Increased competition in the market has formed a novel production model of multivariety and small batch to satisfy the demand of different users for personalized products. Since each user pursues different objectives, a multi-agent system is integrated into the novel production model to balance the satisfaction between diverse users and improve the overall benefit of the model. Multi-agent flexible job shop scheduling problem (MAFJSP) is researched in this article, with objectives including total tardiness (TTD) of user agents and delivery time balancing (DTB) of the job shop agent. Deep learning on graphs with evolutionary neural topology (GDL-ENT) is devised to address the MAFJSP. Aheterogeneous graph is designed to carefully represent the environment information containing the operation, machine, and user agents, while a heterogeneous attention network (HAN) is employed to hierarchically extract state features according to user agents. Meanwhile, the automatic generation of the structure and hyperparameters for the neural network in deep learning on graphs is achieved by the evolutionary neural topology search method. The performance and generalization of the GDL-ENT, as well as the influence of main components in the GDL-ENT, are analyzed on the randomly generated test suite, public benchmark instances, and the real-world dataset, respectively. The GDL-ENT has superior competitiveness compared to the state-of-the-art algorithms for solving the MAFJSP from experiment results.

Moth-flame optimization (MFO) algorithm has received a lot of attention recently, due to its simple structure and easy coding. Researchers have demonstrated that the original MFO algorithm suffers from the drawbacks of insufficient variety, slow convergence speed, and readily sliding into local optimum, which are brought about by the imbalance between local and global search. Reinforcement learning driven moth-flame optimization (RLMFO) algorithm is designed to correct these issues. Opposition learning is employed to broaden the variety of the initial population. Reinforcement learning is introduced to direct the local and global search process of the algorithm. A strategy pool containing Gaussian mutation (GM), Cauchy mutation (CM), Lévy mutation (LM), and elite strategy (ES) is created to hold strategies with various functions. RLMFO is verified on the benchmark test suite in CEC 2017. RLMFO performs better than cutting-edge algorithms according to experimental findings.

The distributed no-wait flow-shop scheduling problem (DNWFSP) is a frontier and important research topic. In this paper, a population-based iterated greedy algorithm (PBIGA) is presented to settle the DNWFSP with the makespan criterion. In PBIGA, an improved FRB2 algorithm is proposed to Initialize a high-quality population. Four local search methods based on the framework of variable neighborhood descent (VND) and optimal block knowledge are presented to improve the quality of the individual. Destruction-Construction operator is proposed according to the characteristics of PBIGA. A selection mechanism is proposed to determine which individuals perform the local search. An acceptance criterion determines is presented, which decides whether the offspring are received. Ultimately, the PBIGA and other algorithms for DNWFSP are tested on the benchmark presented by Naderi and Ruiz.

The moth-flame optimization (MFO) algorithm is extensively employed to attain the global optimization of a problem. The original MFO algorithm has drawbacks of low population diversity, slow convergence speed, and falling into local optimum easily. An improved moth-flame optimization algorithm (CLMFOLDS) based on comprehensive learning (CL) mechanism and low discrepancy sequence (LDS) is presented in this paper to solve the problem. A random population with uniform distribution is generated in the search space by using LDS. The information of the entire population is learned to gain the position of the new moth, which is called the CL strategy. External storage is designed to save the suboptimal solution throughout the iteration. The elimination mechanism is employed to strike out the poor solution in the population to enhance the global search capability of the algorithm. The CLMFOLDS is assessed in the CEC 2017 benchmark problem. Experimental results illustrate that the CLMFOLDS algorithm is superior to state-of-the-art algorithms.

Coherent imaging of synthetic aperture radar (SAR) systems generates multiplicative speckle noise, severely impairs SAR images’ interpretability. Although numerous despeckling methods have been proposed over the past three decades, SAR despeckling remains an unsolved problem due to its uniqueness and complexity. To address these issues, we propose a novel SAR image despeckling method based on the framework of weighted nuclear norm minimization (WNNM). First, a Gaussian function is used to approximate the distribution of good similar patches (GSP). Clustering is then used to select the optimal patches for the GSP matrix. WNNM can then estimate the underlying clean component of the GSP matrix. To increase the speed of the WNNM, a modified version of the singular value decomposition (SVD) is introduced. Additionally, we developed a noise variance estimation method that enables blind despeckling with the proposed method. Extensive experimental results demonstrate that the proposed method yields superior objective indices and subjective visual inspection.

It is challenging to build domain-specific emotional lexicon for film reviews, due to its unique characteristics, such as massive data, endless new login words, and others. To improve the accuracy of film reviews classification, this article proposes a method for extending emotional lexicon based on word distance and point mutual information. First, using the improved K-means++ algorithm to cluster and select seed words with obvious emotional tendencies. Next, the Distance of Word and Point Mutual Information (DW-PMI) algorithm is presented to determine the emotional polarity of emotional words in the domain of film reviews. Four types of vocabulary, including degree adverb, negation, emoticon and emotion dictionary in the film reviews domain are added to the basic emotion dictionary to extend the film reviews emotional lexicon. From the experimental results, the expanded emotional lexicon of the Chinese film reviews can improve the accuracy and preciseness of the film reviews emotion analysis.