An Enhanced Semisteady‐State Jaya Algorithm With a Control Coefficient and a Self‐Adaptive Multipopulation Strategy

Journal of Electrical and Computer Engineering, Journal Year: 2025, Volume and Issue: 2025(1)

Published: Jan. 1, 2025

This paper introduces the enhanced semisteady‐state Jaya (ESJaya) algorithm, an improved version of (SJaya) algorithm. The ESJaya algorithm uses a control coefficient to regulate influence best solution, achieving better balance between exploration and exploitation. It also features self‐adaptive multipopulation strategy removes absolute value operators in its update equation for performance. Using 20 benchmark functions, is compared with traditional Jaya, SJaya, elitism‐based (SAMPEJaya) algorithms. ranks first obtaining optimum values, mean accuracy, stability, showing overall performance than others. average rank 1.750, followed by SAMPEJaya, SJaya 2.650, 2.700, 2.900, respectively. Wilcoxon signed‐rank test confirms statistical significance rankings. When Snow Geese Algorithm (SGA), Big Bang–Big Crunch (BBBCA), firefly (FA), bat (BA), cuckoo search (CSA), flower pollination (FPA), gives competitive results terms stability. four real‐world engineering problems, recently proposed piranha predation optimization (PPOA) state‐of‐the‐art algorithms, namely, COLSHADE sCMAgES SASS EnMODE finds solutions good consistency, Overall, it has slower convergence longer run time due solution after each update. However, consistently more optimal other

Language: Английский

Hybrid weighted fuzzy production rule extraction utilizing modified harmony search and BPNN

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 31, 2025

Weighted Fuzzy Production Rules (WFPRs) are vital for Clinical Decision Support Systems (CDSSs), significantly impacting diagnostic accuracy and bridging the gap between data-driven insights actionable clinical decisions through knowledge engineering. This paper proposes an integrated approach combining Dynamic Dimension Adjustment Harmony Search (DDA-HS) Algorithm Back Propagation Neural Networks (BPNNs) to enhance WFPR extraction accuracy. DDA-HS dynamically adjusts search space dimensions fitness evaluations, optimizing initial weights in BPNNs leveraging absorbing Markov chain transition probabilities, supporting exploration avoiding local optima high-dimensional spaces. Evaluated against existing optimization methods including (HS), Cuckoo (CS), Adaptive Global Optimal (AGOHS), with (HSCS) Algorithms, achieves 74.48% BPNN classification 77.08% on PIMA dataset, representing improvements of 3.6% 6.5%, respectively. enhances interpretability by revealing feature influences decision-making, improving both transparency. The proposed method offers a robust framework reliable interpretable CDSSs healthcare.

Language: Английский

Enhancement of AVR system performance by using hybrid harmony search and dwarf mongoose optimization algorithms

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

Published: Nov. 8, 2024

Innovations in control algorithms, integration of smart grid technologies, and advancements materials manufacturing techniques all push the boundaries AVR performance. As demand for power systems progresses with complexity variety loads, conventional designs may struggle to handle these ever-changing circumstances efficiently. Therefore, need new optimization methods is crucial bolstering efficiency, reliability, adaptability AVRs. Thus, this work aims improve performance system controller by using a novel hybrid technique between Harmony Search (HS) Dwarf Mongoose Optimization (DMO) algorithms tune proportional-integral-derivative (PID) acceleration (PIDA) parameters. The suggested approach ensures an accurate solution balanced exploration exploitation rates. reliability proposed HS-DMOA verified through comparison different carried out on time frequency indicators, disturbances form changes constants, dynamic input signals. PID-based has better overshoot than HS, LUS, TLBO, SMA, RSA, L-RSAM 20.37%, 18.5%, 2.77%, 5.55%, respectively. Regarding phase margin, TLBO 39%, 37%, 38%, While PIDA-based PID HS-DMOA-based 14%, 17%, 20%, Moreover, robustness under disturbance proved PIDA based enhancement around 0.3%~20% cases. Finally, main contribution paper propose relatively method enhance detailed analysis domains normal disturbances.

Language: Английский