Mechanical fault vibration signal is a typical non‐Gaussian process, they can be characterized by the infinite variance process, and the noise within these signals may also be the process in complex environments. The performance of the traditional cross‐term reduction algorithm is compromised, sometimes yielding incorrect results under the infinite variance process environment. Several robust fractional lower order time–frequency representation methods are proposed including fractional low‐order smoothed pseudo Wigner (FLOSPW), fractional low‐order multi‐windowed short‐time Fourier transform (FLOMWSTFT), and improved fractional low‐order multi‐windowed short‐time Fourier transform (IFLOMWSTFT) utilizing fractional low‐order statistics and short‐time Fourier transform (STFT) to mitigate cross‐terms, enhance time–frequency resolution, and accommodate the infinite variance process environment. When compared to traditional methods, simulation results indicate that they effectively suppress the pulse noise and function effectively in lower mixed signal noise ratio (MSNR) in an infinite variance process environment. The efficacy of the proposed time–frequency algorithm is validated through its application to mechanical bearing outer ring fault vibration signals contaminated with Gaussian noise and subjected to an α infinite variance process.

Wireless-powered mobile edge computing (WP-MEC) is a new network computing paradigm, which integrates with the advantages of wireless power transfer and mobile edge computing. In WP-MEC, the time of wireless power transfer is a key factor affecting the performance of network system when the harvest-then-offload protocol is employed. If the time of wireless power transfer is too short, the user cannot harvest enough energy; If it is too long, the task uploading time left for the user is insufficient. Both result in numerous user tasks being discarded. To tackle this problem, an optimization algorithm for the time of wireless power transfer based on differential evolution is proposed. The hybrid mutation operator and perturbation based binomial crossover operator are designed for this algorithm. These two improvements effectively enhance the optimization performance of DE, conducive to find the optimal time of wireless power transfer. Moreover, the micro-population is introduced into this algorithm in order to improve the optimization efficiency. Finally, the performance of this algorithm is verified through the existing computation completion ratio maximization model under the WP-MEC scenario with multiple edge servers. Numerical results show that the computation offloading scheme incorporating this algorithm can achieve a higher computation completion rate of user tasks than the benchmark schemes. This proves that the proposed algorithm can find a better wireless power transfer time than the benchmark schemes and is an effective wireless power transfer time optimization scheme.

Summary Breast cancer is the most common tumor that seriously threatens the life of women. However, with imprecise measure methods, the detection results are not reliable enough, and this will bring more pain and cost to patients. Therefore, accurate identification of breast cancer is a very important issue. To tackle this problem, a composite firefly algorithm (named CoFA) is proposed, in which each firefly is attracted compositely by the best and two randomly selected fireflies. First, the composite attraction method increases the probability that the current firefly generates better solution. In addition, the two fireflies are randomly selected, whatever they are better or worse than current firefly, the population diversity can be improved. The proposed CoFA has been tested on several breast cancer datasets derived from UCI. Experimental results verified that CoFA significantly improves the recognition accuracy.

Brain storm optimization (BSO) is a kind of swarm intelligence, which is derived from human brainstorming process. And it has been successfully applied in solving practical problems. As a relatively new algorithm, BSO has the problem of slow convergence speed and being prone to local optimum. In this paper, BSO with role-playing strategy (RPBSO) is proposed. In RPBSO, role-playing strategy is adopted to classify ideas, and idea difference strategy is utilized to generate new ideas. To maintain the diversity of ideas and prevent getting into local optimum, re-initialization operation is adopted as well. RPBSO and several variants of BSO are compared on CEC 2013 benchmark functions. The experimental results show that RPBSO is better than other variants of BSO, which verifies the performance of RPBSO.

Cuckoo search algorithm (CS), as a new heuristic algorithm, has been paid increasing attention and studied by many scholars because of its efficient performance. However, premature convergence is a defect of CS. Recently, some heuristic algorithms have been successfully applied to some high performance computing frameworks, effectively overcome the premature convergence problem of the algorithm, which provides us with a new idea to enhance CS. Therefore, a novel CS variant, called Spark-based gaussian bare-bones cuckoo search with dynamic parameter selection (SparkGDCS), which combines a novel CS variant with the efficient Spark framework, is proposed in this paper. In SparkGDCS, GDCS is a new variant which combines Gaussian bare-bones strategy and dynamic parameter selection, whose purpose is to enhance the search ability of CS. Finally, by testing the benchmark functions proposed by the 2010 and 2013 IEEE Congress on Evolutionary Computation special session (CEC 2010 and CEC 2013), comprehensive experiments prove the effectiveness of SparkGDCS.

Brain storm optimization algorithm (BSO) is a new but excellent algorithm who based on brainstorming process. However, BSO has some disadvantages like premature convergence and high time complexity. In order to solve these problems, a new BSO based on competition mechanism (BSOCM) is proposed in this paper. BSOCM replaces the k-means cluster by sorting the population, and adopts the mutation strategy of competition mechanism to stimulate the population to generate more individuals. In this way, BSOCM reduces time complexity. At the same time, the strategy of competition mechanism is added to ensure the optimization ability of the algorithm, and the precocity of the algorithm is reduced. The experimental results showed that BSOCM could avoid premature local optimization. The benchmark function of CEC 2013 was used in a comprehensive experiment, the test results of BSO, DE, MBSO, PSO and BSOCM were compared respectively. Relevant experiments in this paper prove that BSOCM has good search efficiency.

This paper presents an improved approach of particle swarm optimization (PSO) based on new neighborhood search strategy with diversity mechanism and Cauchy mutation operator (denoted EPSONS). Firstly, with a test on thirteen well-known benchmark functions, the proposed algorithm has significant imp rovement over several other PSO variants for global numerical optimization. The proposed approach is then applied to data clustering. The experimental results on fourteen benchmark data sets including artificial and real-world data sets show that the proposed method outperforms than other comparative clustering algorithms in terms of accuracy and convergence speed.

Generalized opposition-based differential evolution (GODE) is an effective algorithm for global optimization over continuous search space. However, the performance of GODE highly depends on its control parameters. To improve the performance of GODE, this paper proposes an enhanced GODE algorithm called AGODE, which employs an adaptive generalized opposition-based learning (GOBL) mechanism to automatically adjust the probability of opposition during the evolution. Experimental study is conducted on a set of 19 well-known benchmark functions. Computational results show that the proposed approach AGODE outperforms some state-of-the-art DE variants on the majority of test problems.