Computing intelligence for the magnetised chemically reactive bidirectional radiative nanofluid flow through the Bayesian regularisation back-propagated neural network

Pramana, Journal Year: 2024, Volume and Issue: 98(4)

Published: Sept. 23, 2024

Language: Английский

---

Atelectasis detection in chest X-ray images using convolutional neural networks and transfer learning with anisotropic diffusion filter

Informatics in Medicine Unlocked, Journal Year: 2024, Volume and Issue: 45, P. 101448 - 101448

Published: Jan. 1, 2024

Atelectasis is the loss of volume caused by decreasing gas in a specific area lung. It occurs when lung sacs (alveoli) do not fully inflate, resulting lack oxygen to blood, tissues, organs, and fill with alveolar fluid. can be pressure outside your lung, an obstruction, poor airflow, or scarring. critical diagnose this condition as soon possible. Chest X-rays are most commonly utilized diagnostic tool for condition. Examining chest X-rays, however, difficult even professional radiologist. There need improve diagnosis accuracy. As result, study proposes novel detection classification approach rapid atelectasis utilizing patient X-ray data. To from images, we used state-of-the-art models like VGG19, Inception, deep learning method (CNN). This presents effective categorizing images normal atelectasis-infected. offers convolutional neural network (CNN) aid medical experts identifying disease. The anisotropic diffusion filtering (ADF) was image edge preservation, reduce noise, contrast limited adaptive histogram equalization (CLAHE) improving low-intensity images. After evaluating CNN model, it achieved 99.88 % training accuracy, 99 validation test In study, result that outperformed (VGG19 Inception). findings, features provided consistent reliable detecting atelectasis. Therefore, suggested expedites radiologists' screening patients.

Language: Английский

---

A neural network approach to modeling magnetohydrodynamic stagnation point Ree-Eyring flow over a convectively heated stretched surface

International Journal of Modelling and Simulation, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 14

Published: April 7, 2024

This study investigates the application of artificial intelligence (AI) in fluid dynamics, mainly using a neural network trained by Levenberg – Marquardt method (NN-BLMM), to model magnetohydrodynamic (MHD) stagnation point Ree Eyring flow. We focus on this flow over convectively heated stretched surface integrating Cattaneo Christov heat model. The initial complex nonlinear partial differential equations (PDEs) are transformed into ordinary (ODEs) suitable similarity variables. A dataset was generated Lobatto IIIA numerical solver analyze effects various and thermal parameters. NN-BLMM then rigorously evaluated through training, testing, validation phases compared with reference data. ensures model's precision effectiveness. observe that an increase Powell parameter notably reduces fluid's shear resistance, implying decrease viscosity. Concurrently, transfer rate within medium increases internal generation parameter. These findings highlight robustness simulating emphasizing AI's potential provide deeper understanding non-Newtonian behaviors. research has important implications for industrial applications which precise control properties is crucial.

Language: Английский

---

Analysis of the convective heat transfer through straight fin by using the Riemann-Liouville type fractional derivative: Probed by machine learning

Heliyon, Journal Year: 2024, Volume and Issue: 10(4), P. e25853 - e25853

Published: Feb. 1, 2024

This work aims to analyze the transfer of heat through new fractional-order convective straight fins by using Riemann-Liouville type fractional derivatives. The convection is considered in such a way that thermal conductivity depends on temperature. transformed problems are constituted an optimization problem L2 norm remains minimal. objective functions further analyzed with hybrid Cuckoo search (HCS) algorithm use artificial neural network (ANN) mechanism. impacts parameter β, thermo-geometric fin ψ, and dimensionless α explained figures tables. efficiency during whole process larger values ψ. It found ψ decline efficacy. declines profile as we approach integer order. convergence HCS performed each case study. residual error touches E−14 for order α. present results validated Table 6 comparing HPM, VIM LHPM, while HCS-ANN E−13. proves proposed efficient.

Language: Английский

---

Thermal analysis of natural convection in rectangular porous fin wetted with CNTs nanoparticles and thermal radiation

ZAMM ‐ Journal of Applied Mathematics and Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik, Journal Year: 2024, Volume and Issue: 104(8)

Published: May 23, 2024

Abstract In the present investigation, phenomenon of heat conduction in rectangular shaped porous fin wetted with nanofluid (a mixture carbon nanotube [CNT] water as base liquid) is examined using local thermal non‐equilibrium (LTNE) paradigm. The transport mechanism involving and solid phases represented by dimensional governing ordinary differential equations (TGODEs). These are transformed into nonlinear (ODEs) relevant non‐dimensional variables. To solve resultant dimensionless TGODEs, probabilists collocation method Hermite polynomials (PCMHPs) utilized. This study temperature analysis has characteristics internal exterior radiation, convection, conductivity to determine attributes affecting transfer. For both phase aspects, distribution revealed tables graphs. Subsequently, it determined that surface‐ambient radiation parameter levels decreased, profile augmented. variance among decreased an escalation wet parameter. numerical outcomes illustrate presented PCMHP approach not only convenient execute but also provides accurate results.

Language: Английский

---

The use of neural computational analysis for drug delivery applications results in hybrid nanofluid flow between the uniform gap of two concentric tubes

Deleted Journal, Journal Year: 2024, Volume and Issue: 6(4)

Published: April 6, 2024

Abstract The blood-based Ag and TiO 2 Hybrid nanofluids (HNFs) flow between the two tubes are used for drug delivery applications. hybrid have immense potential as agents due to their unique properties, controlled release capabilities, targeting abilities, synergistic effects. Extensive research is being conducted optimize design maximize effectiveness in various therapeutic applications using experimental approaches. recent work has been focused on theoretical analysis existing data. These HNFs functionalized with ligands or antibodies specifically target deliver drugs diseased tissues cells. This targeted approach enhances accumulation at desired site, minimizing systemic toxicity improving treatment outcomes. An external magnetic field applied control of from nanofluids. Magnetic nanoparticles such iron oxide incorporated into nanofluids, which respond a specific location time. offers system. graphical numerical outcomes dimensionless momentum thermal boundary layers investigated discussed. It observed that often exhibit superior heat transfer (HT) primarily high conductivity nanoparticles. Improving helps reduce skin friction by maintaining more uniform temperature distribution near surface. Also, this acts optimization blood analysis. In terms applications, prominent refining through optimized transfer, shown comparison.

Language: Английский

---

Machine learning-based Nusselt number prediction for falling-film evaporators in absorption refrigeration systems

Case Studies in Thermal Engineering, Journal Year: 2024, Volume and Issue: 58, P. 104380 - 104380

Published: April 17, 2024

The evaporator serves as a pivotal component of an absorption refrigeration system (ARS), bolstered by improved wettability and mitigation the irregular arrangement liquid film. complexities evaporation heat transfer characteristics falling films have led to numerous empirical correlations for falling-film Nusselt number (Nu) estimation, demanding substantial computational resources experimental expenses limiting their universal applicability. This study used machine learning predict Nu evaporator. Artificial neural network (ANN) random forest regression (RFR) models were establish novel correlation using experimentally derived dataset. Correlations established six tube types data, ANN, RFR predictions then compared based on Nu. ANN provided high prediction performance within 10 % error R2 0.985 0.999, respectively. from demonstrated satisfactory agreement, typically ±15 results lower than that correlations. optimized demonstrates promising ability correlations, thereby reducing need immense efforts.

Language: Английский

---

Predictive modelling of flow dynamics in micropolar hybrid nanofluids subjected to magnetic dipole influence using nonlinear autoregressive artificial neural networks with exogenous input

Numerical Heat Transfer Part A Applications, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 35

Published: April 22, 2024

In the present research article, we explore intelligence-based numerical computation of a nonlinear autoregressive artificial neural network with exogenous input using Levenberg-Marquardt algorithm (ANN-LMA) trained to analyze unsteady two-dimensional micro-polar flow an incompressible hybrid nanofluid (Al2O3−Fe3O4/Ethylene Glycol) under impact magnetic field introduced by dipole on stretched sheet. first step research, partial differential equations are converted into ordinary appropriate transmission and then solved numerically via Successive Over Relaxation method after applying finite difference method. The numerous emerging parameters solutions is displayed graphically, physical significance discussed. results show that concentration profile displays dwindling trend for Brownian motion parameter, opposite witnessed thermophoretic parameter. Moreover, increasing values dimensionless distance parameter ferromagnetic interaction temperature velocity profiles exhibit tendency. second study, validated outcomes ANN-LMA. For this purpose, suggested ANN-LMA six different scenarios reference dataset points given model. analysis shows LM-SNNs yield similar results, decreasing

Language: Английский

---

A design of computational stochastic framework for the mathematical severe acute respiratory syndrome coronavirus model

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 100, P. 107049 - 107049

Published: Nov. 5, 2024

Language: Английский

---

THEORETICAL REVIEW OF ISSUES RELATED TO POST-AMPUTATION RECOVERY OF MILITARY PERSONNEL: PSYCHOLOGICAL ASPECT

Visnyk Taras Shevchenko National University of Kyiv Military-Special Sciences, Journal Year: 2025, Volume and Issue: 1 (61), P. 26 - 32

Published: Jan. 1, 2025

B a c k g r o u n d . The article presents the findings of theoretical review conducted to analyze issues psychological post-amputation recovery military personnel. loss an extremity is serious trauma that impacts mental state serviceman, jeopardizes their self-esteem, changes perception bodies, disrupts future plans and forces them accept new reality. Thus, all these factors create need for high-quality support during phase. It worth mentioning phase personnel encounter numerous emotional difficulties require comprehensive professional assistance. In particular, they may experience profound feelings loss, fears about future, diminished sense helplessness, even depression. Moreover, process adapting physical limitations mastering use prosthetics are extremely important often psychologically draining stage recovery. Therefore, plays critical role in improving quality life facilitating social adaptation M e t h s At this research authors have relied on methods, mainly analysis, synthesis, generalization, comparison, systematization. Strictly scientific up-to-date references both Ukrainian English were analyzed. R l Despite relevance topic further increased by full-scale invasion taking place territory Ukraine, relevant has been strikingly limited terms number studies dedicated topic, specifically aspect Throughout able identify possible reasons behind insufficient attention devoted issue, namely: encountering own barriers, researchers not being mentally ready work with category respondents (military amputation), encountered while organizing involving C i allowed classify aspects into following categories urgent thorough – states amputations, methodology provided at different stages recovery, skills experts involved post amputation.

Language: Английский

---