Earticle

This study was aimed to develop a planning method of CCTV cameras surveilling juvenile victimization to school crimes. With spatial settings of school common spaces, evolutionary algorithm was applied to implement the planning method for accommodating numerous variable compositions. The required variables, their initial conditions and boundary conditions were derived from the theoretical exploration on precedent research works. The applied evolutionary algorithm used a search method with tracking fitness factor. The fitness factor of the implemented algorithm was calculated from standard deviation of distributed non-surveillance ratio and shadow area ratio. The overall algorithm utilized, as computational parameters, the camera layout information including each camera’s position, panning angle and tilting angle under the initial and boundary conditions. Finally, the developed method enabled CCTV camera layout schemes, surveillance areas and the quantitative results to be generated by the heuristic search process. This study also showed method applicability to school settings especially focusing on indoor common spaces.

According to Genetic algorithms principle, the new hybrid evolutionary algorithm (HEA) is proposed in this paper by combining the Immune algorithm, Genetic algorithm and Pareto optimal solutions. The HEA has high convergence precision and improved the diversity of population. Multiple near optimization paths can be developed by the algorithm with multi‐objective restriction, and satisfy to minimize the routing of transportation and the numbers of the vehicles. The HEA has been used to solve the vehicle routing problem, the results of simulation experiment show that the HEA can gain higher global convergence rate and higher speed.

With the fast development of data analysis and computer science technology, the design and implementation of image retrieval system has been a hot topic. The prior research focus more on image-size based approaches which are not intelligent or convenient. In this paper, we present a novel modified evolutionary algorithm based image retrieval framework theoretically with applications. To achieve more accuracy in less number of iteration, this paper, proposed a new approach to enhance the performance of content guided retrieval methodology by improving the performance of RF through Particle Swarm Optimization, Genetic Algorithm and Support Vector Machine. The objective of using Genetic Algorithm and Particle Swarm Optimization is to increase the number of images in relevant set where SVM is used to classify the relevant and irrelevant images. The experimental and numerical simulation indicate the efficiency of our method which means the presented technique is helpful in the fields where high accuracy rate of image retrieval is required. Further work of interest is also discussed in the final section.

This paper introduces a novel intelligent computation adopted from a natural phenomenon entitled Thunderstorm Algorithm (TA) which is applied to optimize an economic dispatch under various technical constraints and environmental requirements. These studies used an IEEE-62 bus system as the sample model for demonstrating ability of TA while searching the optimal solution. Obtained results show that TA gives good performances for determining the optimal solution. This demonstration also describes that the optimal solution is searched in faster convergence and shorter time. This computation also performs its characteristic in smooth and stable processes for completing all steps. In detail, the optimal solution is obatined in 22 steps for 15,586 $/h after pointing at 28,858 $/h at the first streaming. Based on executions, the computation needed 2.5 s for the streaming and it also needed 0.09 for covering the dead tracks included 0.5 s for the replacement.

In this paper, chaos theory and the traditional multi-objective optimization evolutionary algorithm is put forward, "Chaos-based multi-objective evolutionary algorithm", combines a variety of optimization strategies. The traditional multi-objective evolutionary algorithm for repeating individual causes of variation is based on chaotic analysis of multi-objective evolutionary algorithm and demonstration. According to the characteristics of chaotic map tent, NSGA-II algorithm in this paper on the basis of chaotic map was proposed based on chaotic tent initialization and chaotic mutation multi-objective evolutionary algorithm. The original NSGA-II algorithm is improved, and the introduction of adaptive mutation operator and a new crowding distance is calculated and applied to the design of the algorithm. Analysis and experimental results show that these methods can better improve the distribution of population performance.

Co-evolutionary mechanism is now used into evolutionary algorithms and provides these algorithms the power to promote the convergence. In order to promote the performance of the traditional quantum-inspired evolutionary algorithm (QEA), we proposed a novel quantum-inspired co-evolutionary algorithm (NQCEA), in this paper. The quantum state population is firstly divided into multiple sub-populations, which complete the evolution processes independently. In each evolution cycle, every sub-population will produce an elitist individual, which is then selected to construct an elite library. Subsequently, these individuals in this elite library can help the poor sub-population to find the global optimal solution or near-optimal solution. In addition, a diversity indicator is defined for every sub-population and is used to measure the diversity of the corresponding sub-population. As for the sub-population with poor diversity, the mutation strategies are implemented in order to expand its diversity and improve its global search ability. Finally, the NQCEA is compared with the traditional QEA to test their performance. Experiments are performed on the global numerical optimization functions and the simulation results indicate that this new algorithm has the characteristics of good global search capability and more stable performance than the traditional QEA.

To further enhance the distribution uniformity and extensiveness of the solution sets and to ensure effective convergence of the solution sets to the Pareto front, we proposed a MOEA approach based on a clustering mechanism. We named this approach improved multi-objective evolutionary algorithm (LMOEA). This algorithm uses a clustering technology to compute and maintain the distribution and diversity of the solution sets. A fuzzy C-means clustering algorithm is used for clustering individuals. Finally, the LMOEA is applied to solve the classical multi-objective knapsack problems. The algorithm performance was evaluated using convergence and diversity indicators. The proposed algorithm achieved significant improvements in terms of algorithm convergence and population diversity compared with the classical NSGA-II and the MOEA/D.

This paper proposes the application method of an Adaptive Quantum-Inspired Evolutionary Algorithm (AQEA) to Vehicular Ad Hoc Networks (VANETs) for enhancing clustering and routing performance. AQEA integrates quantum-inspired principles, including quantum bits, quantum superposition, and adaptive quantum rotation gates, to effectively navigate the highly dynamic and complex environments characteristic of VANETs. By dynamically balancing exploration and exploitation, AQEA encodes cluster configurations as quantum states and adjusts them using a fitness-driven rotation operator. Comparative simulations reveal that AQEA consistently produces larger, more stable clusters and reduces both reconfiguration overhead and routing costs compared to conventional algorithms such as the Grasshopper Optimization Algorithm (GOA) and Whale Optimization Algorithm (WOA). AQEA consistently achieves larger and more stable clusters, significantly reduces cluster reconfiguration overhead, and minimizes routing costs. Statistically significant improvements were observed: a 59.5% increase in cluster size and a 29.10% reduction in stability penalty relative to WOA, and a 32.99% reduction in routing cost compared to GOA. These results confirm AQEA’s superior adaptability and robustness, positioning it as an effective solution for managing clustering and routing in dynamic VANET environments. These results validate the practical relevance and algorithmic superiority of AQEA, positioning it as a robust and adaptive solution for managing clustering and routing in dynamic VANET scenarios. Also, these results highlight AQEA’s robustness and adaptability, positioning it as an effective solution for managing clustering and routing in dynamic VANET scenarios. Future research directions include real-world validations, expanded performance evaluations, and further refinement of the algorithm's adaptive mechanisms.

The paper represents an evolutionary algorithm (EA) solution to the unit commitment problem for Virtual Power Plants. EAs are general optimization techniques based on principles inspired from the biological evolution, using metaphors of mechanism such as natural selection, genetic recombination and survival of the fittest. One of EA implementation using the standard crossover and mutation operators could locate near optimal solution. Theoretical results and expectations are proved through simulations of a realistic scenario.

An optimal Fractional Order PIλDμ (FOPID) controller is designed for a full vehicle nonlinear active suspension system. The optimal values of FOPID controller parameters for minimizing the cost function are tuned using an Evolutionary Algorithm (EA), which offers an optimal solution to a multidimensional rough objective function. The fitness parameters of FOPID controller (proportional constant P, integral constant I, derivative constant D, integral order λ and derivative order μ) are selected from ranges of reliable values, depending on survival-to-the-fitness principle used in the biology science. A full vehicle nonlinear active suspension model including hydraulic actuators, nonlinear dampers and nonlinear springs has been proposed with structural and analytical details. The nonlinear frictional forces due to rubbing of piston seals with the cylinders wall inside the actuators are taken into account to find the real supply forces generated by the hydraulic actuator. The results of the full vehicle nonlinear suspension system using the FOPID controller are compared with the corresponding passive suspension system (system without controller). The controlled suspension system has been investigated under typical vehicle maneuvers: cruising on rough road surface, sharp braking and cornering. The results have clearly shown the effectiveness and robustness of the proposed controller.

Under mild conditions, it can be induced from the Karush–Kuhn–Tucker condition that the Pareto set, in the decision space, of a continuous Multiobjective Optimization Problems(MOPs) is a piecewise continuous (m 1)  D manifold(where m is the number of objectives). One hand, the traditional Multiobjective Optimization Algorithms(EMOAs) cannot utilize this regularity property; on the other hand, the Regular Model-Based Multiobjective Estimation of Distribution Algorithm(RM-MEDA) only able to build the linear model of decision space using linear modelling algorithm, such as: the local principal component analysis algorithm(Local PCA).Aim at the shortcomings of EMOAs and RM-MEDA, the Manifold-Learning-Based Multiobjective Evolutionary Algorithm Via Self-Organizing Maps(ML-MOEA/SOM) is proposed for continuous multiobjective optimization problems. At each generation, first, via Self-Organizing Maps, the proposed algorithm learns such a nonlinear manifold in the decision space; then, new trial solutions is built through expanding the neurons of SOM with random noise; at the end, a nondominated sorting-based selection is used for choosing solutions for the next generation. Systematic experiments have shown that, overall, ML-MOEA/SOM outperforms NSGA-II, and is competitive with RM-MEDA in terms of convergence and diversity, on a set of test instances with variable linkages. We have demonstrated that, compared with NSGA-II and RM-MEDA, via self-Organizing maps, ML-MOEA/SOM can dig nonlinear manifold hidden in the decision space of multiobjective optimization problems.

Active disturbance rejection control (ADRC) is a unique control strategy that combines the effectiveness of error driven PID controller, usefulness of state observer and strength of nonlinear feedback. This control algorithm, not only actively (online) estimates but also compensates the effects of unknown internal and external disturbances, present inherently in the plant with the help of a well-tuned extended state observer (ESO). Although, the classical solution to the parameter tuning performed by using parameterization technique provides good solution, it is not optimal for having desired performance specifications. Consequently, it became imperative to have intelligent tuning technique to achieve optimized solution to parameter tuning problem. In this regards, the Evolutionary Algorithms (EA), inspired by natural system and based on swarm intelligence, are proven to be the best tool to find the optimized solution of multi-dimensional problems. This paper presents an application of an EA optimized ADRC controller on an uncertain 2-DoF revolute-prismatic (RP) robotic manipulator for efficient trajectory tracking and parametric robustness. Eventually, the conventional ADRC design problem is converted into a special optimization problem for finding the optimal controller tuning parameters. To accomplish this task, two well-known EA’s viz. Particle Swarm Optimization (PSO) and Bacteria Foraging Optimization (BFO) are implemented and performance of EA based controller-plant configuration is individually analyzed for each algorithm. The results of this note illustrate the benefits and weakness of the EA for implementing ADRC on MIMO systems. The performance of both the optimization techniques is compared in terms of computational time and convergence efficiency. Further, the optimized controllers are tested for the robustness in presence of disturbance and sensor noise to imitate real engineering. MATLAB based simulation results are presented and compared to demonstrate the effectiveness of both the EA's in designing an ADRC controller for improving manipulator tracking ability.

Neural networks are known as kinds of intelligent strategies since they have learning capability. There are various their applications from intelligent control fields, however, their applications have limits from the point that the stability of the intelligent control systems is not usually guaranteed. In this paper we propose an Adaptive Tracking Control of Nonlinear System the radial basis function network that is a kind of neural networks. The learning method involves structural adaptation and parameter adaptation. No prior knowledge of the plant is assumed, and the controller has to begin with exploration of the state space. The exploration versus exploitation dilemma of reinforcement learning is solved through smooth transitions between the two modes. The controller is capable of asymptotically approaching the desired reference trajectory, which is showed in simulation result.

Due to the normal forecasting methods for subgrade settlement using observation data have different applicabilities, and the predicting results has bigger volatility and lower accuracy. In view of the above problems, a method based on least square support vector regression (LSTSVR) and real-coded quantum evolutionary algorithm (RQEA) is proposed. Firstly, the LSTSVR parameter is chosen as a combinatorial optimization problem, and determining the objective function of the combinatorial optimization problem, then, using RQEA to solve the combinatorial optimization problem and optimize the LSTSVR parameters, Finaly, LSTSVR-RQEA is used to sovle the prediction of subgrade settlement. The simulation results show that RQEA is an effective method to select LSTSVR parameters, and has excellent performance when applied to the prediction of subgrade settlement.

Due to the normal forecasting methods for subgrade settlement using observation data have different explicabilities, and the predicting results has bigger volatility and lower accuracy. The Combined forecasting model of subgrade settlement based on forecasting availability and real-coded quantum evolutionary algorithm (RQEA) is put forward in this paper. At the first, according to the basic settlement law of subgrade and characteristics of settlement curve, the growth curve with the S-type characteristics are chosen as single forecasting model; Then, to get the weights of each single forecasting model, objective function is build on the basis of standard of forecasting availability maximization, and RQEA is employed to solve the objective function, and to construct the combined forecasting model of subgrade settlement. The result of engineering practice shows that the proposed method has better prediction accuracy and stability, and can meet engineering demand.

Due to the normal forecasting methods for subgrade settlement using observation data have different applicability and disadvantages, The Combined forecasting model is put forward based on support vector machine (SVM) and real-coded quantum evolutionary algorithm (RQEA) in this paper. Its core is that, according to the basic settlement law of subgrade and characteristics of settlement curve, the growth curve which has S-type characteristic are chosen as single forecasting model, then support vector machine is used to combine the predicting results of each single forecasting model, at the same time, RQEA is adopted to optimize support vector machine parameter to improve the SVM’s performance. The analytical result of engineering practice indicates that the proposed combined forecasting model of subgrade settlement base on SVM and RQEA can not only improve the predicting accuracy, but also reduce the predicting risk, and can meet engineering demand.

The paper presents an evolution of personalized courses based on genetic algorithms (PCEGA). The genetic algorithm are successfully applied in the dynamic update process of the course during the whole learning process. Under this framework of this algorithm, the target user model updates dynamically, and the courses evolve during the process. It provides a good general purpose and scalable framework that addresses the personalized course generation in an online learning environment.

The paper provides an improved evolutionary strategy (ES) of genetic algorithm (GA) on the basis of the existing literature. The ES overcomes the shortage of traditional GA whose excellent child individuals obtained in the crossover process may not survive in the process of mutation. In addition, the crossover probability and mutation probability which is hard to determine in traditional GA is removed for this proposed strategy. At the same time, it increases the number of individuals produced in process of crossover. This may increase the possibility of producing excellent individuals, thus lead to better improvement of the traditional GA. The test result of finding the optimal values of four functions using transitional GA and the proposed GA is presented in this paper. The result shows that the improved ES presented in this paper has faster calculation speed and significantly smaller number of iterations than the traditional GA. Thus, the improvement of improved ES is powerfully illustrated. Based on articles in the existing research literature, the initial population generation methods were further explored when using the genetic algorithm(GA) for solving constrained optimization problem. Through the research we present a new method about initial interior point’s generation. Firstly, construct a constraint posed by the objective function, which is based on the characteristics of constrained optimization problems. Then translate the problem of evaluating the initial interior point into a problem of solving a series of unconstrained optimization. By solving the unconstrained optimization problem, we achieve the solution of the initial interior point. Based on this idea, the research has given a method on the generation of the rest initial population individuals. In addition, through the research we concluded that the key to generate the initial population is to obtain an initial point. The production of other individuals will take less time after the initial internal point is obtained. Finally, we verified by examples that the initial population generation method given by this paper is a fast and reliable method. Thus the shortage of the GA of which the initial population is difficult to be produced in some constrained optimization problem is overcome

At the present time, computerized tests are one of the most critical means to evaluate learning. Choosing tailored questions for each learner is a important part of such tests. Since, wide and varied learners with different abilities are involved, even randomized test cannot serve the purpose of assessment. Some form of personalized and intelligent testing is needed in E-Learning. One of the main components in composing intelligent testing is selecting the items from a huge Item Bank as the accuracy of the test depends on the quality of the assessment which in turn depends on the items selected for assessment. Furthermore, pickingappropriate items is critical in developing as assessment sheet that satisfies multiple criteria. It includes the number of test items, the definitedissemination of course concepts to be assessed, and the expected degree of difficultness and discrimination and exposure frequency. These tests, must effectively select questions from a large item bank, and to manage this problem an optimized assessment sheet composition system using the modified form of nature inspired Intelligent Water Drops optimization algorithm is proposed by embedding a local heuristic as evolutionary operator. This system is designed to choosepersonalizedtest items for each and every learner. Furthermore, the proposed approach is able to effectively generate near optimal items from large item bank that satisfy multiple constraints. The results show that the Evolutionary Intelligent Water Drops approach is suitable for the selection of nearoptimal items from large-scale item bank.