Search

With global climate change posing a major threat to human society, a growing number of countries have taken "carbon-neutral" as a national strategy and proposed a vision of carbon-free future. As an important supplement to traditional fossil energy, renewable energy is the main force to reduce the use of high-carbon energy and carbon dioxide emissions, which will become the trend of social development in the future. Finding the optimal renewable energy source is of particular significance for achieving the net zero emissions. However, the existing evaluation methods of renewable energy sources have obvious shortcomings. In terms of weight calculation methods, such as the randomness of the subjective method is strong and the index weights do not reflect the small changes of the evaluation matrix, which affect the reliability and accuracy of the evaluation result. The existing ranking methods can only achieve the complete ranking of the different objects, but cannot classify the renewable energy technical alternatives into different grades. Given this background, this paper proposes a novel evaluation method for renewable energy plans based on improved sparrow search algorithm and projection pursuit model. Firstly, this paper improves the traditional sparrow search algorithm from three aspects: population initialization, population update and population variation. Then, the projection pursuit model is constructed, and the improved sparrow search algorithm is applied to optimize the projection target to find the optimal projection direction, so as to determine the weight values of each evaluation index. Finally, the weighted rank-sum ratio method is used to select the best renewable energy technical plan, which can not only realize the complete ranking of different plans, but also classify the technical plans into different levels. Based on the actual renewable energy development data from a province in China, experiments were carried out to investigate the effectiveness of the proposed method. Experimental results show that the proposed method performs better than some existing evaluation methods of renewable energy technical plans. [ABSTRACT FROM AUTHOR]

The focus of this paper is on achieving a win-win situation regarding the economic, environmental, and social impacts of the cold chain logistics terminal distribution system. This paper proposes three multi-objective models to investigate the above effects by incorporating soft time windows, heterogeneous fleets, and path flexibility, with defining the objectives of examining logistics costs, fuel consumption, carbon emissions, quality damage to perishable commodities, and customer satisfaction using six evaluation functions. To solve the proposed models, an efficient optimization framework is developed by combining domain operators with versatile multi-objective evolutionary algorithms (MOEA) to obtain Pareto solutions. Extensive experiments are conducted to test the validity of the concerned model and algorithms. The results demonstrate that: (1) the proposed algorithm is effective in solving the proposed model; (2) the proposed multi-path strategy can effectively improve the performance of cold-chain logistics systems compared to single-path strategies; (3) evaluation functions that assess customer satisfaction greatly affect the performance of cold-chain logistics systems; and (4) the trade-off relationship between the objectives should be investigated to define the model. The paper also provides valuable managerial insights for improving the efficiency and sustainability of cold-chain logistics operations. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new deformable convolutional network with attention mechanism to deal with the Chinese character of various dynasties. These ancient Chinese characters are hieroglyph with special spatial structure and gradually evolving into modern Chinese characters. However, because of the intrinsic limitations of traditional convolutional networks in the model, the geometric structure of the convolutional module is fixed. Therefore, we build a new architecture called attention-based deformable networks for this task. Besides, we construct a new dataset called the Chinese characters from Various Dynasties Dataset (CCDD), which includes the evolution of Chinese characters between major dynasties. Deformable convolution based on attention mechanism can obtain those more important offsets, resulting in better performance than the original deformable convolution. In the experimental stage, extensive experiments validate the performance of our approach. Firstly, the effectiveness of this network was verified on two text datasets, Mnist(99.38%) and notMnist(98.22%) both comparing with several modules. Finally, the best performance was achieved on the CCDD dataset(91.50%) compared to other classical deep learning networks. This is the first paper to apply deep learning methods to recognize and classify the characters of major dynasties in China. And archaeological workers need to be able to recognize Chinese characters from various periods in China, and our algorithm can assist them in completing this task to a certain extent. It can also help cultural relic enthusiasts roughly determine the age of cultural relics. [ABSTRACT FROM AUTHOR]

• Study analyzes 1374 papers on sensitivity analysis in Scopus. • RStudio, CiteSpace, and VOSviewer are used. • China has most articles published; India leads in international cooperation. • Top three cited journals: J. Clean. Prod., Expert Syst. Appl., and Comput. Ind. Eng. • Most cited authors are Pamučar D, Kahraman C, and Zavadskas EK. In the present era, the implementation of scientifically grounded Multi-Criteria Decision Making (MCDM) has emerged as a pivotal solution to diverse decision-making challenges across various domains. Although a substantial body of exploratory, conceptual, and experimental studies exists, only 9.457% studies have incorporated sensitivity analyses to assess the robustness of MCDM methods. An exhaustive scientific exploration of sensitivity analysis within the scope of MCDM is thus lacking. This research aims to address this gap through Bibliometric Analysis while examining 1374 articles published between January 2000 and March 2023 from the Scopus database. Using RStudio (Biblioshiny), CiteSpace, and VOSviewer software, the study constructs a visual representation of the most prolific countries, institutions, and authors. Impressively, China takes the lead in article publications, while India excels in international collaboration. "An extended TODIM multi-criteria group decision-making method for green supplier selection in an interval type-2 fuzzy environment," featured in the Journal of Environmental Management, emerges as the most cited paper with a total citation of 455. The study also identifies the top three most cited journals, namely "Journal of Cleaner Production," "Expert Systems With Applications," and "Computers and Industrial Engineering." "North China Electric Power University" is the leading institute with the highest research outputs. "Pamučar D" is the most cited author, with 2594 citations and 39 articles, followed by "Kahraman C" and "Zavadskas EK. This study sheds light on trends in scientific developments and collaborations, providing a model for the application of sensitivity analysis in MCDM research and highlighting global trends. An understanding of the current state of sensitivity analysis research can assist researchers working in the entire domain of MCDM. Additionally, the visualization provides prescriptive data for future work and applications related to sensitivity analysis. [ABSTRACT FROM AUTHOR]

With the advent of the post-pandemic era, the global economic situation has tightened, and the economic benefits of container ports have also been affected. This paper attempts to build a novel berth-tugboat-quay crane joint scheduling method for container ports to reduce the economic cost of container ports. Firstly, from the perspective of the economic cost of container ports, considering random economic factors, this paper proposes a new berth-tugboat-quay crane joint dispatch optimization model, namely E-BUQC, by taking the minimum time cost of vessels in port, the cost of additional freight distance for trucks, the cost of tugboat operation, and the minimum operation cost of quay cranes as the objective function. Then, in order to obtain a relatively high-quality solution, based on chaotic mapping and quantum computing, this paper constructs a new chaotic quantum adaptive satin bower bird optimizer algorithm, namely CQASBO, formulates exclusive coding rules for the E-BUQC model, develops a feasible integer algorithm, and proposes a new joint scheduling solution method of berth-tugboat-quay crane, named E-BUQC_CQASBO. Subsequently, based on the simulation examples of two ports in northern China, the new solution method is tested. The simulation test results show that the E-BUQC model obtains an appropriate solution; The CQASBO constructed in this paper has better performance than other traditional comparison algorithms selected in this paper and can provide a better solution when solving the E-BUQC model. [ABSTRACT FROM AUTHOR]

Over recent decades, China's economy has continued to develop steadily and rapidly, contributing to a large environmental cost. Therefore, many researchers propose various methods to evaluate environmental efficiency to deal with these serious issues accurately. This paper is the first to evaluate environmental efficiency using a model featuring not only a parallel structure with three component processes (primary, secondary, and tertiary industries) in the first stage but also a sewage treatment process in the second stage. Simultaneously, we propose radial but also nonradial versions of the Environmental Multiple Variable Return to Scale (EMVRS) model. These two models both consider shared inputs as well as shared outputs, and the proportion of the shared inputs and shared outputs utilized in each component process is assumed to be unknown. Additionally, we further analyze the factors influencing environmental efficiency by utilizing the Tobit model. The results when EMVRS is applied to Chinese provinces can be divided into 3 parts: (1) Most provinces do not purify wastewater appropriately contributing to the bad environmental efficiency. (2) The efficiency values of the three industry types are similar or identical to each other in most provinces. (3) The population of people employed negatively impacts environmental efficiency. [ABSTRACT FROM AUTHOR]

As an effective approach in ranking decision making units (DMUs), cross-efficiency evaluation is only extended to two basic network systems: series and parallel, which is not applicable to the common complex network system in reality. By using the directional distance function (DDF), this paper extends the cross-efficiency evaluation to a complex system called the parallel two-stage system, which consists of several independent parallel processes and each of them is a sub-system with a general two-stage series structure. The proposed method is able to decompose the cross-efficiency measure of the system into the weighted average of those of processes, stages and overall stages, respectively, and as a result, successfully achieves the layer-by-layer decomposition of cross-efficiency measures under complex nested networks. An empirical study on 40 open-ended equity funds in China from 2018 to 2020 verifies that the newly proposed method not only has a stronger performance discrimination power than self-evaluation, but also can identify the relationships among efficiencies of the system, processes and stages, and meanwhile it can reflect the effects of processes and stages on the system. More importantly, our method has a better practical value for actual fund investment selection. [ABSTRACT FROM AUTHOR]

Applying artificial intelligence in education is relevant to addressing the current educational crises. Many available solutions apply Convolutional Neural Networks (CNNs) to help improve educational outcomes. Therefore, a series of works have been developed integrating techniques in different educational contexts, for instance, in online teaching practices. Given the various studies and the relevance of CNNs for educational applications, this paper presents a systematic literature review to discuss the state-of-the-art. We reviewed 133 papers from the IEEE Xplore, ACM Digital Library, and Scopus databases. Based on our revision, we discuss characteristics of studies such as publication venues, educational context, datasets, types of CNNs models, and performance of models. We evidence that the literature regarding CNNs still misses more studies discussing educational problems faced by Global South students, considering both teaching and learning perspectives. Such a population cannot be neglected during experiments due to specific educational weaknesses (for example, basic skills) demanding personalized solutions. • A systematic literature review of 133 published papers. • China covered most publications, followed by India. • There is a research gap regarding using CNNs in some regions of the Global South. • The main educational context with CNN applications is students' performance. [ABSTRACT FROM AUTHOR]

Forest carbon sink project (FCSP) has received growing attention for its outstanding advantages in carbon emission reduction, environment protection, and achieving the carbon neutrality objective. Using a government-social capital cooperation model, FCSP helps to revitalize the ecological and economic benefits of the forest with standard and efficient management. However, the management and operation barriers of FCSP implementation are complex, multiple and indefinite in the long run, which requires a comprehensive barrier evaluation framework. Hence, this paper is devoted to constructing a barrier evaluation framework for FCSP implementation in China with an integrated multi-criteria decision-making (MCDM) method. To this end, critical barriers are identified and the criteria system is constructed with a two-stage systematic literature review and interaction with the experts. Later, an applicable and comprehensive barrier evaluation framework is built, wherein the interval type-2 fuzzy set (IT2FS) is used to process fuzziness and uncertain information, the best-worst method (BWM) is adopted to determine the criteria weight, and the Preference Ranking Organization Method for Enrichment Evaluations II (PROMETHEE II) is introduced for comprehensive barrier evaluation. The criteria weighting results indicate that FCSP implementation encounters challenges taking into account institutional and governance barriers (criteria weight: 0.3592), management barriers (0.2384), economic and market barriers (0.1637), knowledge barriers (0.0747), technical and infrastructure barriers (0.1639), C1 "Lack of clear leadership and policies" and C5 "Forest management performance" were determined the most significant criteria, A5 and A4 respectively performed the lowest and the highest barrier level. In sensitivity analysis, the ranking results were stable when the criteria changed, and Spearman's rank correlations of B2, B4, and B5 are significant. The results were validated by a comparative analysis with other methods with the help of Spearman's rank correlation coefficient, which reflects accepted high correlations (Spearman's pro values of BWM-IT2F-PROMETHEE II (Gaussian rule), BWM-IT2F-TOPSIS, and BWM-TFN-VIKOR are 1.00, 1.00, 1.00). The findings of the paper help the decision makers to develop more rational strategies and successfully implement the FCSP. [ABSTRACT FROM AUTHOR]

With the number of market participants rising, the issue of contradiction between heavy supervision task and insufficient supervision resource have become increasingly urgent for regulatory authorities to consider. The credit risk rating of enterprises is therefore introduced to improve the efficiency of supervision. By analyzing the purposes of enterprise credit risk rating and the multiple demands for regulatory authorities, this paper offers a multi-classification ensemble model with hybrid decomposition strategy and two-stage multi-objective feature selection. First, an adaptive resampling technique is introduced into the hybrid decomposition strategy for multi-classification, so to appropriately allocate supervision resources in each credit risk class. Then, a two-stage multi-objective feature selection method is developed to combine the various demands of regulatory authorities for feature selection. In the first stage, results of multiple Filter feature selection methods are integrated as output to improve the performance of feature information; In the second stage, the feature information from the first stage is used as input to guide the Wrapper feature selection, which is based on the Improved Multi-objective Ant Colony Optimization. Finally, a real listed enterprise credit dataset of China is used to evaluate the performance of each module and the entire model. The empirical results show that the design of hybrid decomposition strategy and multi-objective feature selection can not only deal with the class-imbalanced problem during the decomposition process, but also take into account the balance of each demand well. More importantly, a desirable framework is set in this paper to simplify the process from imbalanced multi-classification to a balanced binary one. [ABSTRACT FROM AUTHOR]

Accurate photovoltaic (PV) power forecast is crucial for carbon neutrality. Current researches on PV power forecast mainly focus on using temporal information from single PV station, and the spatial information in multiple PV power stations are often neglected. To address this problem, this paper introduces Moran index to verify the spatial autocorrelation of PV power for the first time, uses Granger causality test and transfer entropy to reveal the spatial information gain in PV power forecast for the first time, and proposes a novel spatial–temporal probabilistic PV forecast method using deep Graph Gated Recurrent Unit (GraphGRU) network-based spatial–temporal multi-task learning and Kernel Density Estimation (KDE). Deep GraphGRU combines the advantages of Graph Convolutional Network (GCN) in spatial feature extraction and the advantages of Gated Recurrent Unit (GRU) network in temporal feature extraction, and thus has strong ability to extract spatial–temporal information in historical data of multiple different PV power stations. Through GraphGRU, temporal dependency information extracted from historical data of multiple PV stations can promote each other to improve the forecast accuracy of each PV stations. KDE is used for estimating the joint probabilistic density function and giving the spatial–temporal probabilistic confidence interval of PV power. Experiments were performed in the five-year actual PV power data from 11 provinces of Belgium and the three-year solar irradiation data from 12 places in China to verify the superiorities of the proposed method. Comparison with conventional spatial–temporal and temporal forecast methods show that the proposed GraphGRU-based spatial–temporal forecast method can extract the spatial–temporal information from multiple PV power stations well and significantly outperform conventional temporal forecast methods. [ABSTRACT FROM AUTHOR]

Using machine learning coupled with stock price data to predict stock price trends has attracted increasing attention from data mining and machine learning communities. An accurate prediction results can help investors reduce investment risks and improve investment returns. The research on correlation stocks is one of the most important directions among many studies. Due to the high volatility and randomness of stock data, the correlation between stocks changes over time, which makes the stock correlation in static correlation stock sets often inconsistent with reality. Furthermore, various raw data related to stocks contain sufficient stock history information to analyze the future trend of stocks, but traditional prediction models cannot make good use of this information, which restricts the learning ability of the model and reduces the prediction accuracy. In this paper, we propose a stock prediction model combining multi-view stock data features with dynamic market correlation information (MDF-DMC). The model extracts stock trend features by combining multi-view raw data of a single stock with a Multi-layer Perceptron Mixer (MLP-Mixer); The improved Transformer encoder learns the correlation between the stock to be predicted and all the selected stocks in the stock market dynamically and extracts the features of the market correlation. We have conducted a large number of experiments on a total of 578 stocks in the stock markets of China and the United States, and the results show that our model has achieved excellent accuracy and returns across all data sets. • Stock movements are influenced by both itself and the market. • Stock multidimensional data can be used to improve the forecasting performance. • The attention mechanism can effectively extract the correlation of market dynamics. [ABSTRACT FROM AUTHOR]

Accurate forecasting of the agricultural power load is important for rural electricity networks' safe and stable operation. But it is more uncertain and difficult to forecast than industrial, commercial, and residential loads. Multivariate time series prediction methods have problems such as poor refinement of weather services and difficulty in quantifying the influencing factors. Univariate time series prediction methods should be emphasized, and the characteristic information in the historical load data should be fully exploited. Therefore, this paper systematically investigates the decomposition strategy and attention-based recurrent neural network for univariate time-series multi-step prediction. The decomposition strategy is employed to generate derived variable sequences from the target sequence as inputs for the model, while the dual-stage attention mechanism is used for dynamically selecting features. A one-year real-world dataset of agricultural power loads in southern China is used for validation. The effectiveness of two different decomposition algorithms on dual-stage attention-based recurrent neural network (DARNN) is discussed, then the proposed ensemble empirical mode decomposition and dual-stage attention-based recurrent neural network (EEMD-DARNN) is compared with four univariate time series prediction models and three ablation models. The proposed model is optimal in four evaluation indicators, with R 2 , R M S E , M A P E , and M A E of 0.970, 12.298, 0.040, and 7.335 respectively in the shortest forecast horizon (15 min), and 0.941, 17.305, 0.065 and 11.347 respectively in the longest forecast horizon (1 h). It is a significant improvement over the existing models. In conclusion, EEMD-DARNN can achieve more accurate ultra-short-term agricultural power load forecasting. [ABSTRACT FROM AUTHOR]

The pursuit of individual mobilities expedites the development of demand-responsive systems, while the balance between service flexibilities and operational cost is becoming particularly important. This paper proposes a method for operating a novel demand-responsive bus system termed terminal-based zonal bus (TZB). It is a flexible system with vehicles executing a terminal-based zone routing scheme in specified service zones. The terminal-based routing scheme intends to generate TZB lines, and each line is operated by one vehicle that travels along a series of terminal stations arranged in order and serves enroute passenger requests between any two consecutive terminal stations. As instant response is the main trait of demand-responsive systems, TZB is able to address instance response by incorporating reserve capacity, which is employed to indicate the vehicle responsive ability of new real-time requests. Further, a tailored heuristic algorithm is designed to solve the proposed model, which simultaneously incorporates several practical restrictions, including the capability of adopting real-time requests, terminal stations' fleet-size constraints, time window constraints, and vehicle capacity. Computational experiments are conducted based upon the newly developed modern city Xiong An, China which confirm that the proposed method is capable of obtaining high-quality solutions efficiently, and TZB can provide flexible service at a relatively low operational cost. [ABSTRACT FROM AUTHOR]

• Exploring the effect of locally weighted learning with machine learning model. • Gain ratio are used to select the most important environmental factor. • LWL-RS-ADT appears as an accurate model in assessing landslide susceptibility. Assessing landslide susceptibility and predicting the possibility of landslide event is the foundation and prerequisite for emergency response and management of landslide disaster. The target of current paper is to propose five integration models based on integrating locally weighted learning (LWL) with a radial basis function classifier (RBF), Fisher's linear discriminant (FLDA), quadratic discriminant analysis (QDA), a Credal decision tree (CDT), an alternating decision tree (ADT) and random subspace (RS) and the performance of five integration models were compared for modeling landslide susceptibility. Yongxin County from China was employed as a study area, 364 landslide locations and fifteen environmental factors were applied. The results demonstrate that the proposed LWL-RS-ADT model is more reliable and stable than the other models. Among the fifteen environmental factors, NDVI, lithology, and altitude are the very significant factors in the six models. It is concluded that the proposed integration models provide an effective way to predict the susceptibility of landslides. [ABSTRACT FROM AUTHOR]

With the increasing consumption of global water resources, research on sustainable water resource utilization has become a topic of urgent interest. Despite the promulgation of policies and laws on the protection of water resources, the sustainable utilization and development of water resources in China are still far from reaching their initially established targets. This is partly explained by real-life conflicts that arise, in which different decision makers (DMs) possess different levels of professional knowledge, social status, and even power in contexts where the parties' ability to leverage information varies greatly. Sustainable water resource utilization conflicts between the government and factories exemplify the impact of this information asymmetry on the relationship between DMs for the purposes of conflict resolution. In this paper, it is assumed that if one DM in a conflict has more information, their information advantage will affect the policy formation of the other DM. Thus, to analyze and resolve relevant problems, the concept of information asymmetry between two DMs is integrated into the basic structure of the graph model for conflict resolution (GMCR). According to the mathematical expression of the information asymmetry preferences of DMs, a set of information asymmetry stability definitions can be introduced to determine the stable state for each DM. The sustainable water resource utilization conflict in Niangziguan Springs Basin is used as an exemplar to confirm the effectiveness and correctness of the proposed method. Stability analysis shows that when the government implements strict environmental policies by leveraging more information, factories should adjust their preference relations to follow the rules and regulations to protect water resource in practice. Finally, comprehensive sustainable utilization and development of natural resource mechanisms must be implemented not only for these factories but also for other industries in China. [ABSTRACT FROM AUTHOR]

Due to more and more awareness of environmental conservancy and sustainable development, automated container terminals (ACTs) have gained increasing attention and become popular worldwide. However, there is a crucial challenge in implementing ACTs, i.e., how to develop terminal layout planning (including terminal layout and facility selection) to realize performance goals. Focusing on this challenge, the aim of this paper is to resolve how to appropriately select terminal layout and facilities in ACTs with respect to various performance criteria. Several research limitations can be gathered from the existing literature: (i) Most of the existing works mainly develop optimization technologies to tackle layout optimization and facility comparison issues within a few types of terminal layout and facilities, yet few researchers have proposed evaluation methods for making selection decisions on terminal planning. (ii) Only a few types of criteria are considered, and requirements and preferences of different participants are ignored, not to say realizing an optimal compromise by employing comprehensive criteria weights in evaluation processes. (iii) New technological improvement in ACTs has not received much attention, and there still lacks a method to precisely quantify the concerned criteria. Accordingly, this paper introduces a criteria system comprising economic, environment, social, resource and performance groups and develops an agent-based simulation method considering different terminal layout and facilities to determine criteria values. A multi-criteria decision making (MCDM) framework is proposed for making the most reasonable and appropriate selection decisions, which employs a variation coefficient weighted method to calculate comprehensive criteria weights, which integrate subjective and objective weights obtained from AHP (analytic hierarchy process) method and entropy weight method. To overcome rank reversal problems in the TOPSIS (technique for order preference by similarity to an ideal solution) method, a new improved rank reversal robust TOPSIS method, called NR-TOPSIS, is utilized to rank and select alternatives, which is ranking stable in the experiments performed. An illustrative application on a container terminal in China demonstrates the effectiveness of the proposed MCDM method and sensitivity and comparative analysis verifies the robustness and stability of the method. [ABSTRACT FROM AUTHOR]

• The ecological management capacity of the Yellow River Basin is evaluated. • An Uninorm combination indicator weight model is proposed. • An integrated model based on the MULTIMOORA-Borda method is developed. • Policy recommendations are given to help improve ecological governance. As a river of great strategic significance in China, the ecological governance of the Yellow River is an important issue. As a multi-attribute decision-making (MADM) problem, evaluating the ecological governance of the Yellow River involves many evaluation indexes. To accurately measure the importance of each indicator, this paper applies the best-worst method (BWM) based on linguistic variables to calculate the subjective weights of the indexes. The improved grey relational (IGR) method is proposed to calculate the objective weights. And the two weights are combined using the Uninorm operator to obtain the combination weights of the indexes. To evaluate the problem from multiple perspectives, we apply the MULTIMOORA method to the ecological governance problem. Then we propose the novel Borda method to aggregate the three evaluation results obtained by the MULTIMOORA method and thus construct the MULTIMOORA-Borda method. Based on the above methods, we analyze the evaluation results and provide policy recommendations for ecological governance of the Yellow River Basin. [ABSTRACT FROM AUTHOR]

The air pollutant diffusion trend prediction plays an important role in the environment protection. The approaches in the existing studies rarely consider spatial and temporal information sequentially or cannot use spatiotemporal structure information effectively. In this paper, we propose a new deep learning-based air pollutant diffusion trend prediction model, called GATBL-Learning. It is an end-to-end neural network model consisting of Graph Attention Network (GAT) and Encoder-Decoder model. Since each city in the region will set as a node, GAT can extract spatial information from them by aggregation operation. Then Encoder-Decoder model, consisting of Bi-LSTM as Encoder and LSTM as Decoder, mines time series features and outputs the data containing spatiotemporal features. In addition, we also observe that the changes of air pollutants show seasonality discipline and training the seasonal model can improve the model adaptability. The results demonstrate the proposed prediction model is effective and superior. [ABSTRACT FROM AUTHOR]

Ensuring food quality and safety is essential after ensuring the quantity of food. Therefore, an improved adaptive particle swarm optimization algorithm (IAPSO) for optimizing the long short-term memory (LSTM) neural network (IAPSO-LSTM) is proposed to develop a food safety risk early warning model in this paper. The proposed IAPSO algorithm is verified by comparing with the traditional PSO (TPSO), the classic PSO (CPSO), the adaptive PSO (APSO) and the deterministic and adaptive PSO (DAPSO) based on five common benchmark functions in terms of the convergence speed and precision. Results show that the IAPSO algorithm has the best convergence speed and precision. Then, the analytic hierarchy process based on the sum product is used to obtain the risk value of food safety detection data, which is used as the desired output of the LSTM. And the root mean square error of the predicted risk value and the real food risk value is used as the objective function of the IAPSO algorithm to optimize the hyperparameters of the LSTM. Finally, the food safety risk early warning model based on the IAPSO-LSTM is evaluated using the composite seasoning detection data from a food testing agency in Guizhou Province, China. The proposed model effectively identifies high-risk factors affecting the risk value, with sodium cyclamate being the primary high-risk factor. The overall performance of the IAPSO-LSTM model is superior to that of the TPSO-based LSTM, the CPSO-based LSTM, the APSO-based LSTM, the DAPSO-based LSTM and the IAPSO-BP, with the prediction error of 0.474, R2 value of 0.998 and the absolute error less than 5. Moreover, the proposed model can help the relevant government departments effectively warn the potential food safety risks to ensure the food safety. [ABSTRACT FROM AUTHOR]

Accurate and reliable runoff prediction is of great significance to water resources management, disaster monitoring and rational development and utilization of water resources. In this paper, a metaheuristic evolutionary deep learning model based on Temporal Convolutional Network (TCN), Improved Aquila Optimizer (IAO) and Random Forest (RF) is proposed for rainfall-runoff simulation and multi-step runoff prediction. In this study, the influence of various input variables on the prediction accuracy is discussed. First of all, in order to avoid the dimensional disaster problems and reduce the calculation time, RF is used to calculate the correlation between the input variables and the prediction object, and the data with high correlation is selected as the final inputs. Then, the filtered data are sent to the TCN model, and the parameters of the TCN model are optimized using the IAO algorithm, and the final prediction results are obtained. In this study, the rainfall and runoff data of five stations in the middle reaches of Jinsha River, China were selected, and the runoff of Panzhihua station was simulated and predicted by establishing multiple models. By analyzing and comparing the predictive results of several models, it shows that the models and improvements proposed in this study are effective. [ABSTRACT FROM AUTHOR]

Accurate and reliable runoff prediction is of great significance to water resources management, disaster monitoring and rational development and utilization of water resources. In this paper, a metaheuristic evolutionary deep learning model based on Temporal Convolutional Network (TCN), Improved Aquila Optimizer (IAO) and Random Forest (RF) is proposed for rainfall-runoff simulation and multi-step runoff prediction. In this study, the influence of various input variables on the prediction accuracy is discussed. First of all, in order to avoid the dimensional disaster problems and reduce the calculation time, RF is used to calculate the correlation between the input variables and the prediction object, and the data with high correlation is selected as the final inputs. Then, the filtered data are sent to the TCN model, and the parameters of the TCN model are optimized using the IAO algorithm, and the final prediction results are obtained. In this study, the rainfall and runoff data of five stations in the middle reaches of Jinsha River, China were selected, and the runoff of Panzhihua station was simulated and predicted by establishing multiple models. By analyzing and comparing the predictive results of several models, it shows that the models and improvements proposed in this study are effective. [ABSTRACT FROM AUTHOR]

• Construct the uncertain multi-stage nonparametric technologies. • Perform efficiency analysis at each level from national and regional viewpoints. • The number of efficient units and innovation efficiency is higher under nonconvex. • Efficiency of the technology development is higher, especially under nonconvex. As an important role in China's economy, the high-tech industry should evaluate and analyze the innovation activities from a systematic perspective to obtain innovation efficiency, thus improving high-quality development. In fact, for the efficiency assessment system of the high-tech industry, the indicators information is imprecise due to the inherent randomness, measurement error, incomplete information on economic phenomena, etc. However, few studies to date have considered and described the imprecise information. Moreover, data indivisibilities and the economic scale of the high-tech industry cause nonconvex technologies. However, little research has been conducted using the nonconvex measure to estimate innovation efficiency. In this regard, this paper is the first to combine convex and nonconvex technologies with uncertainty theory in a multi-stage system to compare the efficiency of the high-tech industry. More specifically, this paper first divides the innovation activities of the high-tech industry into a technological development stage and an economic transformation stage from the perspective of the innovation value chain. Second, uncertainty theory is adopted to express imprecise information, and uncertain multi-stage nonparametric frontier techniques are constructed to measure the innovation efficiency of the high-tech industry. Third, the high-tech industrial efficiency evaluation based on two-stage nonparametric techniques is established. Empirical results indicate that efficiency in the technology development stage is higher, particularly under nonconvex. Furthermore, the inefficiency of the whole system is mainly due to the inefficiency in the economic transformation under nonconvex, while under convex, the primary reason becomes the joint inefficiency of the two stages. [ABSTRACT FROM AUTHOR]

Exposure to air pollutants has become a major global health threat and is a dominant contributor to increasing respiratory mortality. Accurate projections of respiratory mortality are crucial to mitigating the adverse influences of air pollution on public health and guiding long-term policy implementation. However, the forecasting models' accuracy is difficult to guarantee because seasonal factors perturb the raw series of air pollutants and respiratory mortality. This paper proposes an enhanced seasonal and self-adaptive multivariate grey convolution model to solve this dilemma. The innovations of the proposed model reside in the following areas: firstly, a seasonal operator vector of multidimensional data is initially built to digitize the seasonality of air pollutants and related mortality. Secondly, a multivariate grey convolution model with an adaptive time-lag cumulative optimization item is put forward. The weight coefficients of each driving variable at different periods are intended to adapt dynamically. Thirdly, the self-adaptive time-delay coefficient is determined by the Particle Swarm Algorithm, enhancing the accuracy of predictions. Theoretically, the generalizability and adaptability of the newly presented model are well-validated. Moreover, its practical applicability and higher forecasting performance are further verified in estimating the respiratory mortality attributable to the comprehensive effects of air pollutants in China. [ABSTRACT FROM AUTHOR]

In China, overlapped routes from multiple bus lines are widespread. Some buses are overcrowded while others have few passengers. The goal of this study is to reduce onboard passenger crowding without wasting bus capacity. This paper examines an extended multiple-depot vehicle scheduling problem (VSP) with multiple vehicle types. First, a bi-objective integer programming model was created. The trade-off between operating cost and passenger travel cost was established and the crowding cost due to different vehicle sizes was especially considered. Then, the capacity restraint incremental assignment algorithm and a vehicle scheduling method with multiple vehicle types were developed to find Pareto-optimal solutions that considered vehicle capacity constraints. Finally, the proposed methodology was validated using a real-world transit network in Beijing, China. The optimization results from about 1.18 million bus card swiping records show that our model and solution algorithm can effectively reduce the passenger crowding cost and avoid the waste of transport capacity. [ABSTRACT FROM AUTHOR]

Data Envelopment Analysis (DEA) is used for not only assessing the performance of a set of homogeneous decision-making units (DMUs), but finding the target operating points to improve inefficient DMUs. When inefficient DMUs are far from their target, it will be impossible to reach those in a single move, therefore, a strategy of gradual improvements with intermediate targets has been proposed. In this study, we propose a method to determine benchmarking paths, which consider the improvement steps as the learning of the production functions, not the learning of inputs and outputs. Under the constant returns-to-scale (CRS) assumption, the paper, for each inefficient DMU, sets the ultimate target as the closest target and determines the shortest improvement path with existing DMUs by Dijkstra's algorithm, and this is illustrated with a numerical experiment. As a real-world example, the method is introduced to the irons and steel enterprises in China, so that the specific steps to make efficient ones has been pointed out. The proposed method is the first study to discuss stepwise benchmarking path from the perspective of the production function. • The benchmarking paths are composed of existing DMUs. • The ultimate target is set as the closest efficient DMU. • The inefficient DMU learns the production functions of DMUs. • The distance between two production functions is calculated. • Dijkstra's algorithm is used to find the optimal benchmarking path. [ABSTRACT FROM AUTHOR]

Predicting the stock price is challenging because of its volatility, high dimensions, and complex non-linearity. The multitask learning methods can capture the internal relationship among sub-tasks and obtain better prediction effect than the traditional single-task learning methods. However, most multitask learning methods ignore the inherent distribution of the original samples, which fails at achieving good generalization performance. In this paper, we first present an asymmetric squared ɛ -insensitive loss function, which can improve the generalization ability of the regressor by adjusting the asymmetric parameter. Then, an asymmetric proximal support vector regression (a-PSVR) model is proposed, which greatly improves the flexibility of proximal support vector regression (PSVR). Based on different multitask learning assumptions, two multitask learning asymmetric proximal support vector regression algorithms, i.e., MTL-a-PSVR and EMTL-a-PSVR, are advanced. Both multitask learning algorithms can obtain optimal solutions by solving quadratic programming problems. Additionally, a special case of multitask learning proximal support vector regression (MTL-PSVR) is introduced by analyzing the asymmetric squared ɛ -insensitive loss function. To illustrate the merit of the methods, the proposed models are applied to predict the trends of stock market indices in China and the U.S. and stock prices of four Chinese securities companies. The experimental results demonstrate the significant advantages of the proposed algorithms in prediction effect and generalization performance. • An ɛ -insensitive loss function is presented for asymmetrically distributed data. • The a-PSVR has better prediction performance than proximal support vector regression. • A multitask joint learning model is proposed to perform the stock market forecast. • The cross-relations and asymmetry among stock data were considered simultaneously. [ABSTRACT FROM AUTHOR]

• A deep learning-based prediction framework of temperature control time is proposed. • Designing a historical rolling data processing method based on mean coding. • Designing a feature selection strategy based on maximum information coefficient. • Designing adaptive genetic algorithms to improve the deep neural network. • Experiments demonstrate the proposed prediction framework has the best performance. Accurate prediction of temperature control time is essential to improving the stability of wide-thick slab hot rolling production. However, the historical rolling data have high-dimensional and nonlinear characteristics, and there are complex relationships between the features affecting the temperature control time, which significantly impede modeling performance. To solve these problems and enhance prediction accuracy, this study proposes a prediction framework of temperature control time (PF-TCT). The proposed PF-TCT framework contains data preprocessing, feature selection, and model training. In the data preprocessing stage, considering the uneven distribution of categorical features taking values, a uniform random sampling method is designed to divide the dataset, and mean encoding is used to convert the categorical features into numerical features. In the feature selection stage, considering the interpretability of relationships between static parameters in historical rolling data and the accuracy of identifying redundant features, a selection strategy is designed based on the maximum information coefficient and approximate Markov blanket. In the model training stage, the deep neural network (DNN), which has a strong fitting ability and high flexibility, is used to build the prediction model. To avoid the dependencies between features and uneven sample distribution affecting the performance of the DNN, an adaptive genetic algorithm (AGA) is designed to optimize the DNN. In the AGA, population fitness and genetic iteration effect are considered to endow the selection, crossover, and mutation operators with adaptive learning ability, which can effectively provide good initial settings for the DNN parameters, thereby significantly improving the prediction performance of the PF-TCT. The proposed PF-TCT is verified by numerical experiments on actual data from a large steel group in China. The experimental results show that the data preprocessing and feature selection process in the PF-TCT can effectively improve the performance of the prediction model. Compared with the classical models, the AGA-based DNN proposed in this paper has lower prediction error and better stability and generalization performances. Finally, considering the maximum information coefficient matrix and approximate Markov blanket of features, the feature selection process is further analyzed, and the process knowledge for improving the hot rolling production of wide-thick slabs is discussed. [ABSTRACT FROM AUTHOR]

Promoting the collaborative governance of regional environmental pollution is a key issue of the "14th Five-Year Plan" period of China, which has great significance in accelerating the construction of Chinese ecological civilization. Given this, this paper uses quantum game theory to analyze the interaction between two heterogeneous governments in environmental governance and to discuss the impact of heterogeneity difference of local governments on the game system. As an embodiment of the innovation of this paper, an interpretation of entanglement and quantum strategy under the context of environmental governance is presented, and the impact of the heterogeneity difference between local governments on the quantum game system is studied. The results show that the entanglement can effectively prevent the free-riding behavior of local governments, and the heterogeneity difference does not change the equilibrium of the quantum game. As a byproduct, this paper reveals the control effect of the combination of punishment mechanism and information disclosure mechanism on free-riding behavior to a certain extent. Finally, we construct the "Entanglement Agreement" of regional environmental collaborative governance according to the interpretation of entanglement and quantum strategy. In addition, it is an important guarantee for incentive enthusiasm of local governments to improve their governance capability. This study provides a quantitative basis and decision-making reference for promoting regional collaborative governance in China. The approach used in this paper can also be applied to similar situations in other countries or regions with suitable modifications. • A quantum game model of collaborative governance is constructed. • The impact of local governments' heterogeneity on a game system is studied. • The control effect of the quantum mechanism on free-riding behavior is analyzed. • An interpretation of the quantum mechanism is proposed for realistic application. • An "Entanglement Agreement" is constructed to guide collaborative governance. [ABSTRACT FROM AUTHOR]

• Game method is used in interval cross evaluation. • Build a variety of evaluation strategies to linearize the model. • Using entropy theory to aggregate the results of different evaluation strategies. Cross-efficiency evaluation is an effective method for the ranking of decision-making units (DMUs) in data envelopment analysis, which is the performed method for peer-evaluation and self-evaluation. In most cross-efficiency evaluation methods, the peer evaluation result is completely constrained by the evaluator's optimal self-evaluation weights. DMUs are connected by a competitive relationship; therefore, they can be regarded as players in the game and the cross efficiency value can be regarded as payment because of this competition. DMUs need to consider the impact of their own weights on other DMUs to identify a set of weights for evaluating themselves. Based on the idea of non-cooperative games in the cross evaluation of DMUs, this paper considers the interval cross game efficiency of DMUs with the interval data. The interval data theory is combined, the best production state and the worst production state are taken as reference states, and four evaluation strategy models are proposed according to the opposition and coordination relationship. Then, the bijective and injective interval game cross models, as well as the algorithm corresponding to the four evaluation strategies are constructed. Moreover, the result of the self-evaluation is used as the initial parameter to prove the existence of the solution and the convergence of the algorithm. Based on the priority relationship of the evaluation results under different strategies, the interval entropy method is used to aggregate the results and obtain the final cross efficiency of the interval game. Furthermore, both the applicability and superiority of this model are exemplified by an example. Finally, based on the method of this paper, the efficiency of forest carbon sequestration in China are studied, seven natural regions in China are ranked by forest carbon sequestration efficiency values reasonably, and the current regions development of forest carbon sequestration in China are evaluated. [ABSTRACT FROM AUTHOR]

• Interval extended by TFN is used to determine the 2-tuple weighted vectors. • 2-tuple water-richness evaluation model is built by an extended ITL-VIKOR using TFN. • Model is verified by three dimensional high-density resistivity method. • Water-richness evaluation is extended to binary pattern for the first time. Jiaozuo coalfield is the most typical in Northern China type coalfield. When it mined the Permian coal seams, it was threatened by water inrush from the confined aquifer of thin karst fissure limestone in the lower Carboniferous. How to scientifically evaluate and predict the water-richness of thin karst fissure limestone in Carboniferous system has become the most important work in mine water control and prevention. Taking the mining of coal seam No. 2 1 of Shanxi Formation in Guhanshan coal mine as an example, this paper analyzed the water-richness main controlling factors of L 8 Limestone Aquifer of Taiyuan Formation, and selected four evaluation indexes, i.e. water inflow of drilling, the thickness of L 8 Limestone Aquifer, the water level of L 8 Limestone Aquifer and fault fractal dimension. The 2-tuple linguistic weights of all factors were obtained by the use of interval 2-tuple linguistic method extended by triangular fuzzy numbers. Following the above outlines, the mathematical model for the 2-tuple linguistic evaluation of water-richness was established based on ITL-VIKOR method extended by triangular fuzzy numbers. The data of geophysical exploration were collected to test the accuracy of the model. In addition, the results of 2-tuple linguistic assessment of water-richness and geophysical exploration were used to evaluate the water-richness of L 8 Limestone Aquifer, which extends the evaluation and prediction of water abundance for karst fractured aquifers to dyadic array. These results have been applied to guide the safe mining in Guhanshan coal mine, and will be further extended to the mines with similar geological conditions. It is our goal to establish an intelligent application system to ensure safe production in coal mines, which is great beneficial to the technical personnel engaged in mine water prevention and control. [ABSTRACT FROM AUTHOR]

• An integrated model for sustainable supplier selection. • Considers all three sustainability perspectives simultaneously. • Obtains criteria weights by both subjective and objective methods. • Two types of weights are combined by Deviation Maximization method reasonably. • An improved fuzzy MULTIMOORA method to rank sustainable suppliers. With the increasing awareness of environmental protection and social responsibility, sustainable supplier selection (SSS) has been receiving more and more attention. However, traditional methods for selecting sustainable suppliers suffer from three main drawbacks: (i) Few existing studies have considered criteria weightings that have been determined both subjectively and objectively, reasonably and simultaneously. Moreover, among these limited studies, existing methods for combining weightings that have been calculated both subjectively and objectively provide only a poor degree of differentiation. (ii) Although MULTIMOORA method has high potential to solve the complex SSS problem, few researchers have given it much attention. (iii) The current Reference Point Approach within MULTIMOORA is not comprehensive as it only considers the distance between the alternative and the positive ideal point. Together, these drawbacks result in both inefficiency and ineffectiveness in SSS. This paper proposes a novel fuzzy MULTIMOORA-based method for SSS. The proposed method, firstly, obtains weights by both group Best Worst Method (subjective method) and fuzzy Shannon Entropy Method (objective method), respectively. Then the two types of weights are combined by Deviation Maximization method, reasonably and effectively. Finally, the paper introduces an improved fuzzy MULTIMOORA method to rank alternative suppliers, which considers both the minimum distance from the positive ideal point and the maximum distance from the negative ideal point. The practicability and effectiveness of the proposed method is verified in an illustrative application in Company L, a well-known international forklift truck manufacturer in China. [ABSTRACT FROM AUTHOR]

• The score function is proposed for hesitant Fermatean fuzzy set. • Unify the framework of Regional Green Development Level Evaluation. • Improve MULTIMOORA method is proposed with hesitant Fermatean fuzzy information. • Level Difference Maximization Method to combine subjective and objective weights. • Case study of RGDL is presented to show the potentiality of the developed method. Economic green development has received increase attention. However, the uncertainty decision processes in the development of green economic growth has brought challenges to the evaluation, which leads to the evaluation index system has not yet reached a consensus. In order to solve the above problems, this paper, based on the established and developed regional green development level evaluation (RGDLE) system in existing literature, employed improved MULTIMOORA group decision model under the hesitant fuzzy Fermatean environment (HFFS-MULTIMOORA) and an innovative weighting method to develop the RGDLE process. This evaluation framework describes the complexity of the RGDLE process. The Level Difference Maximization Method to combine the average-based subjective weight-determining method and the Shannon-entropy-based objective weight-determining method is developed to fit RGDLE problems with cognitive complex information. This innovative index system and HFFS-MULTIMOORA method based group decision-making framework is further applied to evaluate the green development level of five provinces and municipalities along the Yangtze River Economic Zone, China. Results showed the optimal green development levels ranking of the five alternative provinces and municipalities of the Yangtze River Economic Zone, China. Moreover, the effectiveness and feasibility of the model framework was verified by robustness and comparative analysis between the existing method. This paper contributes not only to the literature on RGDLE but also to giving decision-makers and researchers inside and outside China valuable inspiration and references for improving the evaluation efficiency and giving policy suggestions. [ABSTRACT FROM AUTHOR]

• A grey seasonal trend support vector machine for energy forecasting is proposed. • The model can efficiently identify the seasonal fluctuations in energy data. • The model is powerful to predict China's energy production. • The predictive performance of the new model is much superior to the benchmarks. This paper proposed a hybrid ensemble forecasting technique that incorporates the merits of the accumulation generation operation (AGO), least-square support vector regression (LSSVR), dummy variable, and time trend item to forecast the seasonal time series characterized by nonlinearity and uncertainty. This proposed framework, a grey seasonal trend least squares support vector machine (GSTLSSVR), can make it easy to add arbitrary seasonality to any feature, which improves model realism significantly. Furthermore, the grid search method and the last block validation are developed to identify the optimal hyperparameter, making it possible for the developed method to capture seasonal and nonlinear patterns of the original data. For illustration and verification, the quarterly petroleum coke production and monthly crude oil production in China are employed to construct diverse competing models, including the seasonal fluctuation grey model (SGM(1,1)), seasonal autoregressive integrated moving average (SARIMA), Holt-Winters (HW), backpropagation neural network (BPNN), a grey seasonal least squares support vector machine (GSLSSVR), long short term memory (LSTM) and LSSVR. The forecasting values of quarterly petroleum coke production are 668.74, 682.68, 679.99, 704.35 for 2019 and 717.59, 734.99, 727.16, 741.53 for 2020, with the lowest MAPEP value (3.7566%). Moreover, the monthly predicted crude oil production for 2019 are 3113.9, 1645, 1562.2, 1625.4, 1599.3, 1619.1, 1627, 1576.9, 1629.6, 1583.6, and 1615.6, while those counterparts for 2020 are 3093.2, 1625, 1547.5, 1621.5, 1610.6, 1644.9, 1662.9, 1615.4, 1667.4, 1615, 1667.4, 1615, and 1640.2, with the lowest MAPEP value (1.0034%). Generally, the empirical results show that the proposed model obtains superior overall performance to other benchmarks in both case studies. Therefore, this proposed model exhibits promising prospects for identifying seasonal patterns in energy production sequences. [ABSTRACT FROM AUTHOR]

Stock price prediction and modeling demonstrate high economic value in the financial market. Due to the non-linearity and volatility of stock prices and the unique nature of financial transactions, it is essential for the prediction method to ensure high prediction performance and interpretability. However, existing methods fail to achieve both the two goals simultaneously. To fill this gap, this paper presents an interpretable intuitionistic fuzzy inference model, dubbed as IIFI. While retaining the prediction accuracy, the interpretable module in IIFI can automatically calculate the feature contribution based on the intuitionistic fuzzy set, which provides high interpretability of the model. Also, most of the existing training algorithms, such as LightGBM, XGBoost, DNN, Stacking, etc, can be embedded in the inference module of our proposed model and achieve better prediction results. The back-test experiment on China's A-share market shows that IIFI achieves superior performance — the stock profitability can be increased by more than 20% over the baseline methods. Meanwhile, interpretable results show that IIFI can effectively distinguish between important and redundant features via rating corresponding scores to each feature. As a byproduct of our interpretable methods, the scores over features can be used to further optimize the investment strategy. • An interpretable fuzzy inference model for stock prediction is proposed. • The proposed model is orthogonal to most of the existing training algorithm. • The contribution of features can be automatically calculated by the model. • The model can render interpretable information for stock prediction result. • The model achieves both high prediction performance and interpretability. [ABSTRACT FROM AUTHOR]

• Develop a complete problem-solving approach for group decision making. • Orient complex large-scale groups and time-sensitive emergency decision scenarios. • Design a feasible mechanism of group consensus strategies under time pressure. • Propose feedback recommendation strategies with a subgroup identification method. • A real case study of China's fight against the COVID-19 epidemic. Group Decision Making (GDM) has been well studied in the last two decades. Yet, two challenges exist: (a) how to resolve large-scale groups in GDM and achieve the consensus of preferences and (b) how to conduct GDM under risk and emergency conditions. In this paper, we develop a complete problem-solving approach for GDM that orients twofold settings of the complex large-scale group and the time-sensitive emergency decision scenarios. The crux of the matter is to design a feasible mechanism of group consensus strategies in the environment of time pressure and natural language preferences. To solve this problem, we propose a closed-loop mechanism of feedback recommendation strategies accompanied with a new subgroup identification method. This mechanism is underlain by a fourfold decomposition of complex large-scale groups, which entails multiple thresholds of group consensus, group hesitation, and time-related iteration of loops. Our mechanism and the whole GDM approach thoroughly orient the most intuitive representation of preferences - human natural language, which can be elicited and quantitatively formulated in probability linguistic preference systems. We illustrate the proposed approach through a real case study of China's fight against the COVID-19 epidemic. We verify that our mechanism can perfectly tradeoff between the effectiveness and the efficiency of complex large-scale GDM under risk and emergency. The results of this research provide proposals for mechanisms on large-scale GDM and are expected to contribute to emergency management such as epidemic controls, anti-terrorism, and other man-made or natural hazards. [ABSTRACT FROM AUTHOR]

• A novel fractional grey Chebyshev polynomial Bernoulli model is proposed. • The structure of the NGBM(1,1,Tn) model is variable. • Comparative study shows that the new model is superior to other five grey models. Accurate mid-to-long term China's renewable energy forecasting is becoming more and more important for integrating renewable energy systems with smart grid and energy strategic planning. For this purpose, this paper proposes a novel fractional structural adaptive grey Chebyshev polynomial Bernoulli model. The new model is based on NGBM(1,1) model to describe nonlinear phenomena. The proposed adjacent accumulation operator can balance old and new information accumulation with less fluctuation. The introduction of the Chebyshev polynomial enables the model to adaptively adjust the structure of the model, which reduces the difficulty of the modeler's operation from the point of view of the expert system. Meanwhile, an improved Grey Wolf optimization algorithm (IGWO) was used to optimize the parameters. Four real cases of renewable energy in China, including production and consumption are used for verification. In addition, Monte Carlo simulation and probability density analysis illustrate the robustness and accuracy of the proposed model. Finally, the development of the four cases in the next 5 years is predicted. [ABSTRACT FROM AUTHOR]

In order to cope with the growing problem of flood disasters, it is crucial to improve the urban flood resilience. Hence, this paper develops a novel evaluation methodology to find the weak links and capacity gaps of urban flood resilience. Firstly, according to the three periods of flood, the urban flood resilience evaluation indicator system is divided into the predictive capacity subsystem before the flood, the absorptive and coping capacity subsystem and the recovery capacity subsystem during the flood, and the adaptive capacity subsystem after the flood. This indicator system also creatively introduces the density of hydrological and meteorological station networks into the predictive capacity subsystem, and divides the adaptive capacity more meticulously into learning capacity at the governmental and individual-society levels. Secondly, a novel three-reference-point (T-R-P) based group ELECTRE III method is proposed to rank the flood resilience of different cities. This method integrates subjective and objective information to obtain more reasonable expert weights, and then sets thresholds with T-R-P to obtain more comprehensive and objective evaluation results. Furthermore, the proposed methodology is applied to six flood-prone cities in China, and its practicality and availability are verified through comparative analysis with other three evaluation methods and sensitivity analysis of the indicator weights. Finally, based on the results, targeted suggestions are made to enhance the flood resilience of the six cities. • A time-based evaluation framework for flood resilience has been established. • Expert weights are determined by integrating heterogeneous information. • A novel three-reference-point based group ELECTRE III method is proposed. • The effectiveness of the proposed method is verified by empirical analysis. [ABSTRACT FROM AUTHOR]

Data envelopment analysis (DEA) is a powerful nonparametric approach for assessing the performance of decision making units (DMUs). Traditional DEA models usually utilize a self-evaluation mode to evaluate DMUs, which have the following shortcomings such as efficiency overestimation and incomplete ranking. As the extension of traditional DEA, cross-efficiency (CE) evaluation remedies these limitations. It connects self-evaluation with peer-evaluation to appraise DMUs and rank them. However, most existing studies on CE evaluation utilize the arithmetic average method to aggregate self-evaluation efficiency and peer-evaluation efficiency, while ignoring the significance of self-efficiency and the irrational psychology of decision-makers (DMs). Observed by the aforementioned phenomena, this paper employs regret theory to portray the regret aversion behavior of DMs and further proposes a novel regret cross-efficiency aggregation (RCEA) method. Considering aggressive and benevolent cross-efficiency models, we apply the RCEA method to calculate the regret-based aggressive cross-efficiency and the regret-based benevolent cross-efficiency, and introduce a parameter reflecting the psychological preference of DMs to aggregate them. To attain consensus between DMUs' expectations for efficiency and the ultimate integration results, we design a regret cross-efficiency adjustment algorithm. This algorithm provides a more acceptable evaluation result and derives a full ranking for all DMUs. Finally, the validity and feasibility of the proposed model are illustrated by evaluating the efficiency of scientific research activities in 13 universities in China. • We develop a novel regret cross-efficiency aggregation method. • Aggregate the regret cross-efficiency in line with DMs' psychological preferences. • A novel regret cross-efficiency ranking model considering consensus is proposed. • The validity of our model is verified by the evaluation of 13 Chinese universities. [ABSTRACT FROM AUTHOR]

Reliable weather forecasting is quite important for sectors with weather-dependent decision-making. To capture unknown and complex dependencies from multiple spatiotemporal factors, i.e., autocorrelated, meteorological causal, meteorological spatial factors, this paper proposes a spatiotemporal feature extraction and fusion network inspired by humans' multi-level cognition process, namely, SFEF-Net, including the data pre-processing stage, transfer pre-training stage, spatiotemporal feature extraction stage, and spatiotemporal feature fusion stage. Specifically, inspired by humans' empirical analysis, the 24 Solar Terms knowledge and Pearson correlation coefficient analysis are utilized to respectively select input timestamps and influencing factors in the first stage. Inspired by humans' associative learning, a Long Short-Term Memory Network (LSTM) layer with powerful remember capability is trained via weather data from multiple neighbored monitoring stations in the second stage, and further is transferred for better feature extraction. Inspired by humans' independent analysis, every factor is separately captured and analyzed via the pre-trained LSTM layer in the third stage, which also coincides with the philosophical idea of divide and conquer. Inspired by humans' comprehensive consideration, extracted features are fused level by level via the attention mechanism with dynamic weights in the fourth stage, which avoids invalid dependencies between multiple features and overfitting. The real-world daily average air temperature forecasting in Shaanxi Province, China is taken to demonstrate the SFEF-Net beyond 12 baseline methods. Additionally, forecasts of drastic change period, ablation analysis, multiple steps, and different stations further present the effectiveness of the SFEF-Net. [ABSTRACT FROM AUTHOR]

Advanced decision support for rail traffic control is significant for enhancing the safety and quality of railway transport service. Data-driven methods have shown powerful learning ability and wide extensibility for prediction, classification, and decision-making problems. In this paper, we propose a hybrid prediction model based on deep forest (DF) ensemble learning to analyze the two common rail traffic control actions, i.e., changing the dwelling times and running times. This basic concept is to mimic the decision-making of rail traffic controllers, providing them with advanced decisions/control actions using data-driven learning algorithms. According to the decision-making approach of rail traffic controllers, the learning process of the model is split into two stages, i.e., learning the type of action (ToA) and the number of changes (NoC) in the dwelling times and running times (i.e., how many dwelling times or running times have been changed compared with the planned ones). The first stage is a classification problem; thus, DF classifier with the synthetic minority oversampling technique (SMOTE) is employed to deal with imbalanced data. In the second stage, the DF regressor treats the NoC in the dwelling and running times as numerical variables and utilizes the information from stage one, i.e., the prediction results of the classification model, to make predictions. The proposed model is calibrated on train operation data from two high-speed railway lines in China. The experimental results and comparative analyses show that the proposed method provides advanced and timely decision support for controllers. These characteristics of the proposed model are imperative for supporting the dynamic decision-making of controllers to manage railway traffic. [ABSTRACT FROM AUTHOR]

• Exploring the interaction of high slope monitoring points based on complex network. • Improving the quantized evaluation of deformation series by topological parameters. • Proposing a complex network-based risk assessment method for high slope projects. With the continuous expansion of infrastructure coverage, construction is gradually shifting to remote mountainous areas, where high slopes are very prone to safety problems, such as landslides and collapses. Existing projects involving high slopes generally avoid engineering accidents by monitoring the deformation at discrete observation points on the slope. However, this approach tends to ignore the interaction between observation points and fails to assess the risk of excessive slope deformation from a systematic perspective. Existing methods rely mainly on the comparison between observed/predicted values and national standards/design requirements, which may lead to risk assessment bias and wrong decisions due to their subjective nature. In this paper, a method based on the analysis of observed data is proposed, by transforming high slope deformation time series into a complex network, which is then used to calculate and determine its network parameters, aiming to analyze the internal topology of the data and assess the potential risk of excessive slope deformation. China's Menghua Coal Transportation Railway was used as an example to verify the effectiveness of the method. The results showed that the method can reveal the systematic characteristics of the interaction between and influence of different observation points on the slope at the macro level and explore the topological characteristics within the deformation time series at the micro level. The relationship between the macroscopic and microscopic network characteristics and the environmental risk distribution across the high slope is established, which can accurately assess the deformation risk of high-slope construction from a systematic perspective and provide theoretical support for risk assessment and safety management in real projects. [ABSTRACT FROM AUTHOR]

• Enhanced linear and nonlinear framework for interval-valued time series is proposed. • Multi-step-ahead forecasting for decomposition-ensemble method is performed. • Multi-factor interval division can mine the internal information of the interval. • Bivariate decomposition algorithm is introduced for multi-scale modeling. • The proposed model outperforms other state-of-the-art methods. To forecast possible air pollution risks, a large number of models have been built to predict the daily average or hourly value of PM 2.5 concentrations. In fact, due to the complexity of PM 2.5 formation and the diversity of its influencing factors, PM 2.5 concentrations may fluctuate greatly during a certain period, single-valued methods cannot present this uncertainty and variability. Therefore, this paper develops a hybrid modeling framework that combines the elastic net (EN) and multivariate relevance vector machine (MVRVM) for interval-valued PM 2.5 time series (IPMTS) forecasting. Following the philosophy of the "linear and nonlinear" modeling framework, the EN and MVRVM are applied to capture the linear and nonlinear patterns hidden in the IPMTS. Different from existing studies that directly model linear and nonlinear patterns of time series, we introduce the multi-factor interval division (MFID) strategy and bivariate empirical mode decomposition (BEMD) algorithm into linear and nonlinear pattern modeling, respectively. This enhanced linear and nonlinear framework (termed MFID-EN-BEMD-MVRVM) can consider the possible linear relationship between PM 2.5 and its related factors within the intervals and model the nonlinear pattern of IPMTS at multiple scales. The IPMTS extracted from four municipalities in China are used to validate the efficiency of the proposed model. Experimental results show that the MFID-EN-BEMD-MVRVM model achieves better forecasting performance than some benchmarks and state-of-the-art models in terms of comprehensive evaluation criteria. In addition, from the application analysis, the proposed interval-valued PM 2.5 modeling architecture has the possibility of real-time forecasting. [ABSTRACT FROM AUTHOR]

• A ST-Random Forest is proposed to predict flight delays. • The new method guaranties the influence of the air traffic network. • The spatial–temporal effect of the airport is considered. • The proposed ST-Random Forest model outperforms the benchmark models. In this paper, we propose a novel prediction framework (ST-Random Forest) for flight delay prediction from temporal and spatial perspective. We first apply complex network theory to extract the spatial feature of the aviation network at edge-, node-, and network-level. Furthermore, considering the temporal correlation of weather condition and airport crowdedness on flight delays, we create a prediction framework based on LSTM units to extract the temporal property of crowdedness and weather condition. Finally, we use the factors (e.g., spatial, temporal and extrinsic) that affect flight delays as inputs and apply Random Forest as classifier to predict flight delays. We apply and test our approach in a case study at China domestic flights between Jun and Aug 2016; after evaluation, we find that the accuracy of our proposed model reaches 92.39%. For the on-time samples, approximately 86% are correct identified; for the delayed samples, the classification accuracy reaches 95%. The ST-Random Forest model contributes to aviation authorities and airport regulators by creating real-time monitoring and high accuracy prediction system to alleviate flight delays and providing insightful suggestions to develop effective air traffic control strategies. [ABSTRACT FROM AUTHOR]

• A deep learning COVID-19 diagnostic system is developed using state-of-the-art deep learning architectures. • A detailed analysis of different methods used for detecting COVID-19 is presented in this paper. • Chest X-rays from different sources are collected to build a robust classification model. • The developed diagnostic model provided efficient results, even with a limited number of input images. • The results produced in this work are validated by an expert radiologist. In recent months, a novel virus named Coronavirus has emerged to become a pandemic. The virus is spreading not only humans, but it is also affecting animals. First ever case of Coronavirus was registered in city of Wuhan, Hubei province of China on 31st of December in 2019. Coronavirus infected patients display very similar symptoms like pneumonia, and it attacks the respiratory organs of the body, causing difficulty in breathing. The disease is diagnosed using a Real-Time Reverse Transcriptase Polymerase Chain reaction (RT-PCR) kit and requires time in the laboratory to confirm the presence of the virus. Due to insufficient availability of the kits, the suspected patients cannot be treated in time, which in turn increases the chance of spreading the disease. To overcome this solution, radiologists observed the changes appearing in the radiological images such as X-ray and CT scans. Using deep learning algorithms, the suspected patients' X-ray or Computed Tomography (CT) scan can differentiate between the healthy person and the patient affected by Coronavirus. In this paper, popular deep learning architectures are used to develop a Coronavirus diagnostic systems. The architectures used in this paper are VGG16, DenseNet121, Xception, NASNet, and EfficientNet. Multiclass classification is performed in this paper. The classes considered are COVID-19 positive patients, normal patients, and other class. In other class, chest X-ray images of pneumonia, influenza, and other illnesses related to the chest region are included. The accuracies obtained for VGG16, DenseNet121, Xception, NASNet, and EfficientNet are 79.01%, 89.96%, 88.03%, 85.03% and 93.48% respectively. The need for deep learning with radiologic images is necessary for this critical condition as this will provide a second opinion to the radiologists fast and accurately. These deep learning Coronavirus detection systems can also be useful in the regions where expert physicians and well-equipped clinics are not easily accessible. [ABSTRACT FROM AUTHOR]

• This paper studies the competition effect of product recommendation networks. • Three network attributes, centrality, connection , and scale are measured. • Their impacts on market competition in a homogeneous product market are tested at the global-network level. • A panel data of 320,981 package tour products was used to estimate the model. • Empirical results confirm the effect of three attributes on market competition. Extant studies have focused on the sales benefits of product recommendation networks; however, the competition effects of such networks have been overlooked. Understanding the competition effects of product recommendation networks is important within an e-commerce platform because maintaining a proper level of competition is critical to the platform ecosystems. This research adopts a data-driven approach and social network analysis, elaborating upon three structural properties of recommendation networks – centrality, connection, and scale – and operationalizes them as e venness of distribution, clustering of structure, and network size at the global-network level. The competition effects of the three proposed network variables were tested based on a daily panel dataset of 320,981 package tour products from Tuniu.com , a top travel service platform in China featuring homogeneous products. Empirical results confirmed that the three proposed structural network properties increase market competition in recommendation networks of homogeneous products. This research contributes to our understanding of the impact of recommendation networks on market competition in the context of homogeneous product markets and offers practical implications of substition recommendation for platform governance. Platform operators can leverage product recommendation networks to alleviate market competition and encourage the entry of sellers with new, innovative products that contribute to the e-commerce platform ecosystems. [ABSTRACT FROM AUTHOR]

Waste sorting is an imperative and significant issue in China, of which sorted-waste collection and transportation are indispensable parts. Despite its vital yet practical significance, few studies research mathematical models or algorithms of waste collection and transportation from the perspective of waste sorting. To address this issue, we extend a novel transportation model for the waste management system, namely, capacitated location routing problem with queuing time (CLRPQT) and design a cross-entropy and simulated-annealing based hyper-heuristic algorithm (CE-SAHH) for it. The main idea of this paper is three-fold: (1) As a particular property of this problem, source nodes cannot but need to be served by more than one vehicle that causes queuing time between a heterogeneous fleet of vehicles, which is novel in terms of the proposed model; (2) For the methodological contribution, a character encoding scheme, new decoding procedure, and local search strategy are designed embedded in the proposed method; (3) An integration of simulated annealing strategy and the cross-entropy-based hyper-heuristic algorithm is developed to overcome the combinatorial optimization problem with a more complex solution of this study. Finally, the results and analysis of three numeric experiments on benchmark datasets, new instances of CLRPQT, and simulation data in Shanghai, China, verify the effectiveness and universality of the proposed model and method. • A novel model with interactional routes for sorted-waste transportation is proposed. • A cross-entropy-based hyper-heuristic algorithm is proposed and performs well. • The novel model and method based on sorted waste enrich the waste management system. • Real-life data is used to verify the method and some managerial insights are drawn. [ABSTRACT FROM AUTHOR]

• An anomaly detection method is developed for the records of UEBMI. • A combination method is utilized to preprocess the experimental data. • A feature selection method involves two aspects, variance and similarity. • An extended OCSVM model is established to improve the model performance. • Interesting findings provide some guideline for the future research and practical issues. Detecting and preventing unusual claims behavior in medical insurance can reduce the drawdown of a group medical insurance pool. Taking the case of the urban employee basic medical insurance (UEBMI) in China, this paper develops a method to detect unusual medical claim patterns in the UEBMI. We collect public domain records involving gastric malignancy as the experimental sample. A method to preprocess the experimental sample for data learning is provided. We present a feature selection method, involving variance analysis and similarity analysis, to determine the core features. Next, we establish an extended one-class support vector machine (OCSVM) model, the kernel density estimation (KDE)-OCSVM, which exploits the Kullback-Leibler divergence and the KDE method to estimate the parameter v of the OCSVM model, to improve model performance. An experiment and two analyses are performed to validate the proposed method. [ABSTRACT FROM AUTHOR]

• Propose the concept of linguistic Pythagorean hesitant fuzzy set (LPHFS). • The weight determining models for expert panel and criteria set under the LPHF environment are derived, respectively. • Put forward the linguistic Pythagorean hesitant fuzzy MULTIMOORA method and construct a multi-criteria decision-making framework. • A practical case of 3PRL provider selection for electric vehicle power battery recycling in China is given. Electric vehicle power battery recycling (EVPBR) is an effective way to utilize resources and reduce environmental damage. In order to ensure the safety and efficiency of electric vehicle batteries (EVBs) reuse and remanufacture, many EVB manufacturers are seeking cooperation with third-party reverse logistics (3PRL) providers to conduct the pre-treatment and transportation of post-used batteries. However, the selection of 3PRL provider is a matter of complex multi-criteria decision-making (MCDM) affected by numerous associated factors. The goal of this paper is to present a linguistic Pythagorean hesitant fuzzy MULTIMOORA method to investigate the selection of 3PRL providers for EVPBR. Firstly, given that the complexity of evaluation information, the linguistic Pythagorean hesitant fuzzy set (LPHFS) is defined in detail. On the basis of new evaluation representation tool, the weight determining models for expert panel and criteria set based on correlation consensus degrees and maximum deviation are derived, respectively. Then a MULTIMOORA method under the linguistic Pythagorean hesitant fuzzy environment is constructed. Later, the evaluation criteria system for the provider capability analysis is set up, and the proposed MCDM approach is applied to select the most suitable 3PRL provider for EVPBR in China. Finally, the sensitivity and comparative analysis results justify the robustness and feasibility of the proposed method. [ABSTRACT FROM AUTHOR]

• A spatial-temporal density-based clustering algorithm is proposed for trip end detection. • Three scenario optimization models are applied to improve the method capability. • A smartphone application is developed for GNSS data collection. • The potential of the method is demonstrated by comparing results with travel log. As a widespread portable probe, smartphone equipped with Global Navigation Satellite System (GNSS) can continuously track individual's travel trajectory, it is potential for trip end information identification. Existing studies mostly use rule-based methods with specific dwelling time and distance thresholds for trip end detection, these methods are highly dependent on expert experience and lack universality across different traffic environments. Some density-based spatial clustering methods also have issues in the case of GNSS signal missing, traffic congestion, short-time stays and repeat visits to the same place etc. Therefore, this paper proposes a two-step method for trip end identification by using smartphone GNSS positioning data. First, a spatial-temporal density-based clustering algorithm (ST-DBCA) is proposed for trip end identification, the method considers both spatial and temporal travel trajectory point density at the same time, and performs much better than traditional clustering methods. Second, three optimization models are further proposed to optimize the identification results, including 1) a short time stay optimization model, 2) a redundant stay optimization model, and 3) a traffic congestion stay optimization model. Field tests in Chengdu China are conducted to verify the feasibility and effectiveness of the proposed methods. Results show that the average trip end identification accuracy under different trip purposes reaches 92.8%, and the average errors of arrival and departure time are smaller than 150 s. [ABSTRACT FROM AUTHOR]