Yi-nan Guo

A novel multi-population cultural algorithm adopting knowledge migration

In existing multi-population cultural algorithms, information is exchanged among sub-populations by individuals. However, migrated individuals cannot reflect enough evolutionary information, which limits the evolution performance. In order to enhance the migration efficiency, a novel multi-population cultural algorithm adopting knowledge migration is proposed. Implicit knowledge extracted from the evolution process of each sub-population directly reflects the information about dominant search space. By migrating knowledge among sub-populations at the constant intervals, the algorithm realizes more effective interaction with less communication cost. Taken benchmark functions with high-dimension as the examples, simulation results indicate that the algorithm can effectively improve the speed of convergence and overcome premature convergence.

A PSO-based multi-objective multi-label feature selection method in classification

Feature selection is an important data preprocessing technique in multi-label classification. Although a large number of studies have been proposed to tackle feature selection problem, there are a few cases for multi-label data. This paper studies a multi-label feature selection algorithm using an improved multi-objective particle swarm optimization (PSO), with the purpose of searching for a Pareto set of non-dominated solutions (feature subsets). Two new operators are employed to improve the performance of the proposed PSO-based algorithm. One operator is adaptive uniform mutation with action range varying over time, which is used to extend the exploration capability of the swarm; another is a local learning strategy, which is designed to exploit the areas with sparse solutions in the search space. Moreover, the idea of the archive, and the crowding distance are applied to PSO for finding the Pareto set. Finally, experiments verify that the proposed algorithm is a useful approach of feature selection for multi-label classification problem.

Multi-population cooperative cultural algorithms

Based on the dual structure of culture algorithm, a multi-population cooperative cultural algorithm is proposed by embedding the competition cooperative genetic algorithm into the population space of culture algorithm. In each sub-population, genetic algorithm is adopted. And its population size is adjusted in terms of population density so as to enhance the diversity. In belief space, each kind of the knowledge extracted from best individual of all sub-population is utilized to induce each sub-populations mutation operator. Simulation results indicate that this algorithm can effectively speed up the convergence and improve the accuracy and stability of the solutions.

Knowledge Migration Based Multi-population Cultural Algorithm

In existing multi-population cultural algorithms, information are exchanged among sub-populations by individuals, which limits the evolution performance. So a novel multi-population cultural algorithm adopting knowledge migration is proposed. Implicit knowledge extracted from each sub-population reflects the information about dominant search space. By migrating the knowledge among sub-populations at the constant interval, the algorithm realizes more effective interaction with less communication cost. Taken benchmark functions as the examples, simulation results indicate that the algorithm can effectively improve the speed of convergence and overcome premature convergence.

Optimal Design of Passive Power Filters Based on Knowledge-Based Chaotic Evolutionary Algorithm

Design of passive power filters shall meet the demand of harmonics suppression effect and economic target. However, traditional experience-based method has difficulty achieving the optimal solution because it only takes technology target into account. To solve the problem, two objectives including minimum total harmonics distortion of current and minimum cost for equipments are constructed. Taken capacitors in passive power filter as variables, such non-dominant objectives are transformed into single weighted objective. In order to achieve the optimal solution effectively, a novel evolutionary algorithm with knowledge-based chaotic mutation is proposed. The scale of mutation is adaptively adjusted based on logistic chaotic sequence according to current implicit knowledge describing the dominant space. Taken three-phase full wave controlled rectifier as harmonic source, simulation results show that filter designed by the proposed algorithm have better harmonics suppression effect and lower investment for equipments than filter designed by experience-based method.

The Evolutionary Algorithm to Find Robust Pareto-Optimal Solutions over Time

In dynamic multiobjective optimization problems, the environmental parameters change over time, which makes the true pareto fronts shifted. So far, most works of research on dynamic multiobjective optimization methods have concentrated on detecting the changed environment and triggering the population based optimization methods so as to track the moving pareto fronts over time. Yet, in many real-world applications, it is not necessary to find the optimal nondominant solutions in each dynamic environment. To solve this weakness, a novel method called robust pareto-optimal solution over time is proposed. It is in fact to replace the optimal pareto front at each time-varying moment with the series of robust pareto-optimal solutions. This means that each robust solution can fit for more than one time-varying moment. Two metrics, including the average survival time and average robust generational distance, are present to measure the robustness of the robust pareto solution set. Another contribution is to construct the algorithm framework searching for robust pareto-optimal solutions over time based on the survival time. Experimental results indicate that this definition is a more practical and time-saving method of addressing dynamic multiobjective optimization problems changing over time.

Find robust solutions over time by two-layer multi-objective optimization method

Robust optimization over time is a practical dynamic optimization method, which provides two detailed computable metrics to get the possible robust solutions for dynamic scalar optimization problems. However, the robust solutions fit for more time-varying moments or approximate the optimum more because only one metric is considered as the optimization objective. To find the true robust solution set satisfying maximum both survival time and average fitness simultaneously during all dynamic environments, a novel two-layer multi-objective optimization method is proposed. In the first layer, considering both metrics, the acceptable optimal solutions for each changing environment is found. Subsequently, they are composed of the practical robust solution set in the second layer. Taking the average fitness and the length of the robust solution set as two objectives, the optimal combinations for the whole time-varying environments are explored. The experimental results for the modified moving peaks benchmark shows that the robust solution sets considering both metrics are superior to the robust solutions gotten by ROOT. As the key parameters, the fitness threshold has the more obvious impact on the performances of MROOT than the time window, whereas ROOT is more sensitive to both of them.

Hybrid Optimization Method Based on Genetic Algorithm and Cultural Algorithm

Knowledge about evolutionary information is not used in genetic algorithms effectively. Cultural algorithms with dual inheritance structure converge slowly because only mutation operator is adopted in the population space. A novel hybrid optimization method is proposed using genetic algorithm in population space. Four kinds of knowledge and two phases are abstracted. Steps of the algorithm are described in detail. Simulation results on the benchmark optimization functions indicate that the method converges faster than traditional cultural algorithms. In iteratively dynamic situation, results show that experience knowledge in the knowledge space is benefit to apperceive the change of situation and has the ability in memory, which increases the speed of convergence in a certain situation

The Coverage Optimization for Wireless Sensor Networks Based on Quantum- Inspired Cultural Algorithm

In order to properly distribute sensor nodes in wireless sensor networks, a coverage model considering maximum coverage ratio and minimum redundancy is given and the optimization strategy based on quantum-inspired cultural algorithm is proposed. In population space, quantum-inspired evolutionary algorithm is used to increase the observed probability. In belief space, the implicit knowledge embodied in the evolution is extracted from the better individuals chosen from the population. It is used to guide the search direction of evolutionary population and influence the update of quantum individuals. Simulation results indicate that the algorithm is superior to other algorithms in coverage optimization and effectively improve the coverage performance of wireless sensor networks.

Path planning method for robots in complex ground environment based on cultural algorithm

In complex ground environment, different regions have different road conditions. Path planning for robots in such environment is an open problem, which lacks effective methods. A novel global path planning method based on common sense and evolution knowledge is proposed by adopting dual evolution structure in culture algorithms. Common sense describes ground information and feasibility of environment, which is used to evaluate and select the paths. Evolution knowledge describes the angle relationship between the path and the obstacles, or the common segments of paths, which is used to judge and repair infeasible individuals. Taken two types of environments with different obstacles and road conditions as examples, simulation results indicate that the algorithm can effectively solve path planning problem in complex ground environment and decrease the computation complexity for judgment and repair of infeasible individuals. It also can improve the convergence speed and have better computation stability.