Using spotted hyena optimizer for training feedforward neural networks

Today, the use of permanent magnet brushless DC (PMBLDC) motors in vehicles is increasing due to the characteristics of sensorless operation. PMBLDC motor controllers can control the speed and position in the closed-loop feedback system without the need for a position sensor mounted on the shaft. Proportional – Integral – Derivative (PID) controller is one of the most common feedback control algorithms used in PMBLDC motor controllers. Optimizing problems using deterministic methods such as Lagrange and simplex methods requires basic information and complex calculations. Meta-heuristic algorithms are a type of stochastic algorithm that is used to find the optimal solution. Meta-heuristic algorithms are divided into three general categories: evolutionary algorithms, swarm intelligence algorithms, and stochastic algorithms. In this paper, using 14 metaheuristic optimisation algorithms, PID control parameters including settling time, time rise, overshoot, and stability of step response of the mentioned system are optimised. In this paper, 14 meta-heuristic algorithms are simulated and evaluated to optimise the PID coefficients of the controller, including settling time, rising time, excessive increase, and step response stability. The simulation result shows that the genetic algorithm (GA) has the best performance in terms of cost function and biogeography-based optimisation (BBO) in terms of settling time and rising time parameters. Finally, the simulation results are confirmed using experimental results.

Boosted ANFIS model using augmented marine predator algorithm with mutation operators for wind power forecasting

Several optimization problems from various types of applications have been efficiently resolved using available meta-heuristic algorithms such as Particle Swarm Optimization and Genetic Algorithm. Recently, many meta-heuristic optimization techniques have been extensively reported in the literature. Nevertheless, there is still room for new optimization techniques and strategies since, according to the literature, there is no meta-heuristic optimization algorithm that may be considered as the best choice to cope with all modern optimization problems. This paper introduces a novel meta-heuristic optimization algorithm named Dynamic Group-based Optimization Algorithm (DGCO). The proposed algorithm is inspired by the cooperative behavior adopted by swarm individuals to achieve their global goals. DGCO has been validated and tested against twenty-three mathematical optimization problems, and the results have been verified by a comparative study with respect to state-of-the-art optimization algorithms that are already available. The results have shown the high exploration capabilities of DGCO as well as its ability to avoid local optima. Moreover, the performance of DGCO has also been verified against five constrained engineering design problems. The results demonstrate the competitive performance and capabilities of DGCO with respect to well-known state-of-the-art meta-heuristic optimization algorithms. Finally, a sensitivity analysis is performed to study the effect of different parameters on the performance of the DGCO algorithm.

Cross-correlation stacking-based microseismic source location using three metaheuristic optimization algorithms

In these recent years, several metaheuristic optimization algorithms have been developed to solve complex real-world problems. However, according to the no free lunch theorem, there is no metaheuristic algorithm which has the best suited for solving all optimization problems. Therefore, developing new metaheuristic algorithms is an open problem. Two major categories of metaheuristics are swarm intelligence and evolutionary algorithms. Both of them have their own advantages. In this paper, we present a naturally swarm and evolutionary algorithm in which its particles have memory, collaboration, information sharing, and competition inherited from one specific analogy. So, it has the advantages of both swarm and evolutionary algorithms without complications of hybridizing them. We formulate a new metaheuristic optimization algorithm called open source development model algorithm (ODMA) inspired by open source development model and communities, in such a way that each potential solution is considered as a software, and by evolution of the softwares, better solutions of the function that should be optimized are searched. The main operations of the algorithm include employing features and methods of leading softwares, evolution of leading softwares based on their history and forking from leading softwares. After a detailed formulation and explanation of its implementation, the algorithm is evaluated by $$17$$17 well-known benchmark functions, and the results are compared with PSO, ICA, and GA. The results show that ODMA outperforms GA, PSO, and ICA in terms of finding the global optimum and convergence.

Spotted hyena optimizer (SHO) is a new metaheuristic algorithm that replicates spotted hyenas' hunting and social behaviour. This article proposes novel SHO algorithm that utilizes chaotic maps for fine‐tuning of control parameters. The chaotic maps help SHO to enhance the searching behaviour and preclude the solution to get trapped in local optima. The authors suggest 10 novel chaotic versions of SHO. The algorithms' performance is evaluated using 29 standardized test functions. The finding reveal that some of the presented algorithms outperform the standard SHO in terms of search capability and solution quality. In addition, five competitive approaches are compared with the suggested algorithms. It is observed from the results that chaos‐based spotted hyena optimizer (CSHO) achieved approximately 3% improvement over SHO in terms of fitness value. CSHO is also tested using five engineering design problems. CSHO achieved a 3%–5% improvement over the existing metaheuristic algorithms in terms of optimal design cost. Experimental results reveal that CSHO outperforms the existing metaheuristic algorithms.

News media always pursue informing the public at large. It is impossible to overestimate the significance of understanding the semantics of news coverage. Traditionally, a news text is assigned to a single category; however, a piece of news may contain information from more than one domain. A multi-label text classification model for news is proposed in this paper. The proposed model is an automated expert system designed to optimize CNN’s classification of multi-label news items. The performance of a CNN is highly dependent on its hyperparameters, and manually tweaking their values is a cumbersome and inefficient task. A high-level metaheuristic optimization algorithm, spotted hyena optimizer (SHO), has higher advanced exploration and exploitation capabilities. SHO generates a collection of solutions as a group of hyperparameters to be optimized, and the process is repeated until the desired optimal solution is achieved. SHO is integrated to automate the tuning of the hyperparameters of a CNN, including learning rate, momentum, number of epochs, batch size, dropout, number of nodes, and activation function. Four publicly available news datasets are used to evaluate the proposed model. The tuned hyperparameters and higher convergence rate of the proposed model result in higher performance for multi-label news classification compared to a baseline CNN and other optimizations of CNNs. The resulting accuracies are 93.6%, 90.8%, 68.7%, and 95.4% for RCV1-v2, Reuters-21578, Slashdot, and NELA-GT-2019, respectively.

3 - Lévy Flights and Global Optimization

Optimizing resource allocation and routing to satisfy service needs is paramount in large-scale networks. Software-defined networking (SDN) is a new network paradigm that decouples forwarding and control, enabling dynamic management and configuration through programming, which provides the possibility for deploying intelligent control algorithms (such as deep reinforcement learning algorithms) to solve network routing optimization problems in the network. Although these intelligent-based network routing optimization schemes can capture network state characteristics, they are prone to falling into local optima, resulting in poor convergence performance. In order to address this issue, this paper proposes an African Vulture Routing Optimization (AVRO) algorithm for achieving SDN routing optimization. AVRO is based on the African Vulture Optimization Algorithm (AVOA), a population-based metaheuristic intelligent optimization algorithm with global optimization ability and fast convergence speed advantages. First, we improve the population initialization method of the AVOA algorithm according to the characteristics of the network routing problem to enhance the algorithm’s perception capability towards network topology. Subsequently, we add an optimization phase to strengthen the development of the AVOA algorithm and achieve stable convergence effects. Finally, we model the network environment, define the network optimization objective, and perform comparative experiments with the baseline algorithms. The experimental results demonstrate that the routing algorithm has better network awareness, with a performance improvement of 16.9% compared to deep reinforcement learning algorithms and 71.8% compared to traditional routing schemes.

Chlorophyll-a (Chl-a) concentration monitoring is very important for managing water resources and ensuring the stability of marine ecosystems. Due to their high operating efficiency and high prediction accuracy, backpropagation (BP) neural networks are widely used in Chl-a concentration inversion. However, BP neural networks tend to become stuck in local optima, and their prediction accuracy fluctuates significantly, thus posing restrictions to their accuracy and stability in the inversion process. Studies have found that metaheuristic optimization algorithms can significantly improve these shortcomings by optimizing the initial parameters (weights and biases) of BP neural networks. In this paper, the adaptive nonlinear weight coefficient, the path search strategy “Levy flight” and the dynamic crossover mechanism are introduced to optimize the three main steps of the Artificial Ecosystem Optimization (AEO) algorithm to overcome the algorithm’s limitation in solving complex problems, improve its global search capability, and thereby improve its performance in optimizing BP neural networks. Relying on Google Earth Engine and Google Colaboratory (Colab), a model for the inversion of Chl-a concentration in the coastal waters of Hong Kong was built to verify the performance of the improved AEO algorithm in optimizing BP neural networks, and the improved AEO algorithm proposed herein was compared with 17 different metaheuristic optimization algorithms. The results show that the Chl-a concentration inversion model based on a BP neural network optimized using the improved AEO algorithm is significantly superior to other models in terms of prediction accuracy and stability, and the results obtained via the model through inversion with respect to Chl-a concentration in the coastal waters of Hong Kong during heavy precipitation events and red tides are highly consistent with the measured values of Chl-a concentration in both time and space domains. These conclusions can provide a new method for Chl-a concentration monitoring and water quality management for coastal waters.

A modified reptile search algorithm for global optimization and image segmentation: Case study brain MRI images

In order to solve the problem that the traditional long-term high-speed traffic forecasting algorithm is affected by the approximation ability of the function and easy to fall into the local mass value, we wrote a multivariate-based highway traffic forecasting algorithm scaling and convolutional networks. Because the feedforward wavelet neural network algorithm predicts the short-term traffic flow in different areas, it is necessary to examine the ability to predict the difference between different models. From the standard feedforward wavelet neural network algorithm using global optimization capabilities, we improve the wolf pack algorithm, improve the search accuracy of the algorithm, get the best solution of the estimated value of the work according to the search results when completing the research objectives, and get the ability to predict the work of the model. Feedforward neural network algorithm: we develop and obtain the best short-term high-speed traffic forecast values. The results are as follows: after using the author’s algorithm, the processing time increases by 1.5 seconds, but the average percentage of errors decreases by more than 50%, in fact the error and the root mean square error decreased by about 30%, and the smoothing coefficient increased by about 1%. The prediction of the author’s algorithm for short-term high-speed traffic is better than the wavelet neural network prediction algorithm, and the prediction accuracy and stability of the author’s algorithm are higher.

Metaheuristic optimization algorithms are characterized by stochastic behavior, making each optimization run unique. In addition, metaheuristic algorithms are usually governed by a number of control parameters that require problem-specific tuning. Many publications on metaheuristic algorithms lack the kind of rigorous statistical convergence assessment that is needed to compensate for the above uncertainties, making it impossible to assess the optimality of the resulting design or the effectiveness of the optimization method. In this contribution, we propose a method to assess the performance (i.e. the ability to find the best known solution and the associated computational cost) of a metaheuristic algorithm that takes into account the influence of its control parameters. First, a large number of simulations (independent optimization runs) are performed, where the values of the control parameters are randomly selected from predefined sets of realistic possibilities. Next, for every value of every control parameter, the corresponding subset of simulations is considered in order to infer the relevant conditional performance statistics. As a example, the approach is used to assess the performance of the genetic algorithm built into matlab for a 25-bar truss test case. It is observed that, for the algorithm and the test case considered, the majority of the control parameters have little influence on algorithm performance.

A fast and robust algorithm for training feedforward neural networks (FNNs) by using a variable forgetting factor and U-D factorization-based recursive prediction error (RPE) method is proposed. In comparison with the backpropagation (BP) and RPE based learning algorithms, the proposed algorithm, called UD-RPE, can provide much more accurate learning results in fewer iterations with fewer hidden nodes and improve convergence rate and numerical stability (robustness). In addition, it is less sensitive to start-up parameters, such as initial weights and initial covariance matrix, and the randomness in the observed data. It also has good generalization ability and needs less learning time. Simulation results of nonlinear dynamic system modeling and identification show that the algorithm proposed here is an effective and efficient learning algorithm for FNNs.

Metaheuristic optimization algorithms are tools based on mathematical concepts that are used to solve complicated optimization issues. These algorithms are intended to locate or develop a sufficiently good solution to an optimization issue, particularly when information is sparse or inaccurate or computer capability is restricted. Power systems play a crucial role in promoting environmental sustainability by reducing greenhouse gas emissions and supporting renewable energy sources. Using metaheuristics to optimize the performance of modern power systems is an attractive topic. This research paper investigates the applicability of several metaheuristic optimization algorithms to power system challenges. Firstly, this paper reviews the fundamental concepts of metaheuristic optimization algorithms. Then, six problems regarding the power systems are presented and discussed. These problems are optimizing the power flow in transmission and distribution networks, optimizing the reactive power dispatching, optimizing the combined economic and emission dispatching, optimal Volt/Var controlling in the distribution power systems, and optimizing the size and placement of DGs. A list of several used metaheuristic optimization algorithms is presented and discussed. The relevant results approved the ability of the metaheuristic optimization algorithm to solve the power system problems effectively. This, in particular, explains their wide deployment in this field.