Multimodal Emotion Recognition in Conversation (MERC) aims to identify the emotional state of a speaker who expresses their opinions through text, vision, and audio information during conversations. MERC enables intelligent machines to exhibit empathy, which can increase the effectiveness of human–computer interactions. However, the existing research lacks sufficient mining of the emotional and semantic information of multiple modalities, as well as the differences and associations between multiple modalities. Hence, the two core focuses of this study are the multimodal feature mining method and the emotion fusion method in the conversational context. We propose a Feature-Enhanced Multimodal Interactive (FEMI) model for MERC tasks. Specifically, the proposed FEMI model is designed considering the following three objectives: (1) designing a feature-enhanced module that contains different feature extractors to explore deep emotional and semantic information from emotional clues and semantic attributes; (2) building a dialogue incremental transformer module to reconstruct the context interaction between interlocutors; and (3) proposing a multimodal interactive module to eliminate multimodal differences and build multimodal and cross-modal emotional associations. Extensive experiments were performed on two public datasets, and the results demonstrated that the proposed FEMI model is superior to MERC tasks.

To address the limitations in precision of conventional traffic state estimation methods, this article introduces a novel approach based on the Transformer model for traffic state identification and classification. Traditional methods commonly categorize traffic states into four or six classes; however, they often fail to accurately capture the nuanced transitions in traffic states before and after the implementation of traffic congestion reduction strategies. Many traffic congestion reduction strategies can alleviate congestion, but they often fail to effectively transition the traffic state from a congested condition to a free-flowing one. To address this issue, we propose a classification framework that divides traffic states into sixteen distinct categories. We design a Transformer model to extract features from traffic data. The k-means algorithm is then applied to these features to group similar traffic states. The resulting clusters are ranked by congestion level using non-dominated sorting, thereby dividing the data into 16 levels, from Level 1 (free-flowing) to Level 16 (congested). Extensive experiments are conducted using a large-scale simulated traffic dataset. The results demonstrate significant advancements in traffic state estimation achieved by our Transformer-based approach. Compared to baseline methods, our model exhibits marked improvements in both clustering quality and generalization capabilities.

Recently, financial institutions and investors have placed an increasing emphasis on ESG (environmental, social, and governance) as a principal indicator for the evaluation of companies. However, the current ESG scoring systems lack uniformity and are often subjective. It is of great importance to be able to make accurate predictions regarding the ESG scores of corporations. A Stacked Generalization Model that employs Random Forest (RF), Gradient Boosting Decision Tree (GBDT), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM) as base learners, with Bayesian Ridge Regression (BRR) as the meta-model for integrating the predictions of these diverse models is proposed. The goal is to develop an ESG score prediction model for Chinese companies. The experimental data set encompasses Chinese A-share listed companies from 2012 to 2020. The Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2) are employed for model evaluation and are compared with seven benchmark models. The results demonstrate that SGM-BRR reduces the RMSE by 18.4%, 17.3%, 13.7%, and 76.1%, the MAE by 15.4%, 18.4%, 15.8%, and 68.4%, and increases the R2 by 2%, 1.4%, 2%, and 6% for ESG, E, S, and G scores, respectively. Furthermore, the model’s performance is validated across different industries, with SGM-BRR exhibiting the most optimal performance of RMSE, MAE, and R2 in 27, 25, and 27 groups, respectively. Consequently, the model demonstrates broad applicability and stability performance in ESG score prediction.

To solve the problems of high sampling requirements and low predictive accuracy resulting from the complexity, uniqueness, and randomness of predicting the risk of the CO2 and N2 injection to enhance coal seam gas drainage (CO2/N2-ECGD) technology. The principal component analysis (PCA) method to reduce the dimensionality of the factor data that contribute to the effect risk of the technology was adopted. And the particle swarm optimization (PSO) method was implemented to search for optimal hyperparameters in support vector machine (SVM) by particle search, as a solution to the traditional SVM hyperparameters optimization problem. A novel risk prediction model using machine learning algorithms for gas injection displacement technology was constructed. The prediction results were tested and compared with those of backpropagation (BP), Random Forest (RF), and Decision Tree (DT) models using data from 29 gas injection displacement field projects in China. The results demonstrated that the SVM model had greater accuracy in prediction than the other three models. Additionally, after PSO optimization and dimensionality reduction, the PCA-PSO-SVM model reached 100% prediction accuracy, while requiring less modeling and operation time. The study provided a reliable and reasonable model for predicting technical effects, along with a theoretical basis for risk management and prevention. First, the technology's influencing indicators were analyzed by examining its mechanisms. Second, we utilized the PCA method to reduce the dimensionality of the factor data that contribute to the risk of the technology's effects. Third, we implemented the PSO method to search for optimal hyperparameters in the SVM through particle search, as a solution to the traditional SVM hyperparameters optimization problem. Finally, the prediction results were tested and compared with those of BP, RF, and DT models using data from 29 gas injection displacement field projects in China. The SVM model was found to have greater accuracy in prediction than the other three models. After PSO optimization and dimensionality reduction, the PCA-PSO-SVM model achieved 100% prediction accuracy while requiring less modeling and operation time. The study presents a valid and reasonable model for predicting technical effects and a theoretical basis for risk management and prevention.

Accurate stock price prediction is critical for investment decisions in the stock market. To improve the performance of stock price prediction, this paper proposes a novel two-stage prediction model that consists of a decomposition algorithm, a nonlinear ensemble strategy, and three individual machine learning models. Specifically, in the first stage, the stock price time series is decomposed into a finite number of sub-series by variational mode decomposition (VMD). Subsequently, three individual machine learning models, namely support vector machine regression (SVR), extreme learning machine (ELM), and deep neural network (DNN), are separately employed to predict decomposed sub-series, and then the obtained sub-series predictions of each individual prediction model are aggregated to generate the preliminary stock price predictions. In the second stage, an ELM-based nonlinear ensemble strategy is employed to combine preliminary stock price predictions. To verify the effectiveness of the proposed two-stage model, it is compared with a total of fourteen models in terms of accuracy evaluation, improvement percentage comparison, and statistical test. The empirical results demonstrate that the proposed two-stage model can obtain better performance than other competitor models.

In recent decades, private labels have been the focus of great development in retail due to their price advantage and consumer-oriented production. With growing customer awareness of safety and health, private-label sustainable supplier selection has become a strategic issue for many retailers. Although there are many studies on supplier selection issues and evaluation methods, studies on the sustainability and consumption sectors are rather limited. Therefore, a novel three-phase MCDM model for private-label supplier selection compliance with sustainability criteria is proposed. First, the Delphi method is used to construct a criteria system based on a detailed literature review. Then, an integrated weight algorithm is suggested, in which objective weights are based on attributes’ entropy measurements, and subjective weights are derived from decision-makers’ preferences. Eventually, during evaluation, a fuzzy set extended in VIKOR is exploited by considering the vagueness of decision makers’ expressions. The results from a case study then show that green packaging and labelling, relationship with manufacturing brand, order flexibility, and product traceability are the most important criteria in retail private-label supplier selection. The flexibility and reliability of the proposed model are also demonstrated in a practical case of supplier evaluation.

Detection of critical nodes in complex networks has recently received extensive attention. Currently, studies of the critical nodes problem (CNP) mainly focus on two problem types: "critical nodes problem/positive" (CNP-Pos) and "critical nodes problem/negative" (CNP-Neg). However, to the best of our knowledge, few studies have been conducted on CNP-Neg for weighed networks. In this paper, we investigate CNP-Neg in undirected weighted networks. We first propose a novel metric DFW to evaluate network fragmentation. Then, we formulate a new nonconvex mixed-integer quadratic programming model, named MIQPM, that aims to simultaneously minimize pairwise connectivity and maximize the weights between the nodes. After that, a general greedy algorithm is employed to solve the corresponding optimization problem. Finally, comparison experiments are carried out for several synthetic networks and four real-world networks to demonstrate the effectiveness of the proposed approaches.

In this paper, we discuss the fuzzy portfolio selection problems in multi-objective frameworks. A comprehensive model for multi-objective portfolio selection in fuzzy environment is proposed by incorporating mean-semivariance model and data envelopment analysis cross-efficiency model. In the proposed model, the cross-efficiency model is formulated within the framework of Sharpe ratio; bounds on holdings, and cardinality constraints are also considered. The nonlinear constrained multi-objective portfolio optimization problem cannot be efficiently solved by using traditional approaches. Thus, a multi-objective firefly algorithm is developed to solve the relevant model. Finally, an example verifies the validity of the proposed approaches.

Influential nodes identification problem (INIP) is one of the most important problems in complex networks. Existing methods mainly deal with this problem in undirected networks, while few studies focus on it in directed networks. Moreover, the methods designed for identifying influential nodes in undirected networks do not work for directed networks. Therefore, in this paper, we investigate INIP in directed networks. We first propose a novel metric to assess the influence effect of nodes in directed networks. Then, we formulate a compact model for INIP and prove it to be NP-Complete. Furthermore, we design a novel heuristic algorithm for the proposed model by integrating a 2-opt local search into a greedy framework. The experimental results show that, in most cases, the proposed methods outperform traditional measure-based heuristic methods in terms of accuracy and discrimination.

This paper presents some continuous dependence theorems on solutions of uncertain differential equations based on uncertain measure. We first introduce some properties on solution of uncertain differential equation. And then, we provide a continuous dependence theorem, and a continuity theorem to the initial value. In the proposed continuity theorem, the solution is regarded as a ternary function of initial values. Furthermore, we discuss how the solution continuously depends on initial value and parameter, and propose two theorems, namely, continuous dependence theorem on parameter, and continuity theorem on parameter to the initial value.

Critical nodes group identification problem has become a hot research in the microscopic level of complex networks. In the big data era, existing methods based on simulations and measures often fail in local solutions with the increasing scale and complexity of complex networks. Meanwhile, the mainstream integer linear programming (ILP) model has the drawback of neglecting internal structures of connected components. Hence, for the critical nodes group identification problem, it needs to carry on a further research on formulating mathematical models from the topological structure and function of networks. In order to solve these problems, this paper proposes a 0-1 nonconvex quadratically constrained quadratic programming (QCQP) model by minimizing the number of pairwise nodes within second-order pathway. Simultaneously, a heuristic algorithm is designed by combining greedy search and local exchange to solve critical nodes problem for large-scale networks. Finally, many synthetic and real-world networks are conducted in the experiments to validate the effectiveness and efficiency of the proposed approach.

Stock index price forecasting is a consistent focus of business intelligence. Various factors influence stock index price forecasting, such as technical indicators, financial news, business status, and the macroeconomics situation. In addition, many studies have shown that the exchange rate is related to the stock index price; however, no study has examined whether the exchange rate can be used to forecast stock index prices. Therefore, this paper focuses on this topic and uses exchange rate to predict China stock index price for the first time. Firstly, we compare the association of China stock index price with different data sources to illustrate the feasibility of using the exchange rate to predict stock index prices. Then, we generate some additional technical features of the exchange rate and propose a strategy to predict the stock index price. Finally, we compare the forecast results of China's stock index price based on four data sources, i.e., technical indicators, exchange rate data, US market index data and finance news data from January 3, 2017 to March 20, 2019. Experimental results demonstrate that the performance of exchange rate data for stock index prediction is comparable to other popular data sources and that, in some prediction periods, the exchange rate outperforms such data sources. The results confirm that the exchange rate could be used for forecasting the Shanghai Composite Index prices.

In financial markets, investors will face not only portfolio risk but also background risk. This paper proposes a credibilistic multi-objective mean-semi-entropy model with background risk for multi-period portfolio selection. In addition, realistic constraints such as liquidity, cardinality constraints, transaction costs, and buy-in thresholds are considered. For solving the proposed multi-objective problem efficiently, a novel hybrid algorithm named Hybrid Dragonfly Algorithm-Genetic Algorithm (HDA-GA) is designed by combining the advantages of the dragonfly algorithm (DA) and non-dominated sorting genetic algorithm II (NSGA II). Moreover, in the hybrid algorithm, parameter optimization, constraints handling, and external archive approaches are used to improve the ability of finding accurate approximations of Pareto optimal solutions with high diversity and coverage. Finally, we provide several empirical studies to show the validity of the proposed approaches.

Link prediction has become an important area in network analysis in recent years due to its theoretical and practical significance. In this paper, we present a similarity-based prediction method under simultaneous consideration of multiple information sources and the corresponding discrimination ability. We first propose a novel supervised transitivity similarity index (STSI), in which the likelihood ratio in the Bayesian theory is employed to supervise the transitivity process. Then, based on the proposed STSI, we design a supervised transitivity similarity algorithm (STSA) for predicting missing links. Finally, empirical experiments are conducted to demonstrate the effectiveness of the proposed method. The experimental results show that our method can achieve a good performance, compared with other mainstream baselines.

Nowadays, the third-party logistics grows rapidly, but some enterprises in distribution industry still choose to build their own logistics department. Why they choose enterprise-owned logistics instead of third-party logistics service? And how enterprise-owned logistics develop in the future? In this paper, we present reasons to choose enterprise-owned logistics and the situations they face. At the end, we offer some countermeasures to develop the enterprise-owned logistics in the future.