Hongbin Dong

Evolutionary programming using a mixed mutation strategy

Abstract Different mutation operators have been proposed in evolutionary programming, but for each operator there are some types of optimization problems that cannot be solved efficiently. A mixed strategy, integrating several mutation operators into a single algorithm, can overcome this problem. Inspired by evolutionary game theory, this paper presents a mixed strategy evolutionary programming algorithm that employs the Gaussian, Cauchy, Levy, and single-point mutation operators. The novel algorithm is tested on a set of 22 benchmark problems. The results show that the mixed strategy performs equally well or better than the best of the four pure strategies does, for all of the benchmark problems.

A trust-based probabilistic recommendation model for social networks

Abstract In social networks, how to establish an effective recommendation model is an important research topic. This paper proposes a trust-based probabilistic recommendation model for social networks. We consider the recommendation attributes of products to determine similarity among users. Then inherent similarity among products is taken into account to derive the transition probability of a target node. In addition, trust of products is obtained based on their reputations and purchase frequencies. In order to solve the problem of users׳ cold start, we consider users׳ latent factor to find their latent similar users. Finally, we adopt the Amazon product co-purchasing network metadata to verify the effectiveness of the proposed recommendation model through comprehensive experiments. Furthermore, we analyze the impact of the transition probability influence factor through experiments. The experimental results show that the proposed recommendation model is effective and has a higher accuracy.

Pure strategy or mixed strategy

Mixed strategy evolutionary algorithms (EAs) aim at integrating several mutation operators into a single algorithm. However no analysis has been made to answer the theoretical question: whether and when is the performance of mixed strategy EAs better than that of pure strategy EAs? In this paper, asymptotic convergence rate and asymptotic hitting time are proposed to measure the performance of EAs. It is proven that the asymptotic convergence rate and asymptotic hitting time of any mixed strategy (1+1) EA consisting of several mutation operators is not worse than that of the worst pure strategy (1+1) EA using only one mutation operator. Furthermore it is proven that if these mutation operators are mutually complementary, then it is possible to design a mixed strategy (1+1) EA whose performance is better than that of any pure strategy (1+1) EA using only one mutation operator.

An adaptive fuzzy kNN text classifier

In recent years, kNN algorithm is paid attention by many researchers and is proved one of the best text categorization algorithms. Text categorization is according to training set which is assigned class label to decide a new document which is not assigned class label belongs to some kind of document. Until now, kNN algorithm has still some issues to need to study further. Such as: improvement of decision rule; selection of k value; selection of dimensions (i.e. feature set selection); problems of multiclass text categorization; the algorithm’s executive efficiency (time and space) etc. In this paper, we mainly focus on improvement of decision rule and dimension selection. We design an adaptive fuzzy kNN text classifier. Here the adaptive indicate the adaptive of dimension selection. The experiment results show that our algorithm is effective and feasible.

Mixed strategy may outperform pure strategy: An initial study

A pure strategy metaheuristic is one that applies the same search method at each generation of the algorithm. A mixed strategy metaheuristic is one that selects a search method probabilistically from a set of strategies at each generation. For example, a classical genetic algorithm, that applies mutation with probability 0.9 and crossover with probability 0.1, belong to mixed strategy heuristics. A (1+1) evolutionary algorithm using mutation but no crossover is a pure strategy metaheuristic. The purpose of this paper is to compare the performance between mixed strategy and pure strategy metaheuristics. The main results of the current paper are summarised as follows. (1) We construct two novel mixed strategy evolutionary algorithms for solving the 0-1 knapsack problem. Experimental results show that the mixed strategy algorithms may find better solutions than pure strategy algorithms in up to 77.8% instances through experiments. (2) We establish a sufficient and necessary condition when the expected runtime time of mixed strategy metaheuristics is smaller that that of pure strategy mixed strategy metaheuristics.

Wright–Fisher multi-strategy trust evolution model with white noise for Internetware

Abstract A trust evolution model plays an important role in ensuring and predicting the behaviors of entities in Internetware system. Most of the current trust evolution models almost adopt expertise or average weight method to calculate entities’ trust incomes, and focus on two strategies (‘full trust’, ‘full distrust’) to analyze trust behaviors. In addition, the researches on dynamics evolution models fail to consider the factor of noise, and cannot effectively prevent free-riding phenomenon. In this paper, a trust measurement based on Quality of Service (QoS) and fuzzy theory by considering timeliness of history data is proposed to improve the accuracy of trust measurement results. Furthermore, a trust evolution model based on Wright–Fisher and the evolutionary game theory is proposed. This model considers multi-strategy and noise problems to improve the accuracy of prediction and adaptability of model in complex networks. Meanwhile, in order to solve the free-riding problem, and improve the trust degree of a system, an incentive mechanism is established based on evolutionary game theory to inspire entities to select trust strategies. The simulation results show that this model has good adaptability and accuracy. In addition, this model can effectively improve network efficiency, and make trust income reach an optimal value, so as to improve trust degree of a system.

A fuzzy clustering algorithm based on evolutionary programming

In this paper, a fuzzy clustering method based on evolutionary programming (EPFCM) is proposed. The algorithm benefits from the global search strategy of evolutionary programming, to improve fuzzy c-means algorithm (FCM). The cluster validity can be measured by some cluster validity indices. To increase the convergence speed of the algorithm, we exploit the modified algorithm to change the number of cluster centers dynamically. Experiments demonstrate EPFCM can find the proper number of clusters, and the result of clustering does not depend critically on the choice of the initial cluster centers. The probability of trapping into the local optima will be very lower than FCM.

An Adaptive Fuzzy kNN Text Classifier Based on Gini Index Weight

In recent years, kNN algorithm is paid attention by many researchers and is proved one of the best text categorization algorithms. Text categorization is according to training set, which is assigned class label to decide a new document, which is not assigned class label belongs to some kind of document. But for a classifier, text preprocessing is the bottleneck of categorization. In the original feature space, there are always thousands upon thousands words. The dimension of feature space is very high. So in this paper, we adopt a new feature weight method---- improved Gini index to reduce the dimension of feature space and improve the categorization precision. In addition, we discuss the improvement of decision rule and dimension selection. We design an adaptive fuzzy kNN text classifier. Here the adaptive indicate the adaptive of dimension selection. The experiment results show that our algorithm is effective and feasible.

Collaborative Filtering Recommendation on Users’ Interest Sequences

As an important factor for improving recommendations, time information has been introduced to model users’ dynamic preferences in many papers. However, the sequence of users’ behaviour is rarely studied in recommender systems. Due to the users’ unique behavior evolution patterns and personalized interest transitions among items, users’ similarity in sequential dimension should be introduced to further distinguish users’ preferences and interests. In this paper, we propose a new collaborative filtering recommendation method based on users’ interest sequences (IS) that rank users’ ratings or other online behaviors according to the timestamps when they occurred. This method extracts the semantics hidden in the interest sequences by the length of users’ longest common sub-IS (LCSIS) and the count of users’ total common sub-IS (ACSIS). Then, these semantics are utilized to obtain users’ IS-based similarities and, further, to refine the similarities acquired from traditional collaborative filtering approaches. With these updated similarities, transition characteristics and dynamic evolution patterns of users’ preferences are considered. Our new proposed method was compared with state-of-the-art time-aware collaborative filtering algorithms on datasets MovieLens, Flixster and Ciao. The experimental results validate that the proposed recommendation method is effective and outperforms several existing algorithms in the accuracy of rating prediction.

Adaptive feature selection using v-shaped binary particle swarm optimization

Feature selection is an important preprocessing method in machine learning and data mining. This process can be used not only to reduce the amount of data to be analyzed but also to build models with stronger interpretability based on fewer features. Traditional feature selection methods evaluate the dependency and redundancy of features separately, which leads to a lack of measurement of their combined effect. Moreover, a greedy search considers only the optimization of the current round and thus cannot be a global search. To evaluate the combined effect of different subsets in the entire feature space, an adaptive feature selection method based on V-shaped binary particle swarm optimization is proposed. In this method, the fitness function is constructed using the correlation information entropy. Feature subsets are regarded as individuals in a population, and the feature space is searched using V-shaped binary particle swarm optimization. The above procedure overcomes the hard constraint on the number of features, enables the combined evaluation of each subset as a whole, and improves the search ability of conventional binary particle swarm optimization. The proposed algorithm is an adaptive method with respect to the number of feature subsets. The experimental results show the advantages of optimizing the feature subsets using the V-shaped transfer function and confirm the effectiveness and efficiency of the feature subsets obtained under different classifiers.