Metaheuristic-optimised gradient boosting models for predicting pavement quality and functional-structural performance indices

Chapter 4 - Hybrid nature-inspired algorithms for the optimal tuning of fuzzy controllers

Interpreting gravity anomalies caused by fault formations is associated with hydrocarbon systems, mineralized areas and hazardous zones and is the main goal of this research. To achieve an effective and robust model over the geologically faulted structures from gravity anomalies, we present a nature‐inspired hybrid algorithm, which synergizes the physics of the particle swarm optimization and gravitational search algorithm with variable inertia weights. The basic principle of developed particle swarm optimization and gravitational search algorithm method is to synergistically use the exploratory strengths of gravitational search algorithm with the exploitation capacity of particle swarm optimization in order to optimize and enhance the effectiveness by both algorithms. The technique has been tested on synthetic gravity data with varying settings of noises over geologically faulted structure before being applied to field data taken from Ahiri‐Cherla and Aswaraopet master fault present in Pranhita–Godavari valley, India. The optimization process is further refined through normalized Gaussian probability density functions, confidence intervals, histograms and correlation matrices to quantify uncertainty, stability, sensitivity and resolution. When dealing with field data, the true model is never known; in these circumstances, the quality of the outcome can only be inferred from the uncertainty in the mean model. The research utilizes a 68.27% confidence intervals to identify a location where the probability density function is more dominant. This region is then used to evaluate the mean model, which is expected to be more appropriate and closer to the genuine model. Correlation matrices further provide a clear demonstration of the strong connection between layer parameters. The results suggest that particle swarm optimization and gravitational search algorithm is less affected by model parameters and yields geologically more consistent outcomes with little uncertainty in the model, aligning well with the available results. The analysed results show that the method we came up with works well and is stable when it comes to solving the two‐dimensional gravity inverse problem. Future research may involve extending the approach to three‐dimensional inversion problems, with potential improvements in computational efficiency and search accuracy for global optimization methods.

—This article presents a hybrid algorithm based on the particle swarm optimization and gravitational search algorithms for solving optimal power flow in power systems. The proposed optimization technique takes advantages of both particle swarm optimization and gravitational search algorithms by combining the ability for social thinking in particle swarm optimization with the local search capability of the gravitational search algorithm. Performance of this approach for the optimal power flow problem is studied and evaluated on standard IEEE 30-bus and IEEE 118-bus test systems with different objectives that reflect fuel cost minimization, voltage profile improvement, voltage stability enhancement, power loss reduction, and fuel cost minimization with consideration of the valve point effect of generation units. Simulation results show that the hybrid particle swarm optimization–gravitational search algorithm provides an effective and robust high-quality solution of the optimal power flow problem.

Hybridization of Constriction Coefficient Based Particle Swarm Optimization and Gravitational Search Algorithm for Function Optimization

Evolutionary algorithms are among the most powerful algorithms for optimization, Firefly algorithm (FA) is one of them that inspired by nature. It is an easily implementable, robust, simple and flexible technique. On the other hand, Integration of this algorithm with other algorithms, can be improved the performance of FA. Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA) are suitable and effective for integration with FA. Some method and operation in GSA and PSO can help to FA for fast and smart searching. In one version of the Gravitational Search Algorithm (GSA), selecting the K-best particles with bigger mass, and examining its effect on other masses has a great help for achieving the faster and more accurate in optimal answer. As well as, in Particle Swarm Optimization (PSO), the candidate answers for solving optimization problem, are guided by local best position and global best position to achieving optimal answer. These operators and their combination with the firefly algorithm (FA) can improve the performance of the search algorithm. This paper intends to provide models for improvement firefly algorithm using GSA and PSO operation. For this purpose, 5 scenarios are defined and then, their models are simulated using MATLAB software. Finally, by reviewing the results, It is shown that the performance of introduced models are better than the standard firefly algorithm.

— In this paper, two optimization algorithms i.e., Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA) are combined to produce a hybrid population-based algorithm PSOGSA. The approach of HPSOGSA is to use the assessment of PSO using the social thinking capability and the manipulation of GSA using the local search proficiency. To increase the performance of HPSOGSA, some benchmark functions are used. Two standard database ORL and YALE is used to assess the classification performance of the proposed method. Classification accuracy is compared for diverse number of training samples per class. Further lead of proposed method is confirmed by analyzing percentage improvement in classification accuracy. With limited accessibility of training sample, percentage enhancement is very successful for face recognition applications. Keywords: Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), Particle Swarm Optimization and Gravitational Search Algorithm (PSOGSA), Hybrid Particle Swarm Optimization and Gravitational Search Algorithm (HPSOGSA). Cite this Article Purvaa Saxena, Gargi Mishra, Apoorva Aggarwal, Ayush Priyadarshi, Nitin Kumar, Rahul. Pattern Recognition Using Hybrid Meta-Heuristic. Journal of Artificial Intelligence Research & Advances. 2019; 6(2): 100–108p.

Summary As global energy demand continues to rise, the need to exploit unconventional resources like shale oil and gas has become progressively urgent. Total organic carbon (TOC) functions as an essential index for evaluating sweet spot and reservoir production in shale oil and gas exploration. To address the shortcomings of existing TOC prediction approaches, we establish a novel TOC prediction model using the extreme gradient boosting (XGBoost) algorithm optimized by grid search (GS) and particle swarm optimization (PSO). Initially, the GS method is utilized to ascertain the optimal values for the three integer hyperparameters, along with the optimal value ranges for four decimal hyperparameters within the XGBoost model. Subsequently, the PSO method is capable of swiftly identifying the optimal values for the four decimal hyperparameters based on the preceding work. Thus, a GS-PSO-XGBoost model with seven optimal hyperparameters is formulated for TOC prediction utilizing conventional well logs. Meanwhile, Shapley additive explanation (SHAP) is used to enhance the interpretability of the model. When compared with extreme learning machine (ELM), support vector regression (SVR), random forest (RF), XGBoost, and GS-XGBoost models, the GS-PSO-XGBoost method demonstrates superior performance for TOC prediction. The GS-PSO-XGBoost method effectively addresses issues previously encountered in TOC prediction studies, such as slow calculating speed, overfitting, and convergence to local minima, thereby significantly enhancing prediction accuracy. This study deepens the use of machine learning (ML) within petroleum engineering, offering a dependable technical reference for the further analysis of unconventional oil-gas resources exploration.

A novel hybrid particle swarm optimization and gravitational search algorithm for solving economic emission load dispatch problems with various practical constraints

Particle swarm optimization (PSO) has been proven to show good performance for solving various optimization problems. However, it tends to suffer from premature stagnation and loses exploration ability in the later evolution period when solving complex problems. This paper presents a sequential hybrid particle swarm optimization and gravitational search algorithm with dependent random coefficients called HPSO-GSA, which first incorporates the gravitational search algorithm (GSA) with the PSO by means of a sequential operating mode and then adopts three learning strategies in the hybridization process to overcome the aforementioned problem. Specifically, the particles in the HPSO-GSA enter into the PSO stage and update their velocities by adopting the dependent random coefficients strategy to enhance the exploration ability. Then, the GSA is incorporated into the PSO by using fixed iteration interval cycle or adaptive evolution stagnation cycle strategies when the swarm drops into local optimum and fails to improve their fitness. To evaluate the effectiveness and feasibility of the proposed HPSO-GSA, the simulations were conducted on benchmark test functions. The results reveal that the HPSO-GSA exhibits superior performance in terms of accuracy, reliability, and efficiency compared to PSO, GSA, and other recently developed hybrid variants.

Performance analysis and feasibility study of ant colony optimization, particle swarm optimization and cuckoo search algorithms for inverse heat transfer problems

Recently, the integration of distributed generation (DG) units to distribution networks has grown significantly. This integration provides an opportunity to control the power flow, resulting in the optimal power flow (OPF) at the distribution level. OPF can reduce system losses and decrease the DG generation costs. Additionally, it can improve the voltage profile. Applying OPF to distribution networks is a challenging task since the nature of distribution networks makes the OPF a nonlinear problem. In this paper, a multi-objective function is used to define the nonlinear power flow problem. To solve the OPF problem, the Particle Swarm Optimization (PSO) and Cuckoo Search (CS) algorithms are applied. These approaches are investigated utilizing IEEE 37 nodes test case. Comparing the results of the two methods shows that the CS algorithm performs better than PSO. The advantages of the CS algorithm, including fewer initial solutions, strong optimization searching ability, and fast convergence speed, make it an effective tool for solving the nonlinear optimization problem.

Effective mentorship is vital for personal and professional growth, particularly in academic and professional settings. However, finding the right mentor from a large number of academic researchers available today can be a challenging task, particularly for newcomers to the field or for research institutions seeking to facilitate mentorship matches. Scholarly recommender systems (SRSs) have been identified as efficient tools in academic and research settings, but they also pose a significant challenge due to their high-dimensional search spaces, a challenge that metaheuristic algorithms have emerged to tackle with efficiency. This approach leverages profile and publication data from the Academic Family Tree (AFT) database and employs Particle Swarm Optimization (PSO) and Cuckoo Search (CS) algorithms to optimize mentorship matching. Data mining methodology consisting of data acquisition, pre-processing, training, and testing was used in this study. Experimental results revealed superior performance, with PSO achieving precision, recall, and accuracy of 1.00, alongside a mean reciprocal rank (MRR) of 0.80. Notably, PSO outperformed CS, which yielded a precision of 0.94, recall of 0.83, accuracy of 0.90, and an MRR of 0.80 at 10 recommendations. These findings underscore the potential of PSO in developing reliable mentorship matching systems.

Using a hybrid approach that incorporates both particle swarm optimization (PSO) and gravitational search algorithms (GSA), this project aims to find the best way for power systems to distribute their energy. A novel heuristic search optimization technique, the GSA is works on the law of gravity. While this strategy has many advantages, it suffers from sluggish search performance and memory constraints. In order to discover a solution to this problem, the PSO technique was utilized. PSO and GSA, were utilized in this investigation to discover the optimal power flow utilizing a combination of these two methodologies. The suggested optimization method merges the social thinking and local search features of particle swarm optimization with those of the GSA, therefore taking benefit of both algorithms. This study examines and evaluates an optimization technique for the optimal power flow problem, focusing on reducing fuel costs, improving the voltage profile, and minimizing real power losses. The investigation and assessment are conducted on the commonly used IEEE 30-bus test systems. The simulation findings showcase the robust and effective resolution of the optimum power transfer problem through the amalgamation of Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA).

Particle Swarm Optimization Applied to Spacecraft Reentry Trajectory

In the lightning monitoring systems, positioning calculation is directly related to the results of the detection accuracy. In this paper, the concept of the particle swarm optimization (PSO) algorithm for lightning location estimation was brought in. The PSO overcome the disadvantages of iterative method, such as the difficulty in finding initial and going to diverge. The numerical simulation results show that: the algorithm can obtained lightning point steadily and accurately, and converge quickly. Therefore, the PSO algorithm on lightning location is feasible. Introduction In the lightning monitoring systems, positioning calculation is directly related to the results of the detection accuracy [1]. The algorithms of lightning location generally use Taylor series and least squares iterative algorithm,which have the shortcomings such as difficult to determine the initial value or easy to diverge. Based on the above, this paper introduces the PSO into the lightning location, and make the numerical simulation and validation. Lightning location Based on Particle Swarm Optimization Algorithm Brief review of the PSO theory and algorithm. The PSO is an effective global optimization algorithms. The basic idea of the PSO is to achieve searching for optimal solutions in complex spatial through collaboration and information sharing among groups of individuals. The PSO adopts Speed-Shift model for action [2]. In each generation population, the particles will track the two extremes: one is the optimal solution the particle itself found so far, namely its extreme [3]; the other is the optimal solution the whole population found so far, namely the global extremum [4]. These two extremes continuously adjust the position of the particle which can be found the optimal solution within a few iterations. PSO can be described as: Let PSO search in an n-dimensional space, the population consists of N particles X = {XX1,XX2, ... ,XXNN}. Each particle location Xii = {xxii1, xxii2, ... , xxiiii} represents a solution of the problem. The particles search for the new solutions by constantly adjusting their positions. Particles by continuously adjust their position (xxiiii) to search for a new solution. Each particle can remember their optimal solutions they have searched for, and the best position (ppgg) the entire particle swarm have went by, which is also the optimal solution searched currently, denoted ppgg. In addition, each particle has a velocity, denoted by Vii = {vvii1, vvii2, ... vviiii}, while the latter two are found, each particle will update their own pace according to Eq. 1. vvii(tt + 1) = wwvi(tt) + cc1RRmm1(ppii − xxii(tt) + cc2RRmm2(ppgg − xxii(tt) (1) xxii(tt + 1) = xxii(tt) + vvii(tt + 1) (2) Where vviiii(tt + 1) represents the i-th particle velocity at t + 1 iterations. ww is the inertia weight, and it can reduce the flight speed of the particle and prevent search divergence; cc1 , cc2 is International Conference on Intelligent Systems Research and Mechatronics Engineering (ISRME 2015) © 2015. The authors Published by Atlantis Press 815 acceleration constant, generally take cc1 = cc2 = 2 ;RRmm1,RRmm2 for n × n -dimensional diagonal matrix, the diagonal elements are random number between [0,1]. In addition, the speed of the particles will not be too large, and you can set the speed limit(vvmmmmmm). That is, in Eq. 1 when vvii(tt + 1) > vvmmmmmm, vvii(tt + 1) = vvmmmmmm; when vvii(tt + 1) < vvmmmmmm,vvii(tt + 1) = −vvmmmmmm. Inertia weight ww is given by Eq. 3: w = (wstart − wend) × (MaxDT−iter) MaxDT + wweeiiii (3) Where MaxDT is the maximum number of iterations; Iter is the current iteration number; wstart,wend were initial inertia weight and termination inertia weight, wstart = 0.9,wend = 0.4. PSO implementation steps are as follows: (1) Initialized. Set various parameters PSO algorithm have been involved. (2) Calculate the fitness of each particle (fitness). Store the best place Pbest of each particle and fitness. Choose the best fitness position of the particle from the population as Gbest of populations; (3) Update state of the particles according to Eq. 1 and Eq.2; (4) If the current situation reaches the maximum number of iterations or final result is less than the convergence precision, stop the iterative and output the optimal solution. Otherwise go to step (2). Start Initialize the particle position and initial velocity randomly throughout the search space Calculate the fitness of each particle Update Pbest and Gbest of each particle Update the velocity and position of each particle, according to the Eq. 1 and Eq.2 If the termination condition is satisfied