The Aquila Optimizer (AO) is a newly proposed, highly capable metaheuristic algorithm based on the hunting and search behavior of the Aquila bird. However, the AO faces some challenges when dealing with high-dimensional optimization problems due to its narrow exploration capabilities and a tendency to converge prematurely to local optima, which can decrease its performance in complex scenarios. This paper presents a modified form of the previously proposed AO, the Locality Opposition-Based Learning Aquila Optimizer (LOBLAO), aimed at resolving such issues and improving the performance of tasks related to global optimization and data clustering in particular. The proposed LOBLAO incorporates two key advancements: the Opposition-Based Learning (OBL) strategy, which enhances solution diversity and balances exploration and exploitation, and the Mutation Search Strategy (MSS), which mitigates the risk of local optima and ensures robust exploration of the search space. Comprehensive experiments on benchmark test functions and data clustering problems demonstrate the efficacy of LOBLAO. The results reveal that LOBLAO outperforms the original AO and several state-of-the-art optimization algorithms, showcasing superior performance in tackling high-dimensional datasets. In particular, LOBLAO achieved the best average ranking of 1.625 across multiple clustering problems, underscoring its robustness and versatility. These findings highlight the significant potential of LOBLAO to solve diverse and challenging optimization problems, establishing it as a valuable tool for researchers and practitioners.
- Klíčová slova
- Aquila optimizer, Data clustering problems, Meta-heuristics optimization algorithms, Opposition-based learning, Optimization problems,
- Publikační typ
- časopisecké články MeSH
Image segmentation using bi-level thresholds works well for straightforward scenarios; however, dealing with complex images that contain multiple objects or colors presents considerable computational difficulties. Multi-level thresholding is crucial for these situations, but it also introduces a challenging optimization problem. This paper presents an improved Reptile Search Algorithm (RSA) that includes a Gbest operator to enhance its performance. The proposed method determines optimal threshold values for both grayscale and color images, utilizing entropy-based objective functions derived from the Otsu and Kapur techniques. Experiments were carried out on 16 benchmark images, which included COVID-19 scans along with standard color and grayscale images. A thorough evaluation was conducted using metrics such as the fitness function, peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and the Friedman ranking test. The results indicate that the proposed algorithm seems to surpass existing state-of-the-art methods, demonstrating its effectiveness and robustness in multi-level thresholding tasks.
- Klíčová slova
- Image segmentation, Medical images, Multi-level threshold, Otsu method, Kapur method, Reptile search algorithm,
- MeSH
- algoritmy * MeSH
- COVID-19 * diagnostické zobrazování virologie MeSH
- lidé MeSH
- počítačové zpracování obrazu * metody MeSH
- poměr signál - šum MeSH
- SARS-CoV-2 izolace a purifikace MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND: Advancements in artificial intelligence (AI) and machine learning (ML) have revolutionized the medical field and transformed translational medicine. These technologies enable more accurate disease trajectory models while enhancing patient-centered care. However, challenges such as heterogeneous datasets, class imbalance, and scalability remain barriers to achieving optimal predictive performance. METHODS: This study proposes a novel AI-based framework that integrates Gradient Boosting Machines (GBM) and Deep Neural Networks (DNN) to address these challenges. The framework was evaluated using two distinct datasets: MIMIC-IV, a critical care database containing clinical data of critically ill patients, and the UK Biobank, which comprises genetic, clinical, and lifestyle data from 500,000 participants. Key performance metrics, including Accuracy, Precision, Recall, F1-Score, and AUROC, were used to assess the framework against traditional and advanced ML models. RESULTS: The proposed framework demonstrated superior performance compared to classical models such as Logistic Regression, Random Forest, Support Vector Machines (SVM), and Neural Networks. For example, on the UK Biobank dataset, the model achieved an AUROC of 0.96, significantly outperforming Neural Networks (0.92). The framework was also efficient, requiring only 32.4 s for training on MIMIC-IV, with low prediction latency, making it suitable for real-time applications. CONCLUSIONS: The proposed AI-based framework effectively addresses critical challenges in translational medicine, offering superior predictive accuracy and efficiency. Its robust performance across diverse datasets highlights its potential for integration into real-time clinical decision support systems, facilitating personalized medicine and improving patient outcomes. Future research will focus on enhancing scalability and interpretability for broader clinical applications.
- Klíčová slova
- Artificial intelligence, Clinical decision support, Disease prediction, Machine learning, Translational medicine,
- MeSH
- lidé MeSH
- neuronové sítě MeSH
- péče orientovaná na pacienta * MeSH
- strojové učení * MeSH
- translační biomedicínská věda * metody MeSH
- translační biomedicínský výzkum * MeSH
- umělá inteligence * MeSH
- výsledek terapie MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
Precise pressure control in shell-and-tube steam condensers is crucial for ensuring efficiency in thermal power plants. However, traditional controllers (PI, PD, PID) struggle with nonlinearities and external disturbances, while classical tuning methods (Ziegler-Nichols, and Cohen-Coon) fail to provide optimal parameter selection. These challenges lead to slow response, high overshoot, and poor steady-state performance. To address these limitations, this study proposes a cascaded PI-PDN control strategy optimized using the electric eel foraging optimizer (EEFO). EEFO, inspired by the prey-seeking behavior of electric eels, efficiently tunes controller parameters, ensuring improved stability and precision. A comparative analysis against recent metaheuristic algorithms (SMA, GEO, KMA, QIO) demonstrates superior performance of EEFO in regulating condenser pressure. Additionally, validation against documented studies (CSA-based FOPID, RIME-based FOPID, GWO-based PI, GA-based PI) highlights its advantages over existing methods. Simulation results confirm that EEFO reduces settling time by 22.7%, overshoot by 78.7%, steady-state error by three orders of magnitude, and ITAE by 81.2% compared to metaheuristic based methods. The EEFO-based controller achieves faster convergence, enhanced robustness to disturbances, and precise tracking, making it a highly effective solution for real-world applications. These findings contribute to optimization-based control strategies in thermal power plants and open pathways for further bio-inspired control innovations.
- Klíčová slova
- Cascaded PI-PDN controller, Electric eel foraging optimizer, Metaheuristics, Nonlinear system, Pressure control, Steam condenser,
- Publikační typ
- časopisecké články MeSH
In recent times, there has been notable progress in control systems across various industrial domains, necessitating effective management of dynamic systems for optimal functionality. A crucial research focus has emerged in optimizing control parameters to augment controller performance. Among the plethora of optimization algorithms, the mountain gazelle optimizer (MGO) stands out for its capacity to emulate the agile movements and behavioral strategies observed in mountain gazelles. This paper introduces a novel approach employing MGO to optimize control parameters in both a DC motor and three-tank liquid level systems. The fine-tuning of proportional-integral-derivative (PID) controller parameters using MGO achieves remarkable results, including a rise time of 0.0478 s, zero overshoot, and a settling time of 0.0841 s for the DC motor system. Similarly, the liquid level system demonstrates improved control with a rise time of 11.0424 s and a settling time of 60.6037 s. Comparative assessments with competitive algorithms, such as the grey wolf optimizer and particle swarm optimization, reveal MGO's superior performance. Furthermore, a new performance indicator, ZLG, is introduced to comprehensively evaluate control quality. The MGO-based approach consistently achieves lower ZLG values, showcasing its adaptability and robustness in dynamic system control and parameter optimization. By providing a dependable and efficient optimization methodology, this research contributes to advancing control systems, promoting stability, and enhancing efficiency across diverse industrial applications.
- Klíčová slova
- DC motor speed regulation, Liquid level control, Mountain Gazelle optimizer, PID controller, Parameter estimation,
- Publikační typ
- časopisecké články MeSH
Many-objective optimization (MaO) is an important aspect of engineering scenarios. In many-objective optimization algorithms (MaOAs), a key challenge is to strike a balance between diversity and convergence. MaOAs employs various tactics to either enhance selection pressure for better convergence and/or implements additional measures for sustaining diversity. With increase in number of objectives, the process becomes more complex, mainly due to challenges in achieving convergence during population selection. This paper introduces a novel Many-Objective Ant Lion Optimizer (MaOALO), featuring the widely-popular ant lion optimizer algorithm. This method utilizes reference point, niche preserve and information feedback mechanism (IFM), to enhance the convergence and diversity of the population. Extensive experimental tests on five real-world (RWMaOP1- RWMaOP5) optimization problems and standard problem classes, including MaF1-MaF15 (for 5, 9 and 15 objectives), DTLZ1-DTLZ7 (for 8 objectives) has been carried out. It is shown that MaOALO is superior compared to ARMOEA, NSGA-III, MaOTLBO, RVEA, MaOABC-TA, DSAE, RL-RVEA and MaOEA-IH algorithms in terms of GD, IGD, SP, SD, HV and RT metrics. The MaOALO source code is available at: https://github.com/kanak02/MaOALO.
- Klíčová slova
- Ant lion optimizer, Convergence, Diversity, MaF benchmark, Many-objective optimization,
- Publikační typ
- časopisecké články MeSH
This research introduces the Multi-Objective Liver Cancer Algorithm (MOLCA), a novel approach inspired by the growth and proliferation patterns of liver tumors. MOLCA emulates the evolutionary tendencies of liver tumors, leveraging their expansion dynamics as a model for solving multi-objective optimization problems in engineering design. The algorithm uniquely combines genetic operators with the Random Opposition-Based Learning (ROBL) strategy, optimizing both local and global search capabilities. Further enhancement is achieved through the integration of elitist non-dominated sorting (NDS), information feedback mechanism (IFM) and Crowding Distance (CD) selection method, which collectively aim to efficiently identify the Pareto optimal front. The performance of MOLCA is rigorously assessed using a comprehensive set of standard multi-objective test benchmarks, including ZDT, DTLZ and various Constraint (CONSTR, TNK, SRN, BNH, OSY and KITA) and real-world engineering design problems like Brushless DC wheel motor, Safety isolating transformer, Helical spring, Two-bar truss and Welded beam. Its efficacy is benchmarked against prominent algorithms such as the non-dominated sorting grey wolf optimizer (NSGWO), multiobjective multi-verse optimization (MOMVO), non-dominated sorting genetic algorithm (NSGA-II), decomposition-based multiobjective evolutionary algorithm (MOEA/D) and multiobjective marine predator algorithm (MOMPA). Quantitative analysis is conducted using GD, IGD, SP, SD, HV and RT metrics to represent convergence and distribution, while qualitative aspects are presented through graphical representations of the Pareto fronts. The MOLCA source code is available at: https://github.com/kanak02/MOLCA.
- Klíčová slova
- Engineering design optimization, Liver cancer algorithm, MOLCA, Multi objective optimization, Non-dominated solution, Pareto front, Pareto solution,
- Publikační typ
- časopisecké články MeSH
The exponential distribution optimizer (EDO) represents a heuristic approach, capitalizing on exponential distribution theory to identify global solutions for complex optimization challenges. This study extends the EDO's applicability by introducing its multi-objective version, the multi-objective EDO (MOEDO), enhanced with elite non-dominated sorting and crowding distance mechanisms. An information feedback mechanism (IFM) is integrated into MOEDO, aiming to balance exploration and exploitation, thus improving convergence and mitigating the stagnation in local optima, a notable limitation in traditional approaches. Our research demonstrates MOEDO's superiority over renowned algorithms such as MOMPA, NSGA-II, MOAOA, MOEA/D and MOGNDO. This is evident in 72.58% of test scenarios, utilizing performance metrics like GD, IGD, HV, SP, SD and RT across benchmark test collections (DTLZ, ZDT and various constraint problems) and five real-world engineering design challenges. The Wilcoxon Rank Sum Test (WRST) further confirms MOEDO as a competitive multi-objective optimization algorithm, particularly in scenarios where existing methods struggle with balancing diversity and convergence efficiency. MOEDO's robust performance, even in complex real-world applications, underscores its potential as an innovative solution in the optimization domain. The MOEDO source code is available at: https://github.com/kanak02/MOEDO .
- Publikační typ
- časopisecké články MeSH