency of the robot movement. Therefore, it yields a practical result of the inverse problem. Moreover, the proposed algorithm is simple and easy to implement owing to the high-calculation efficiency of NLSPSA. Finally, the effectiveness of the proposed method is verified through numerical examples using a redundant manipulator.

Effect of solar wind disturbances on small-amplitude simultaneous Forbush events during solar cycle 23

The transient and rapid reduction in galactic cosmic ray (GCR) flux intensity, commonly referred to as Forbush decrease (FD), is widely used as a mediator variable in searching for solar-terrestrial weather linkages. Whereas literature in the field is replete with high-amplitude (FD(%) ⩾3) FD-based analyses, the empirical connections between low-amplitude (FD(%) ⩽3) events and Sun-Earth variables are seldom tested. It is recently observed that the dearth of such studies might be due to the daunting task of accurate detection/precise timing of FDs and other transient astrophysical events. Using a sensitive version of the FD detection algorithm, we selected 264, 267, and 206 low amplitude (FD(%) ⩽3) FDs from the daily GCR data of Hermanus (HRMS), Newark (NWRK) and Oulu (OULU) neutron monitor stations respectively during solar cycle 23. A total of 80 simultaneous small-amplitude FDs were identified from the three stations with a simple coincident computer code. Statistically significant correlations at 95% confidence level exist between the planetary K-index (Kp), disturbance storm time index (Dst), planetary A-index (Ap), and the corresponding simultaneous small-amplitude FDs at OULU station, but not found in HRMS and NWRK data. These significant links between the weak FDs and the geomagnetic indices (Kp, Dst, and Ap) at OULU station suggest that the parameters (Kp, Dst, and Ap) are likely connected with some common solar activities.

The Importance of Statistics in Medical Healthcare

Abstract: Statistical principles play a fundamental role in shaping the landscape of medical science by providing a structured framework for analyzing data, drawing conclusions, and making informed decisions in healthcare settings. In the realm of medical research, statistical principles are crucial for designing experiments, interpreting results, and ensuring the reliability and validity of findings. Key statistical concepts like hypothesis testing, confidence intervals, regression analysis, and survival analysis are extensively utilized in medical studies to assess the effectiveness of treatments, understand disease patterns, and evaluate healthcare interventions. These principles enable healthcare professionals to make evidence-based decisions, tailor treatments to individual patient needs, and continuously improve the quality of care provided to patients. The role of statistics in medical research starts at the planning stage of a clinical trial or laboratory experiment to establish the design and size of an experiment that will ensure a good prospect of detecting effects of clinical or scientific interest. Statistics is again used during the analysis of data (sample data) to make inferences valid in a wider population. In simple situations computation of simple quantities such as P-values, confidence intervals, standard deviations, standard errors or application of some standard parametric or nonparametric tests may suffice.

Automated Assignment of 15N And 13C Enrichment Levels in Doubly-Labeled Proteins.

Uniform enrichment of 15N and 13C in proteins is commonly employed for 2D heteronuclear NMR measurements of the three-dimensional protein structure. Achieving a high degree of enrichment of both elements is important for obtaining high quality data. Uniform labeling of proteins and glycoproteins expressed in higher organisms (yeast or mammalian cell lines) is more challenging than expression in Escherichia coli, a prokaryote that grows on simple, chemically defined media but does not provide appropriate eukaryotic modifications. It is difficult to achieve complete incorporation of both heavy isotopes, and quality control measures are important for quantitating the level of their enrichment. Mass spectrometry measurements of the isotopic distribution of the intact protein or its proteolytic fragments provide the means to assess the enrichment level. A mass accuracy of 1 ppm or better is shown to be required to distinguish the correct combination of 13C and 15N enrichment due to subtle shifts in peak centroids with differences in the underlying, but unresolved, isotopic fine structure. A simple computer program was developed to optimize the fitting of experimental isotope patterns to statistically derived distributions. This method can determine the isotopic abundance from isotope patterns and isotopologue masses in conventional MS data for peptides, intact proteins, and glycans. For this purpose, MATLAB's isotope simulator, isotopicdist, has been modified to permit the variation of 15N and 13C enrichment levels and to perform a two-dimensional grid search of enrichment levels of both isotopes. We also incorporated an alternate isotope simulator, js-emass, into MATLAB for use in the same fitting program. Herein we benchmark this technique on natural abundance ubiquitin and uniformly [15N,13C]-labeled ubiquitin at both the intact and peptide level, outline considerations for data quality and mass accuracy, and report several improvements we have made to the previously reported analysis of the [15N,13C]-enriched human IgG Fc domain, a glycoprotein that has been expressed in Saccharomyces cerevisiae.

Accounting for Localized Deformation: A Simple Computation of True Stress in Micropillar Compression Experiments

Accounting for Localized Deformation: A Simple Computation of True Stress in Micropillar Compression Experiments

RBFsim – A tool for early planning stage of riverbank filtration systems

Riverbank filtration (RBF) is increasingly being considered an effective method to support the management of water supply and the management of groundwater-river water exchange. Literature, however, provides very limited methods for the initial evaluation of the RBF system. Specifically, initial evaluations need to rely on limited data, be cost-effective, and provide sufficient useful output. The paper provides the development of a tool called RBFsim, designed for the early assessment of flow hydraulics in a riverbank filtration (RBF) scheme during site selection and optimization of well operation. The developed tool allows simplified computation (based on the Analytical Element Method or AEM) of the flow field for single and multiple wells in a 2D homogeneous and isotropic aquifer with uniform flow. The tool superimposes analytical solutions for key RBF quantities such as residence time (the time required for river water to reach the well) and the proportions of water (contributed by the river and groundwater) in the well discharge. These solutions are superimposed on the developed flow field. Additionally, the tool can be used to evaluate the impact of riverbed clogging on the operation of the RBF system. The simplified computation due to AEM and limited data requirements allows the tool to be used in handheld (smartphones) or desktop devices with or without internet connection. RBFsim results are verified by comparing them with results from MODFLOW and MODPATH simulations, which are based on entirely different (finite difference) computational schemes. The obtained results from both these models match within the error margin of less than 5%. Further, the practicality and applicability of RBFsim are illustrated using synthetic and field data. While the tool provides a matching river water contribution ratio with field data, it demonstrates the best-fit residence times primarily for higher well discharge rates. These limitations are attributed to complexities observed in the field, such as a heterogeneous aquifer and nonuniform flow. Overall, the developed tool simplifies the complex computations required, particularly for assessing the feasibility and risk of RBF schemes. The developed tool’s methods and code are open-sourced (licensed under CC-BY 4.0), which promotes personalized modifications and extensions.

Pantograph Slider Detection Architecture and Solution Based on Deep Learning.

Railway transportation has been integrated into people's lives. According to the "Notice on the release of the General Technical Specification of High-speed Railway Power Supply Safety Testing (6C System) System" issued by the National Railway Administration of China in 2012, it is required to install pantograph and slide monitoring devices in high-speed railway stations, station throats and the inlet and exit lines of high-speed railway sections, and it is required to detect the damage of the slider with high precision. It can be seen that the good condition of the pantograph slider is very important for the normal operation of the railway system. As a part of providing power for high-speed rail and subway, the pantograph must be paid attention to in railway transportation to ensure its integrity. The wear of the pantograph is mainly due to the contact power supply between the slide block and the long wire during high-speed operation, which inevitably produces scratches, resulting in depressions on the upper surface of the pantograph slide block. During long-term use, because the depression is too deep, there is a risk of fracture. Therefore, it is necessary to monitor the slider regularly and replace the slider with serious wear. At present, most of the traditional methods use automation technology or simple computer vision technology for detection, which is inefficient. Therefore, this paper introduces computer vision and deep learning technology into pantograph slide wear detection. Specifically, this paper mainly studies the wear detection of the pantograph slider based on deep learning and the main purpose is to improve the detection accuracy and improve the effect of segmentation. From a methodological perspective, this paper employs a linear array camera to enhance the quality of the data sets. Additionally, it integrates an attention mechanism to improve segmentation performance. Furthermore, this study introduces a novel image stitching method to address issues related to incomplete images, thereby providing a comprehensive solution.

Innovative thermal management in the presence of ferromagnetic hybrid nanoparticles

In the present work, a simple intelligence-based computation of artificial neural networks with the Levenberg-Marquardt backpropagation algorithm is developed to analyze the new ferromagnetic hybrid nanofluid flow model in the presence of a magnetic dipole within the context of flow over a stretching sheet. A combination of cobalt and iron (III) oxide (Co-Fe2O3) is strategically selected as ferromagnetic hybrid nanoparticles within the base fluid, water. The initial representation of the developed ferromagnetic hybrid nanofluid flow model, which is a system of highly nonlinear partial differential equations, is transformed into a system of nonlinear ordinary differential equations using appropriate similarity transformations. The reference data set of the possible outcomes is obtained from bvp4c for varying the parameters of the ferromagnetic hybrid nanofluid flow model. The estimated solutions of the proposed model are described during the testing, training, and validation phases of the backpropagated neural network. The performance evaluation and comparative study of the algorithm are carried out by regression analysis, error histograms, function fitting graphs, and mean squared error results. The findings of our study analyze the increasing effect of the ferrohydrodynamic interaction parameter β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta$$\\end{document} to enhance the temperature and velocity profiles, while increasing the thermal relaxation parameter α\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\alpha$$\\end{document} decreases the temperature profile. The performance on MSE was shown for the temperature and velocity profiles of the developed model about 9.1703e−10, 7.1313ee−10, 3.1462e−10, and 4.8747e−10. The accuracy of the artificial neural networks with the Levenberg-Marquardt algorithm method is confirmed through various analyses and comparative results with the reference data. The purpose of this study is to enhance understanding of ferromagnetic hybrid nanofluid flow models using artificial neural networks with the Levenberg-Marquardt algorithm, offering precise analysis of key parameter effects on temperature and velocity profiles. Future studies will provide novel soft computing methods that leverage artificial neural networks to effectively solve problems in fluid mechanics and expand to engineering applications, improving their usefulness in tackling real-world problems.