In general, the existing evolutionary algorithms are prone to premature convergence and slow convergence in coping with combinatorial optimization problems. So an intelligent optimization algorithm called physarum-energy optimization algorithm (PEO) is proposed and put TSP as the carrier in this paper. This algorithm consists of four parts: the physarum biological model, the energy model, the age factor model and the stochastic disturbance model. First, the high parallelism of PEO is enlightened from the physarum’s low complexity and high parallelism. Second, we present an energy mechanism model in PEO, which is mainly to develop the shortcomings of existing algorithm, such as slow convergence and lack of interaction capability. Third, inspired by the characteristic of ants’ spatiotemporal variations, the age factor mechanism is introduced to raise search capacity, which can control the convergence speed and precision ability of PEO. In addition, in order to avoid premature convergence, the stochastic disturbance mechanism is adopted into PEO. And also the feasibility and convergence of PEO has been analyzed and verified theoretically. Moreover, we compare the algorithm and other algorithms to TSPs of diverse scope. The experiment results show that PEO has the advantages of excellent global optimization, high optimization accuracy and high parallelism and is significantly better than other algorithms.

A wolf pack can hunt prey efficiently due to reasonable social team hierarchy and effective team cooperation. Inspired by the collective intelligence of wolf pack, in this paper, a novel swarm algorithm named the social team building optimization (STBO) algorithm is proposed for solving optimization problems. In order to mimic the method of social team building, which is an optimization process in reality, STBO algorithm is in terms of social team hierarchy, team building state and process control. Firstly, the social team model separates individuals of population into different swarms according to the appropriate team hierarchy. In this way, the proposed algorithm not only has fast search speed but also avoids to fall into the local optimum prematurely. Secondly, the team building state model divides the optimization process into three states. In different states, individuals at different levels act diverse social behaviors to make the algorithm maintain population diversity and possess better search capability. Thirdly, the team power model is designed to determine the states of optimization process by means of the team power and the team cohesion. The main aim of this model is to make the algorithm have a good balance between exploration and exploitation, namely to find the optimal solutions as possible as it can. Moreover, the mathematical models of STBO are educed by the swarm theory, the state evolution theory and the energy–entropy theory. Meanwhile, the convergence property of the presented algorithm has been analyzed theoretically in this paper. And STBO was compared to three classical nature-inspired algorithms on 11 basic standard benchmark functions and also three state-of-the-art evolutionary methods on CEC2016 competition on learning-based single-objective optimization. Some simulation results have shown the effectiveness and high performance of the proposed approach.

The matter state change, which is a common phenomenon in nature, shows the process that the matter how to reach the optimal state in the environment. This paper presents a novel particle state change model (PSCM) inspired by mimicking the process of the matter state change. Based on PSCM, a novel particle state change (PSC) algorithm is proposed for solving continuous optimization problems. As a new algorithm, PSC has many differences from other similar nature-inspired algorithms in terms of the basic principle models, mathematical formalization and properties. This paper considers three states of the matter, namely gas state, liquid state and solid state. In a certain circumstance, the matter always converts from an unstable state into a stable state. It is similar to find the optimal solution of an optimization problem. The proposed algorithm also has the advantages in the respects of higher intelligence, effectiveness and lower computation complexity. And the convergence property of PSC is discussed in detail. In order to illustrate the ability of solving optimization problems in continuous domain, the new proposed algorithm is tested on basic function optimization, CEC2016 single-objective real-parameter numerical optimization and CEC2016 learning-base real-parameter single-objective optimization, and compared with eleven existing algorithms. The numerous simulations have shown the effectiveness and suitability of the proposed approach.

As the world gradually transforms from an information world to a data-driven world, areas of pattern recognition and data mining are facing more and more challenges. The process of feature subset selection becomes a necessary part of big data pattern recognition due to the data with explosive growth. Inspired by the behavior of grabbing resources in animals, this paper adds personal grabbing-resource behavior into the model of resource allocation transformed from the model of feature selection. Multi-colony fairness algorithm (MCFA) is proposed to deal with grabbing-resource behaviors in order to obtain a better distribution scheme (i.e., to obtain a better feature subset). The algorithm effectively fuses strategies of the random search and the heuristic search. In addition, it combines methods of filter and wrapper so as to reduce the amount of calculation while improving classification accuracies. The convergence and the effectiveness of the proposed algorithm are verified both from mathematical and experimental aspects. MCFA is compared with other four classic feature selection algorithms such as sequential forward selection, sequential backward selection, sequential floating forward selection, and sequential floating backward selection and three mainstream feature selection algorithms such as relevance–redundancy feature selection, minimal redundancy–maximal relevance, and ReliefF. The comparison results show that the proposed algorithm can obtain better feature subsets both in the aspects of feature subset length which is defined as the number of features in a feature subset and the classification accuracy. The two aspects indicate the efficiency and the effectiveness of the proposed algorithm.

In this paper, a clustering algorithm based on emotional preference and migratory behavior (EPMC) is proposed for data clustering. The algorithm consists of four models: the migration model, the emotional preference model, the social group model and the inertial learning model. First, the migration model calculates the probability of individuals being learned, so that individuals can learn from the superior. Second, the emotional preference model is introduced to help individuals find the most suitable neighbor for learning. Third, the social group model divides the whole population into different groups and enhances the mutual cooperation between individuals under different conditions. Finally, the inertial learning model balances the exploration and exploitation during the optimization, so that the algorithm can avoid falling into the local optimal solution. In addition, the convergence of EPMC algorithm is verified by theoretical analysis, and the algorithm is compared with four clustering algorithms. Experimental results validate the effectiveness of EPMC algorithm.