Design of Intelligent Neuro-Supervised Networks for Brain Electrical Activity Rhythms of Parkinson’s Disease Model

Biomimetics, Journal Year: 2023, Volume and Issue: 8(3), P. 322 - 322

Published: July 21, 2023

The objective of this paper is to present a novel design intelligent neuro-supervised networks (INSNs) in order study the dynamics mathematical model for Parkinson’s disease illness (PDI), governed with three differential classes represent rhythms brain electrical activity measurements at different locations cerebral cortex. proposed INSNs are constructed by exploiting knacks multilayer structure neural back-propagated Levenberg–Marquardt (LM) and Bayesian regularization (BR) optimization approaches. reference data grids input target samples were formulated reliable numerical solver via Adams method sundry scenarios PDI models way variation sensor measure impact activity. designed both backpropagation procedures implemented on created datasets segmented arbitrarily into training, testing, validation mean squared error based fitness function. Comparison outcomes basis exhaustive simulations LM BR methodologies was conducted solutions means learning curves MSE, adaptive control parameters algorithms, absolute error, histogram plots, regression index. endorse efficacy solvers models, but accuracy BR-based relatively superior, albeit cost slightly more computations.

Language: Английский

---

Parameter characterization of PEM fuel cell mathematical models using an orthogonal learning-based GOOSE algorithm

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Sept. 9, 2024

Language: Английский

---

Percentile-Based Adaptive Immune Plasma Algorithm and Its Application to Engineering Optimization

Biomimetics, Journal Year: 2023, Volume and Issue: 8(6), P. 486 - 486

Published: Oct. 14, 2023

The immune plasma algorithm (IP or IPA) is one of the most recent meta-heuristic techniques and models fundamental steps convalescent treatment, attracting researchers’ attention once more with COVID-19 pandemic. IP determines number donors receivers when two specific control parameters are initialized protects their values until end termination. However, determining which appropriate for by adjusting guessing how they interact each other difficult tasks. In this study, we attempted to determine an improved mechanism that depended on dividing whole population into sub-populations using a statistical measure known as percentile then novel variant IPA called (pIPA) was introduced. To investigate performance pIPA, 22 numerical benchmark problems were solved assigning different algorithm. Moreover, complex engineering problems, required filtering noise from recorded signal path planning unmanned aerial vehicle, pIPA. Experimental studies showed percentile-based donor–receiver selection significantly contributed solving capabilities pIPA helped it outperform well-known state-of-art algorithms.

Language: Английский

---

Enhancing the Zebra Optimization Algorithm with Chaotic Sinusoidal Map for Versatile Optimization

Iraqi Journal for Computer Science and Mathematics, Journal Year: 2024, Volume and Issue: 5(1)

Published: Jan. 2, 2024

In this study, the Chaotic Sinusoidal Map (CSM)-enhanced Zebra Optimization Algorithm (CZOA)is introduced. CZOA combines CSM's integration strengths with ZOA's optimization skills. ZOA already exhibitsgreat capabilities, but addition of CSM increases its potential even more. This greatlystrengthens exploration and exploitation skills flexibility for various tasks.CZOA outperforms both original contemporary optimisation methods on 23 benchmark functions,including high-dimensional (FD), multimodal (MM), unimodal (UM) challenges. Using chaos toinvestigate regional optimal determine better convergence exploration-exploitation equilibrium are shownby CZOA, which also shows more profitable solution locations. demonstrates resilience versatilitythrough multiple activities, underscoring as an adaptable tool. CZOAbecomes a potent metaheuristic by combining biological inspiration chaotic dynamics to solve difficultoptimisation problems. Inspired natural behaviour zebras, Optimisation (ZOA) is arelatively new technique. It makes use herd mechanism ideas leadership andfollowing, in members population—zebras case—cooperate issues thebest possible ways

Language: Английский

---

Fault Diagnosis Method for Rolling Bearings Based on Grey Relation Degree

Entropy, Journal Year: 2024, Volume and Issue: 26(3), P. 222 - 222

Published: Feb. 29, 2024

Aiming at the difficult problem of extracting fault characteristics and low accuracy diagnosis throughout full life cycle rolling bearings, a method for bearings based on grey relation degree is proposed in this paper. Firstly, subtraction-average-based optimizer used to optimize parameters variational mode decomposition algorithm. Secondly, vibration signals are decomposed by using optimized results, feature vector intrinsic function component corresponding minimum envelope entropy extracted. Finally, proximity similarity standard distance weighted calculate comprehensive between each state. By comparing different states degrees realized. The XJTU-SY dataset was experimentation, results show that achieves diagnostic 95.24% has better performance compared various algorithms. It provides reference cycle.

Language: Английский

---