Search

Accurate classification of high-dimensional biomedical data highly depends on the efficient recognition of the data's main features which can be used to assist diagnose related diseases. However, due to the existence of a large number of irrelevant or redundant features in biomedical data, classification approaches struggle to correctly identify patterns in data without a feature selection algorithm. Feature selection approaches seek to eliminate irrelevant and redundant features to maintain or enhance classification accuracy. In this paper, a new wrapper feature selection method is proposed based on the chimp optimization algorithm (ChOA) for biomedical data classification. The ChOA is a newly proposed metaheuristic algorithm whose capability for solving feature selection problems has not been investigated yet. Two binary variants of the ChoA are introduced for the feature selection problem. In the first approach, two transfer functions (S-shaped and V-shaped) are used to convert the continuous version of ChoA to binary. In addition to the transfer function, the crossover operator is utilized in the second approach to improve the ChOA's exploratory behavior. To validate the efficiency of the proposed approaches, five publicly available high-dimensional biomedical datasets, and a few datasets from different domains such as life, text, and image are employed. The proposed approaches were then compared with six well-known wrapper-based feature selection methods, including multi-objective genetic algorithm (GA), particle swarm optimization (PSO), Bat algorithm (BA), ant colony optimization (ACO), firefly algorithm (FA), and flower pollination (FP) algorithm, as well as two standard filter-based feature selection methods using three different classifiers. The experimental results demonstrate that the proposed approaches can effectively remove the least significant features and improve classification accuracy. The suggested wrapper feature selection techniques also outperform the GA, PSO, BA, ACO, FA, FP, and other existing methods in the terms of the number of selected genes, and classification accuracy in most cases. [ABSTRACT FROM AUTHOR]

The paper demonstrates a comprehensive performance assessment of the two metaheuristic swarm-based optimization algorithms namely PSO (Particle swarm optimization), BFOA (Bacterial foraging optimization algorithm), and the hybrid PSO-BFOA optimizer for the alleviation and control of the power oscillations in a two-area four generator system integrated with a large-scale PV-farm. After sunset, the PV-plant operates as VSC (Voltage Source Converter)-STATCOM (Static synchronous compensator) using its overall inverting capabilities for the power system stability improvement. While in the daytime during the faults, the PV-farm immediately stops the active power production and behaves as PV-STATCOM until the normal operating conditions are resumed. The modified version of Kundur's two-area system comprising of a large-scale PV-farm is simulated with MATLAB software. An innovative control strategy employing the two PI controllers distinctly controls the DC-AC currents of the PV-STATCOM. The series compensation is set to an optimal value of 85% and subjected to a 3-φ fault. Zero mechanical dampings, along with extra disturbances of 20% variation in reference voltage and electromagnetic torque are introduced to flaunt the worst damping scenarios. The simulation outcomes and time-domain analysis for various test conditions: without a controller, with PSO-based PV-STATCOM, with BFOA-based PV-STATCOM, and with the Hybrid PSO-BFOA-based PV-STATCOM, reveal that all the system modes are stabilized with PSO application. The stability of modes is progressively improved with BFO control, eventually, the modes are optimally stabilized by deploying the hybrid PSO-BFO algorithm. [ABSTRACT FROM AUTHOR]

This paper presents a powerful swarm intelligence metaheuristic optimization algorithm called Dynamic Cat Swarm Optimization. The formulation is through modifying the existing Cat Swarm Optimization Algorithm. The original Cat Swarm Optimization suffers from the shortcoming of "premature convergence," which is the possibility of entrapment in local optima which usually happens due to the off balance between exploration and exploitation phases. Therefore, the proposed algorithm suggests a new method to provide a proper balance between these phases by modifying the selection scheme and the seeking mode of the algorithm. To evaluate the performance of the proposed algorithm, 23 classical test functions, 10 modern test functions (CEC 2019) and a real-world scenario are used. In addition, the dimension-wise diversity metric is used to measure the percentage of the exploration and exploitation phases. The optimization results show the effectiveness of the proposed algorithm, which ranks first compared to several well-known algorithms available in the literature. Furthermore, statistical methods and graphs are also used to further confirm the outperformance of the algorithm. Finally, the conclusion and future directions to further improve the algorithm are discussed. [ABSTRACT FROM AUTHOR]

The Whale Optimization Algorithm (WOA) is one of the recent meta-heuristic algorithms. WOA has advantages such as an exploration mechanism that leads towards the global optimum, a suitable balance between exploration and exploitation that avoids the local optimum, and a very good exploitation capability. In this study, five new hybrid algorithms are proposed to develop these advantages. Two of them are developed by combining WOA and Particle Swarm Optimization (PSO) algorithms, and three of them are developed by adding the Lévy flight algorithm to this combination in different ways. The proposed algorithms have been tested with 23 mathematical optimization problems, and in order to make a more accurate comparison, the average optimization results and corresponding standard deviation results are calculated by running these algorithms 30 times for each optimization problem. The proposed algorithms' performances were evaluated among themselves, and the WOALFVWPSO algorithm performed better among these algorithms. This proposed algorithm has been first compared with WOA and PSO, then with other algorithms in the literature. According to WOA and PSO, the proposed algorithm performs better in 19 of 23 mathematical optimization problems, and according to other literature, it performs better in 15 of 23 problems. Also, the proposed algorithm has been applied to the pressure vessel design engineering problem and achieved the best result compared to other algorithms in the literature. It has been proven that the WOALFVWPSO algorithm provides competitive solutions for most optimization problems when compared to meta-heuristic algorithms in the literature. [ABSTRACT FROM AUTHOR]

Multilevel inverters (MLIs) are one of the most popular topics of power electronics. Selective harmonic elimination (SHE) method is used to eliminate low-order harmonics in the MLI output voltage by determining the optimum switching angles. It includes the solution of nonlinear sets of transcendental equations. The optimization becomes more difficult as the number of levels in MLIs increases. Therefore, various metaheuristic algorithms have emerged toward obtaining optimal solutions to find the switching angles in the SHE problem in the last decade. In this study, a number of recent metaheuristics, such as ant lion optimization (ALO), hummingbird algorithm (AHA), dragonfly algorithm (DA), harris hawk optimization, moth flame optimizer (MFO), sine cosine algorithm (SCA), flow direction algorithm (FDA), equilibrium optimizer (EO), atom search optimization, artificial electric field algorithm and arithmetic optimization algorithm (AOA), are employed as an attempt to find the best optimization framework to identify switching moments in 11-level MLI. Marine predator algorithm (MPA), whale optimization algorithm (WOA), grey wolf optimizer (GWO), particle swarm optimization (PSO), multiverse optimizer (MVO), teaching–learning-based optimization (TLBO), and genetic algorithm (GA), which are widely used in solving this problem, are selected for performance analysis. AHA, ALO, AOA, DA, EO, FDA, GA, GWO, MFO, MPA, MVO, PSO, SCA, SSA, TLBO and WOA methods meet maximum 8% THD requirement specified in IEEE 519 standard in the range of 0.4–0.9 modulation index. Simulation results show that MFO is superior other algorithms in terms of THD minimization, convergence rate, a single iteration time and robustness. [ABSTRACT FROM AUTHOR]

The multilayer perceptron (MLP), a type of feed-forward neural network, is widely used in various artificial intelligence problems in the literature. Backpropagation is the most common learning method used in MLPs. The gradient-based backpropagation method, which is one of the classical methods, has some disadvantages such as entrapment in local minima, convergence speed, and initialization sensitivity. To eliminate or minimize these disadvantages, there are many studies in the literature that use metaheuristic optimization methods instead of classical methods. These methods are constantly being developed. One of these is an improved grey wolf optimizer (IMP-GWO) proposed to eliminate the disadvantages of the grey wolf optimizer (GWO), which suffers from a lack of search agent diversity, premature convergence, and imbalance between exploitation and exploration. In this study, a new hybrid method, IMP-GWO-MLP, machine learning method was designed for the first time by combining IMP-GWO and MLP. IMP-GWO was used to determine the weight and bias values, which are the most challenging parts of the MLP training phase. The proposed IMP-GWO-MLP was applied to 20 datasets consisting of three different approximations, eight regression problems, and nine classification problems. The results obtained have been suggested in the literature and compared with the gradient descent-based MLP, commonly used GWO, particle swarm optimization, whale optimization algorithm, ant lion algorithm, and genetic algorithm-based MLP methods. The experimental results show that the proposed method is superior to other state-of-the-art methods in the literature. In addition, it is thought that the proposed method can be modeled with high success in real-world problems. [ABSTRACT FROM AUTHOR]

Many optimization algorithms have been used to solve complex real-world problems, motivating many scientists to improve various optimization algorithms. The monarch butterfly optimization algorithm MBO has been proven to have good performance and is an effective tool for solving many problems. However, the migration and updating operators mainly learn from the global best and are often trapped in local optima as well as premature convergence in many optimization problems. This work introduces an adaptive learning strategy and elitism strategy namely ALMBO to enhance the exploration capacity of the algorithm and ensure that the fittest individuals are retained in the next generation. The experimental results on fourteen benchmark functions show that compared with the two representative MBO algorithm and other methods, ALMBO performs much better than the others on mean values, best values, standard deviation and convergence speed. [ABSTRACT FROM AUTHOR]