Recent applications and advances of African Vultures Optimization Algorithm

Artificial Intelligence Review, Год журнала: 2024, Номер 57(12)

Опубликована: Окт. 17, 2024

Язык: Английский

---

Looking Back the Nonlinear Optical Crystals in a Functionalized Unit's Perspective

Advanced Functional Materials, Год журнала: 2024, Номер unknown

Опубликована: Дек. 15, 2024

Abstract Nonlinear optics, signifying a revolutionary paradigm change within the realm of has ushered in transformative era by employing nonlinear optical crystals to manipulate and harness laser power for at least six decades. The most exciting aspects (NLO)crystal is repercussions bonding over extended functionalized units external force how slight alterations atomic scale can result huge changes macroscopic properties. However, date, precisely controlling unit its potential induce directed property is, yet, not fully realized. Here, NLO are explored prospected from viewpoint unit, with an emphasis on application material design control regulate key properties start regulating their functions. An introduction anionic group theory started here, which considers functional be primary, then turns discussion modification through emerging strategies this facilitates new materials. Additional breakthroughs rational strategy functionalize groups covered, including integration, preferential arrangement induction, microcosmic performance maximization as well supports these materials discovery theoretical method. Beyond gratifying achievements made, some future perspectives move step forward finally provided.

Язык: Английский

---

An effective optimization algorithm for hydrogen fuel cell-based hybrid energy system: A sustainable microgrid approach

International Journal of Hydrogen Energy, Год журнала: 2024, Номер 98, С. 1341 - 1355

Опубликована: Дек. 16, 2024

Язык: Английский

---

Integrated Optimization and Prediction Framework for Titanium-Based Tools: A Henry Gas Solubility and Machine Learning Approach for Surface Roughness and Residual Stress

SSRN Electronic Journal, Год журнала: 2025, Номер unknown

Опубликована: Янв. 1, 2025

Owing to their remarkable material properties, titanium-based tools are generally used in aerospace, automotive, and biomedical services. Machining titanium alloys is complex difficult, characterized by high cutting forces, rapid tool wear, sometimes undesirable surface quality especially residual stress. In this study, we developed a nano-scale imaging-based novel hybrid hybridization platform based on Henry Gas Solubility Optimization (HGSO) state-of-the-art machine learning models predict optimize machining roughness framework, Hypergravity Search optimally tune parameters predictive (e.g., Feedforward Neural Network (FNN)) for both stress, obtain value of R square scores they score 0.94 0.92 respectively. The stress improvements were confirmed through experimental validation, showing 12.8% 10.5% increases, respectively, over the non-optimized conditions. findings validate framework exploring challenges while improving sustainability decreasing wear energy consumption. This correspondence serves as means connect world theory with practical applications offers scalable solution improve machining.

Язык: Английский

---

Evaluation of diffusion and Henry's coefficients of CO2 absorption using Response Surface Methodology and Artificial Neural Network models

Case Studies in Chemical and Environmental Engineering, Год журнала: 2024, Номер 9, С. 100723 - 100723

Опубликована: Апрель 24, 2024

Язык: Английский

---

Convex combination search algorithm: A novel metaheuristic optimization algorithm for solving global optimization and engineering design problems

Journal of Engineering Research, Год журнала: 2024, Номер unknown

Опубликована: Май 1, 2024

In this paper, a novel metaheuristic optimization algorithm (MHOA) called convex combination search (CCS) is proposed as solution to global problems and engineering design problems. CCS based on of rules that depend upon the concept linear combination. These are mathematically modeled guarantee variety solutions at initialization stage achieve equilibrium between exploitation, exploration capabilities generation stage, algorithm's convergence, robustness. A detailed mathematical model offered. As an advantage for algorithm, it requires just two parameters which population size number generations determining optimal any problem. The effectiveness suggested investigated 17 unconstrained multimodal test functions, 7 constrained benchmark having different characteristics. addition, five challenges resolved confirm robustness dependability in resolving applications. efficiency competitiveness were illustrated comparison with other methods. statistical analysis results has been carried out illustrate power algorithm. Finally, sensitivity presented show sensitivities these performance

Язык: Английский

---

IntelELM: A Python Framework for Intelligent Metaheuristic-based Extreme Learning Machine

Neurocomputing, Год журнала: 2024, Номер unknown, С. 129062 - 129062

Опубликована: Ноя. 1, 2024

Язык: Английский

---

Deep learning solutions for inverse problems in advanced biomedical image analysis on disease detection

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Авг. 9, 2024

Inverse problems in biomedical image analysis represent a significant frontier disease detection, leveraging computational methodologies and mathematical modelling to unravel complex data embedded within medical images. These include deducing the unknown properties of biological structures or tissues from observed imaging data, presenting unique challenge decoding intricate phenomena. Regarding this technique has played critical role optimizing diagnostic efficiency by extracting meaningful insights different modalities like molecular imaging, MRI, CT scans. contribute uncovering subtle abnormalities employing iterative optimization techniques sophisticated algorithms, enabling precise early detection. Deep learning (DL) solutions have emerged as robust mechanisms for addressing inverse analysis, especially recognition. involve reconstructing parameters DL model excels representations mappings. This study develops Solution Problems Advanced Biomedical Image Analysis on Disease Detection (DLSIP-ABIADD) technique. The DLSIP-ABIADD exploits approach solve detect presence diseases To problem, uses direct mapping approach. Bilateral filtering (BF) is used preprocessing. Besides, MobileNetv2 derives feature vectors input Moreover, Henry gas solubility (HGSO) method applied optimal hyperparameter selection model. Furthermore, bidirectional long short-term memory (BiLSTM) deployed identify Extensive simulations been involved illustrate better performance experimentation outcomes stated that performs than other models.

Язык: Английский

---

Hierarchical Learning-Enhanced Chaotic Crayfish Optimization Algorithm: Improving Extreme Learning Machine Diagnostics in Breast Cancer

Mathematics, Год журнала: 2024, Номер 12(17), С. 2641 - 2641

Опубликована: Авг. 26, 2024

Extreme learning machines (ELMs), single hidden-layer feedforward neural networks, are renowned for their speed and efficiency in classification regression tasks. However, generalization ability is often undermined by the random generation of hidden layer weights biases. To address this issue, paper introduces a Hierarchical Learning-based Chaotic Crayfish Optimization Algorithm (HLCCOA) aimed at enhancing ELMs. Initially, to resolve problems slow search premature convergence typical traditional crayfish optimization algorithms (COAs), HLCCOA utilizes chaotic sequences population position initialization. The ergodicity chaos leveraged boost diversity, laying groundwork effective global efforts. Additionally, hierarchical mechanism encourages under-performing individuals engage extensive cross-layer enhanced exploration, while top performers directly learn from elite highest improve local exploitation abilities. Rigorous testing with CEC2019 CEC2022 suites shows HLCCOA’s superiority over both original COA nine heuristic algorithms. Ultimately, HLCCOA-optimized extreme machine model, HLCCOA-ELM, exhibits superior performance reported benchmark models terms accuracy, sensitivity, specificity UCI breast cancer diagnosis, underscoring practicality robustness, as well HLCCOA-ELM’s commendable performance.

Язык: Английский

---

GIJA:Enhanced geyser‐inspired Jaya algorithm for task scheduling optimization in cloud computing

Transactions on Emerging Telecommunications Technologies, Год журнала: 2024, Номер 35(7)

Опубликована: Июль 1, 2024

Abstract Task scheduling optimization plays a pivotal role in enhancing the efficiency and performance of cloud computing systems. In this article, we introduce GIJA (Geyser‐inspired Jaya Algorithm), novel approach tailored for task environments. integrates principles Geyser‐inspired algorithm with algorithm, augmented by Levy Flight mechanism, to address complexities optimization. The motivation research stems from increasing demand efficient resource utilization management computing, driven proliferation Internet Things (IoT) devices growing reliance on cloud‐based services. Traditional algorithms often face challenges handling dynamic workloads, heterogeneous resources, varying objectives, necessitating innovative techniques. leverages eruptive dynamics geysers, inspired nature's channeling guide decisions. By combining simplicity effectiveness offers robust framework capable adapting diverse Additionally, integration mechanism introduces stochasticity into process, enabling exploration solution spaces accelerating convergence. To evaluate efficacy GIJA, extensive experiments are conducted using synthetic real‐world datasets representative workloads. Comparative analyses against existing algorithms, including AOA, RSA, DMOA, PDOA, LPO, SCO, GIA, GIAA, demonstrate superior terms quality, convergence rate, diversity, robustness. findings provide promising quality addressing environments (95%), implications system performance, scalability, utilization.

Язык: Английский

---