Jianshe Wu

Moea/d with adaptive weight adjustment

Recently, MOEA/D (multi-objective evolutionary algorithm based on decomposition) has achieved great success in the field of evolutionary multi-objective optimization and has attracted a lot of attention. It decomposes a multi-objective optimization problem (MOP) into a set of scalar subproblems using uniformly distributed aggregation weight vectors and provides an excellent general algorithmic framework of evolutionary multi-objective optimization. Generally, the uniformity of weight vectors in MOEA/D can ensure the diversity of the Pareto optimal solutions, however, it cannot work as well when the target MOP has a complex Pareto front (PF; i.e., discontinuous PF or PF with sharp peak or low tail). To remedy this, we propose an improved MOEA/D with adaptive weight vector adjustment (MOEA/D-AWA). According to the analysis of the geometric relationship between the weight vectors and the optimal solutions under the Chebyshev decomposition scheme, a new weight vector initialization method and an adaptive weight vector adjustment strategy are introduced in MOEA/D-AWA. The weights are adjusted periodically so that the weights of subproblems can be redistributed adaptively to obtain better uniformity of solutions. Meanwhile, computing efforts devoted to subproblems with duplicate optimal solution can be saved. Moreover, an external elite population is introduced to help adding new subproblems into real sparse regions rather than pseudo sparse regions of the complex PF, that is, discontinuous regions of the PF. MOEA/D-AWA has been compared with four state of the art MOEAs, namely the original MOEA/D, Adaptive-MOEA/D, -MOEA/D, and NSGA-II on 10 widely used test problems, two newly constructed complex problems, and two many-objective problems. Experimental results indicate that MOEA/D-AWA outperforms the benchmark algorithms in terms of the IGD metric, particularly when the PF of the MOP is complex.

Globally stable adaptive robust tracking control using RBF neural networks as feedforward compensators

In previous adaptive neural network control schemes, neural networks are usually used as feedback compensators. So, only semi-globally uniformly ultimate boundedness of closed-loop systems can be guaranteed, and no methods are given to determine the neural network approximation domain. However, in this paper, it is showed that if neural networks are used as feedforward compensators instead of feedback ones, then we can ensure the globally uniformly ultimate boundedness of closed-loop systems and determine the neural network approximation domain via the bound of known reference signals. It should be pointed out that this domain is very important for designing the neural network structure, for example, it directly determines the choice of the centers of radial basis function neural networks. Simulation examples are given to illustrate the effectiveness of the proposed control approaches.

MOEA/D with opposition-based learning for multiobjective optimization problem

Multiobjective evolutionary algorithm based on decomposition (MOEA/D) has attracted a great deal of attention and has obtained enormous success in the field of evolutionary multiobjective optimization. It converts a multiobjective optimization problem (MOP) into a set of scalar optimization subproblems and then uses the evolutionary algorithm (EA) to optimize these subproblems simultaneously. However, there is a great deal of randomness in MOEA/D. Researchers in the field of evolutionary algorithm, reinforcement learning and neural network have reported that the simultaneous consideration of randomness and opposition has an advantage over pure randomness. A new scheme, called opposition-based learning (OBL), has been proposed in the machine learning field. In this paper, OBL has been integrated into the framework of MOEA/D to accelerate its convergence speed. Hence, our proposed approach is called opposition-based learning MOEA/D (MOEA/D-OBL). Compared with MOEA/D, MOEA/D-OBL uses an opposition-based initial population and opposition-based learning strategy to generate offspring during the evolutionary process. It is compared with its parent algorithm MOEA/D on four representative kinds of MOPs and many-objective optimization problems. Experimental results indicate that MOEA/D-OBL outperforms or performs similar to MOEA/D. Moreover, the parameter sensitivity of generalization opposite point and the probable to use OBL is experimentally investigated.

Decentralized backstepping output-feedback control for stochastic interconnected systems with time-varying delays using neural networks

This paper addresses the decentralized adaptive output-feedback control problem for a class of interconnected stochastic strict-feedback uncertain systems described by It

MOEA/D with uniform decomposition measurement for many-objective problems

\hat{\hbox{o}}

Global Synchronization and State Tuning in Asymmetric Complex Dynamical Networks

differential equation using neural networks. Compared with the existing literature, this paper removes the commonly used assumption that the interconnections are bounded by known functions multiplying unknown parameters, and all unknown interconnections are lumped in a suitable function which is compensated by only a neural network in each subsystem. So, the controller is simpler even than that for the strict-feedback systems described by the ordinary differential equation. Moreover, the circle criterion is applied to designing nonlinear observers for the estimates of system states. A simulation example is used to illustrate the effectiveness of control scheme proposed in this paper.

MOEA/D with Baldwinian learning inspired by the regularity property of continuous multiobjective problem

The link prediction algorithm which based on node similarity is the research hotspot in recent years. In addition, there are some methods which based on the network community structure information to predict the missing links, however, these studies only concerned about the obvious information between different communities such as direct links. We found that it is hard to predict the missing links if the two communities have little direct connections. In fact, there is similarity between communities such as the similarity between nodes and this similarity is significant for prediction. So, we define a community similarity feature which named community relevance by using not only the obvious information but also the latent information between different communities in this paper. Then a novel algorithm which based on the community relevance and ruler inference is proposed to predict missing links. In this method, we extract the community structure by using the local information of the network first. Next, calculate the relevance of each pair of communities by using the new community relevance indices. Finally, a simple prediction model which based on ruler inference is applied to estimate the probability of the missing links. It is shown that the proposed method has more effective prediction accuracy and the community relevance features improve the predictor with low time complexity, with experiments on benchmark networks and real-world networks in different scales, and compared with other ten sate of the art approaches.

A spectral clustering-based adaptive hybrid multi-objective harmony search algorithm for community detection

Many-objective problems (MAPs) have put forward a number of challenges to classical Pareto-dominance based multi-objective evolutionary algorithms (MOEAs) for the past few years. Recently, researchers have suggested that MOEA/D (multi-objective evolutionary algorithm based on decomposition) can work for MAPs. However, there exist two difficulties in applying MOEA/D to solve MAPs directly. One is that the number of constructed weight vectors is not arbitrary and the weight vectors are mainly distributed on the boundary of weight space for MAPs. The other is that the relationship between the optimal solution of subproblem and its weight vector is nonlinear for the Tchebycheff decomposition approach used by MOEA/D. To deal with these two difficulties, we propose an improved MOEA/D with uniform decomposition measurement and the modified Tchebycheff decomposition approach (MOEA/D-UDM) in this paper. Firstly, a novel weight vectors initialization method based on the uniform decomposition measurement is introduced to obtain uniform weight vectors in any amount, which is one of great merits to use our proposed algorithm. The modified Tchebycheff decomposition approach, instead of the Tchebycheff decomposition approach, is used in MOEA/D-UDM to alleviate the inconsistency between the weight vector of subproblem and the direction of its optimal solution in the Tchebycheff decomposition approach. The proposed MOEA/D-UDM is compared with two state-of-the-art MOEAs, namely MOEA/D and UMOEA/D on a number of MAPs. Experimental results suggest that the proposed MOEA/D-UDM outperforms or performs similarly to the other compared algorithms in terms of hypervolume and inverted generational distance metrics on different types of problems. The effects of uniform weight vector initializing method and the modified Tchebycheff decomposition are also studied separately.