The multi-granular probabilistic linguistic modeling allows decision makers to express cognitive information using multiple linguistic term sets based on their preferences. However, personalized individual semantics (PIS) can lead to different meanings of the same word within the linguistic context. To address this issue and manage consensus in large-scale group decision making , this study proposes a decision framework that employs multi-granular probabilistic linguistic preference relations (MGPLPRs). First, a transformation method is presented to unify different granularity levels of MGPLPRs, thus ensuring the consistency of granularity. Moreover, a consistency-driven optimization model is constructed to generate the numerical scales with PIS for different experts. Thereafter, a two-stage consensus reaching process (CRP) is developed, including both within-cluster and across-cluster CRP, to achieve group consensus. The experts’ original weights are derived from a social network, taking into account the trust relationships among them. A dynamic weighting mechanism is used to update the experts’ weights based on their contributions to group consensus, which better reflects the actual situation than fixed weights. The proposed method is exemplified through a case study of assessing and selecting campus surveillance measures for COVID-19. Finally, the effectiveness and robustness of the proposed framework are verified through comparative analysis and sensitivity analysis.

This paper proposes an extended VlseKriterijuska Optimizacija I Komoromisno Resenje (VIKOR) method based on the particle swarm optimization (PSO) algorithm for solving multicriteria group decision-making problems with probabilistic linguistic information. First, we define the novel operations of probabilistic linguistic term sets and then prove the corresponding properties. Second, we apply a modified PSO algorithm to the consensus reaching process to improve the collective consensus level. In the context of probabilistic linguistic information, each participant can be recognized as a particle moving towards the best position. The consensus level can be regarded as the objective function that is used to construct the fitness function. In the update function, the trust relationship and the similarity measure between experts are exploited to determine the adjustment coefficient. The new consensus model based on PSO can ensure that the ultimate evaluation achieves a high level of consensus. Afterward, we propose the extended VIKOR method to obtain the optimal solution, which not only avoids the loss of decision information, but also considers the separation of each alternative from the positive ideal solution and the negative ideal solution when criteria are interactive. The advantages of the proposed method are highlighted through a numerical example. Finally, we perform a comparative analysis and a sensitivity analysis to reveal the effectiveness and applicability of the method.

Class imbalance is often a problem in various real-world datasets, where one class contains a small number of data and the other contains a large number of data. It is notably difficult to develop an effective model using traditional data mining and machine learning algorithms without using data preprocessing techniques to balance the dataset. Oversampling is often used as a pretreatment method for imbalanced datasets. Specifically, synthetic oversampling techniques focus on balancing the number of training instances between the majority class and the minority class by generating extra artificial minority class instances. However, the current oversampling techniques simply consider the imbalance of quantity and pay no attention to whether the distribution is balanced or not. Therefore, this paper proposes an entropy difference and kernel-based SMOTE (EDKS) which considers the imbalance degree of dataset from distribution by entropy difference and overcomes the limitation of SMOTE for nonlinear problems by oversampling in the feature space of support vector machine classifier. First, the EDKS method maps the input data into a feature space to increase the separability of the data. Then EDKS calculates the entropy difference in kernel space, determines the majority class and minority class, and finds the sparse regions in the minority class. Moreover, the proposed method balances the data distribution by synthesizing new instances and evaluating its retention capability. Our algorithm can effectively distinguish those datasets with the same imbalance ratio but different distribution. The experimental study evaluates and compares the performance of our method against state-of-the-art algorithms, and then demonstrates that the proposed approach is competitive with the state-of-art algorithms on multiple benchmark imbalanced datasets.

Structural equation modeling (SEM) is a system of two kinds of equations: a linear latent structural model (SM) and a linear measurement model (MM). The latent structure model is a causal model from the latent parent node to the latent child node. Meanwhile, MM’s link is from latent variable parent node to observed variable child node. However, researchers should determine the initial causal order between variables based on experience when applying SEM. The main reason is that SEM does not fully construct causal models between observed variables (OVs) from big data. When the artificial causal order is contrary to the fact, the causal inference from SEM is doubtful, and the implicit causal information between the OVs cannot be extracted and utilized. This study first objectively identifies the causal order of variables using the DirectLiNGAM method widely accepted in recent years. Then traditional SEM is converted to expanded SEM (ESEM) consisting of SM, MM and observation model (OM). Finally, through model testing and debugging, ESEM with good fit with data is obtained.