Search

• Propose an innovative Bayesian model to control the risk of COVID-19 patients. • Propose two indicators to verify the feasibility and effectiveness of the model. • Provide the tool for risk assessment in the field of epidemics. In the context of the outbreak of coronavirus disease (COVID-19), this paper proposes an innovative and systematic decision support model based on Bayesian networks (BNs) to identify and control the risk of COVID-19 patients spreading the virus, which requires the following three steps. First, by consulting the related literature and combining this with expert knowledge, we identify and classify the characteristics (risk factors) of COVID-19 and obtain a conceptual framework for COVID-19 Risk Assessment Bayesian Networks (CRABNs). Second, data on COVID-19 patients with expert scoring results on patient risk levels were collected from hospitals in Hubei Province of China and are used as the training set, and the structure and parameters of the CRABNs model are obtained through machine learning. Finally, we propose two indicators, namely, Model Bias and Model Accuracy, and use the remaining data to verify the feasibility and effectiveness of the CRABNs model to ensure that there are no significant differences between the predicted results of the model and the actual results provided by experts who have relevant experience in treating COVID-19. At the same time, we compared the CRABNs model with the support vector machine (SVM), random forest (RF), and k-nearest neighbour (KNN) models through four indicators: accuracy, sensitivity, specificity, and F-score. The results suggest the reliability of the model and show that it has promising application potential. The proposed model can be used globally by doctors in hospitals as a decision support tool to improve the accuracy of assessing the severity of COVID-19 symptoms in patients. Furthermore, with the further improvement of the model in the future, it can be used for risk assessments in the field of epidemics. [ABSTRACT FROM AUTHOR]

Natural gas, an efficient, eco-friendly and clean green energy, has become one of the important energy structures of various countries in the world, accurately predicting the production of natural gas can help the national energy agency solve "gas shortage" problem. To accurately predict natural gas production in China, this paper establishes an optimized grey system model with weighted fractional accumulation generation operation (abbreviated as WFNGBM(1,1,N)). The proposed model has all the advantages of the GMP(1,1,N) model, NGBM(1,1) model and weighted fractional accumulation generation operation, which makes it have excellent prediction performance. Moreover, five outstanding intelligent optimization algorithms (whale optimization algorithm, marine predators algorithm, grasshopper optimization algorithm, equilibrium optimization algorithm and arithmetic optimization algorithm) are used to solve the hyperparameters of the WFNGBM(1,1,N) model. It is found that the WFNGBM(1,1,N) model has the characteristics of convertibility and small sample modeling, which indicates that it is a small sample prediction model with strong compatibility. After confirming the feasibility of the proposed model compared with its competing models by using natural gas production in Germany, Italy and Canada as examples, the proposed model is used to study China's natural gas production. The results show that this model is very suitable for predicting and analyzing natural gas production in China. Based on this, the WFNGBM(1,1,N) model is used to estimate China's natural gas production in the next three years, and some reasonable suggestions are given according to the development trend of natural gas production. • The concept of weighted fractional accumulation generation operation is given. • An optimized nonlinear grey Bernoulli prediction model is established. • Five algorithms are used to solve the parameters of the proposed model. • The proposed model is used to study natural gas production in China. [ABSTRACT FROM AUTHOR]

Water quality assessment analysis is an important technical means for water pollution prevention and control. In this research area, mechanism models and real observation data of water quality evolution are always used to perform water quality assessment. However, the existing water quality evolution mechanism modeling researches commonly use a single time-invariant model to model the water quality evolution process. It is inappropriate to directly describe the complex behavior of long-term water quality evolution with the existing models, since the evolution process contain different feature states, and the water quality evolution characteristics under these states are different. In addition, the existing water quality assessment methods are mostly methods for directly processing and calculating the observation data of water quality. This makes the existing methods difficult to effectively compensate for the contingency and randomness in the water quality evolution process, which leads to deviations and errors in performing the water quality assessment. Considering these deficiencies, this paper proposes a water quality evolution mechanism modeling and health risk assessment method based on stochastic hybrid dynamic systems (SHDS). Firstly, a hybrid water quality evolution mechanism (H-WQEM) model is established based on SHDS, and a hybrid improved fruit fly optimization algorithm (H-IFFOA) is proposed to identify the unknown parameters of the H-WQEM model. Then, an improved interacting multiple model extended Kalman filter algorithm (IIMM-EKF) is employed to estimate the probability distribution of the hybrid state of the H-WQEM model, including the probability distribution of different feature states of water bodies and the probability distribution of water quality indexes under these states. Finally, the health degree of water quality is proposed as an indicator to achieve a quantitative assessment of the water health risk status. Real observation data from a monitoring station at Baiyangwan in China is used to validate the effectiveness of the proposed method. The results show that the method can effectively describe the complex water quality evolution process, and reasonably assess the water quality health risk status. • Stochastic hybrid dynamic systems are used to model water quality evolution. • Improved fruit fly optimization algorithm is proposed to identify the model parameters. • Improved interacting multiple model filter algorithm is proposed to estimate hybrid state. • Health degree of water quality is established to achieve health risk assessment. [ABSTRACT FROM AUTHOR]

• The industrial chain information is introduced to improve the stock forecast results. • DM test was carried out on the results, conclusion was statistically supported. • An interpreter based on LIME algorithm is constructed to explain the results. • The investment strategy is constructed, and the yield of maturity exceeds that of the buy-and-hold strategy. The prediction of stock price has always been a main challenge. The time series of stock price tends to exhibit very strong nonlinear characteristics. In recent years, with the rapid development of deep learning, the ability to automatically extract nonlinear features has significantly attracted scholars' attention. However, the majority of the relevant studies have concentrated on prediction of the changes of stock market based on the data of the specific stock (e.g., transaction data, financial data, etc.), while those studies ignored the interaction between stocks of different industries, especially the interaction between the stocks of upstream enterprises and downstream enterprises in the industrial chain. This paper aims to propose a combination of transfer learning of industrial chain information and deep learning models, including multilayer perceptron (MLP), recurrent neural network (RNN), long short-term memory (LSTM), and gated recurrent unit (GRU), for stock market prediction. These models are used to predict the trend of the 379 stock market indices by industry in China, and the DM test was employed for validation of the prediction results. It can be concluded that RNNs are not necessarily such an optimal choice for the prediction when dealing with specific time series data, and it could be justified by using the local interpretable model-agnostic explanations (LIME) algorithm. Hence, the MLP was selected to effectively improve the accuracy of the prediction of the stock market indices based on the transfer learning of industrial chain information. The investment strategy is constructed according to the prediction results, and the yield of maturity exceeds that of the buy-and-hold strategy. [ABSTRACT FROM AUTHOR]

• A new multi-classification assessment model of bank personal credit is proposed. • The D-S evidence theory is used to integrate six different base classifier advantage. • The new model has higher accuracy and stronger universality than other classifiers. There have been many studies on machine learning and data mining algorithms to improve the effect of credit risk assessment. However, there are few methods that can meet its universal and efficient characteristics. This paper proposes a new multi-classification assessment model of personal credit risk based on the theory of information fusion (MIFCA) by using six machine learning algorithms. The MIFCA model can simultaneously integrate the advantages of multiple classifiers and reduce the interference of uncertain information. In order to verify the MIFCA model, dataset collected from a real data set of commercial bank in China. Experimental results show that MIFCA model has two outstanding points in various assessment criteria. One is that it has higher accuracy for multi-classification assessment, and the other is that it is suitable for various risk assessments and has universal applicability. In addition, the results of this research can also provide references for banks and other financial institutions to strengthen their risk prevention and control capabilities, improve their credit risk identification capabilities, and avoid financial losses. [ABSTRACT FROM AUTHOR]

Corporate financial distress prediction research has been ongoing for more than half a century, during which many models have emerged, among which ensemble learning algorithms are the most accurate. Most of the state-of-the-art methods of recent years are based on gradient boosted decision trees. However, most of them do not consider using feature importance for feature selection, and a few of them use the feature importance method with bias, which may not reflect the true importance of features. To solve this problem, a heuristic algorithm based on permutation importance (PIMP) is proposed to modify the biased feature importance measure in this paper. This method ranks and filters the features used by machine learning models, which not only improves accuracy but also makes the results more interpretable. Based on financial data from 4,167 listed companies in China between 2001 and 2019, the experiment shows that compared with using the random forest (RF) wrapper method alone, the bias in feature importance is indeed corrected by combining the PIMP method. After the redundant features are removed, the performance of most machine learning models is improved. The PIMP method is a promising addition to the existing financial distress prediction methods. Moreover, compared with traditional statistical learning models and other machine learning models, the proposed PIMP-XGBoost offers higher prediction accuracy and clearer interpretation, making it suitable for commercial use. • The model Combines a corrected feature selection measure and XGBoost. • Permutation importance can correct the bias of feature importance. • The model is validated on Chinese listed companies datasets over five metrics. • The model is proved to outperform several benchmark techniques. • The feature importance and partial dependence plot enhance model interpretation. [ABSTRACT FROM AUTHOR]

• The method is based on the Bayesian theory and thrice-standard-error principle. • The method can better account for the data fluctuation and deduce the results. • Disrupted roads, detour roads, and congestion roads can be accurately determined. • GPS data make the estimation of disruption more quickly and the coverage wider. Incidents, such as natural disasters, public events, and holidays, often cause problems to highways, even paralyze the operation of the whole networks, leading to a serious threat to travel efficiency and safety of the public. To provide better transport management and plans for emergencies, it is important to quickly and accurately identify such incidents and estimate their disruptive effects on the networks. To this end, a novel approach has been proposed in this paper, which is based on the Bayesian theory and thrice-standard-error principle while utilizing vehicle GPS data. Two important indicators, including traffic flows and congestion indexes, along with their change ratios, are built to detect the incidents and evaluate the extent of the disruption. The specific disrupted and detour roads are further determined. The proposed method has been tested using two real-world events in China, and the potential and effectiveness of this technique are demonstrated. With more and more vehicles being equipped with GPS devices worldwide, the designed method can be easily transferable to other countries, paving a way for the adoption of the approach for a more spatial–temporal sensitive highway network disruption analysis method that supports the establishment of a more resilient transport system for emergencies. [ABSTRACT FROM AUTHOR]

• European option datasets were time-sequenced by maturity to extract time information. • Two deep learning models were built for the option pricing tasks. • Our models can price option accurately without volatility calibration and simulation. • An interpretable method was used to find how models improved the pricing results. • Accumulate local effect range method was proposed to get feature emphasis of models. In this paper, we investigated the feasibility of pricing European options with time-sequencing data processing method and deep learning models, based on two European options, the ETF50 options of China and the S&P 500 options of America. Four competing models were built to verify the improvement of the 1D-CNN and LSTM models on the option pricing task. Methods like cross-validations and statistical tests were also used to make our experiments more robust. Besides, in order to increase the stability and the interpretability of our pricing models, we selected the ALE method to interpret and analyze the behavior of the deep learning models. The empirical results indicate that, in both ETF50 option and S&P500 option pricing tasks, the 1D-CNN and LSTM models had significant advantages in forecasting accuracy and robustness under moneyness, trading date or maturity dimension irrespectively. Especially for the LSTM model, which has robust performance using different kinds of cross-validation methods. With the help of ALE method, we proved that the improved performance brought by the 1D-CNN and LSTM models could be attributed to their capability of capturing time-series information and their different emphasis on input features and lags. [ABSTRACT FROM AUTHOR]

At present, integrating investor sentiment into the prediction of stock market crisis has attracted more and more attention. However, the existing researches only considered the impact of the market indicators and the micro investor sentiment on stock market, while ignored the impact of the macro one. Therefore, in this paper, we develop an early warning system for predicting stock market crisis via market indicators and mixed frequency investor sentiments. The proposed early warning system consists of five components, which includes the construction of mixed frequency investor sentiments that consider both macro and micro investor sentiments, the identification of stock market crisis, the determination of the forecast horizon using Ensemble Empirical Mode Decomposition (EEMD), the definition of the early warning signal, and the building of prediction model using artificial neural network (ANN). Lastly, we apply the developed warning system to China's stock markets. Experimental results show that mixed frequency investor sentiments can improve the early warning ability in predicting the stock market crisis, and the ANN model has better performance than other methods including Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), K-Nearest Neighbor (KNN), and Logistic Regression (LR). • Combine investor sentiment to predict stock market crisis. • Construct the mixed frequency investor sentiments. • Extensive experimental results verify the effectiveness of constructed sentiments. [ABSTRACT FROM AUTHOR]

• Novel grey forecasting model called the neural ordinary differential grey model (NODGM) is proposed. • NODGM can be learned through a training procedure. • NODGM has a wider application range and can learn the characteristics of different data samples. • The predicting sequence is obtained by using the Runge–Kutta method to solve the model. Due to the efficiency of grey models in predicting the time series of small samples, grey system theory has been well studied since it was first proposed and has now become an important method for small sample prediction. Inspired by the neural ordinary differential equations (NODE), this paper proposes a novel grey forecasting model called the neural ordinary differential grey model (NODGM). The NODGM model includes a novel whitening equation that allows the prediction model to be learned through a training procedure. Therefore, compared with other models whose structures and terms need to be artificially predefined based on the laws of real samples, the NODGM model has a wider application range and can learn the characteristics of different data samples. Then, to obtain a model with better prediction performance, we apply NODE to train the model. Finally, the predicting sequence is obtained by using the Runge–Kutta method to solve the model. In the experiments, we apply NODGM model to two energy samples and then contrast the experimental results with the results of some classical grey models to validate the effectiveness of NODGM model. The comparison results from predicting China's annual crude oil consumption and forecasting oilfield production in northern China show that the prediction accuracies achieved by NODGM model are 28% and 8% higher, respectively, than those achieved by the state-of-the-art grey forecasting models. [ABSTRACT FROM AUTHOR]

• It proposes a hybrid multi-period network structure with feedback. • It provides an unbiased evaluation under the cooperation hypothesis. • A binary heuristic algorithm is proposed to obtain the optimal efficiency. • It is empirically supported by using the 5-year ecological data of China. Decision-making unit (DMU) internal structure simulation is the basis for network Data Envelopment Analysis (DEA) to open "black box" and evaluate system efficiency with complex internal structure. Based upon summarizing and analyzing the existing model assumptions in network DEA, this paper proposes a hybrid multi-period DEA model with feedback to open the internal structure of the DMU system, as well as to provide horizontal comparison of the efficiency change of a same DMU at different time periods. In the model construction, the global production frontier is used for multi-period evaluation, Chebyshev distance is used to construct an unbiased two-stage model. Under the cooperation hypothesis, it is considered that the two stages are equally important, which solves the defect that the current two-stage method is not unique in its optimal solution and has two-stage contribution bias. A binary heuristic algorithm is proposed to reduce the time complexity of model solving while maintaining relatively high accuracy. The correctness and feasibility of the algorithm are demonstrated through the investigation of the relevant properties. Finally, the 5-year ecological data of China is used for illustrative application, providing suggestions for future environmental governance. Several comparative experiments are conducted to demonstrate the advantages of our proposed model. [ABSTRACT FROM AUTHOR]

• A network closest target model for a two-stage system is built. • A closest target frontier projection is obtained. • Efficient stages are used for the closest target for an inefficient DMU. • A case of 16 leading commercial banks in China is analyzed. Traditional data envelopment analysis (DEA) models mainly set the furthest targets as the frontier projection for inefficient decision-making units (DMUs). To achieve the efficient status with less effort, the closest target models are introduced which projected the least input/output improvement for inefficient DMUs. However, these works typically consider each DMU as a "black box" in the closest target setting, and thus these models cannot be directly extended to a system with network structure because there may be no efficient DMU for reference. This paper fills the gap by developing a closest target model for a two-stage system. Instead of constructing the efficient frontier only by the system efficient DMUs in the "black box" system, all the extreme efficient stages of the DMUs are considered to form the closest target for an inefficient DMU. Using our network closest target (NCT) model, a case of the 16 leading commercial banks in China is analyzed. The results show that these commercial banks performed steadily in both efficiency and input/output required improvement during the study period. Moreover, compared with the network furthest target (NFT) model, NCT requires each DMU less improvement on inputs/outputs, and usually obtain the higher efficiency. That is, NCT is more feasible, economical and optimistic. Lastly, we discuss the proportion of each dominating peer referred by the inefficient banks and the importance of these peers is ranked accordingly. [ABSTRACT FROM AUTHOR]