Search

The classification of hazard is critical in industrial informatics, as it enhances early safety alerts, supports decision-making, and facilitates policy assessment. However, previous studies have generally neglected the temporal attributes of hazards, thereby constraining the effectiveness of models. This paper introduces a new model for hazard classification termed DLGM. DLGM represents a deep learning framework, with the structural parameters of grey models to encapsulate the hazard temporal attributes. To better accommodate the fluctuations of hazard series, a new grey model termed FSGM(1,1) equipped with Fourier series is proposed. Moreover, DLGM leverages a novel hierarchical feature fusion neural network (HFFNN) to optimize feature processing. Extensive experiments across three hazard themes involving 18 large-scale industrial processes have demonstrated the competitiveness of DLGM (e.g., it surpasses benchmark models such as Random Forest and BERT by approximately 2% in both accuracy and F1), the suitability of FSGM(1,1) (e.g., its mean absolute percentage error is less than 10% and mean squared error is below 0.02) and the effectiveness of HFFNN (e.g., it enhances the accuracy and F1 of DLGM by about 1%). [ABSTRACT FROM AUTHOR]

Fractional Grey Lotka-Volterra Model with variable order is introduced and used for modeling the transaction counts of three cryptocurrencies namely Bitcoin, Litecoin and Ripple. Bitcoin and Litecoin then both three cryptocurrencies transaction counts are modeled in 2 and 3-dimensional framework respectively. Dataset include transaction counts of cryptocurrencies of interest. The 2-dimensional model uses Bitcoin and Litecoin transactions from April, 28, 2013 to February, 10, 2018. The 3-dimensional model uses transactions from August, 7, 2013 to February, 10, 2018. The actual values and the model values of n-dimensional model n = { 2 , 3 } are displayed. The Mean Absolute Percentage Error (MAPE) suggests a high accuracy of the 3-dimensional Variable-order Fractional Lotka-Volterra model (VFGLVM) for the overall model values of Bitcoin and a reasonable accuracy for both model values of Litecoin and Ripple. The 2-dimensional VFGLVM has a good accuracy for the overall forecasting values of Bitcoin and a reasonable accuracy for the forecasting values of Litecoin. By analysing values of Lyapunov exponents and patterns of the corresponding Lotka-Volterra models, the 2 and 3-dimensional models show a chaotic behavior. Forecasting values indicate a future slight linear increase in transacting Bitcoin and a future decreasing transaction of Litecoin and Ripple. Bitcoin will keep relatively higher transaction counts and Litecoin transaction counts will be everywhere higher than that of Ripple. [ABSTRACT FROM AUTHOR]

Interbank Offered rate is the only direct market rate in China’s currency market. Volatility forecasting of China Interbank Offered Rate (IBOR) has a very important theoretical and practical significance for financial asset pricing and financial risk measure or management. However, IBOR is a dynamics and non-steady time series whose developmental changes have stronger random fluctuation, so it is difficult to forecast the volatility of IBOR. This paper offers a hybrid algorithm using grey model and extreme learning machine (ELM) to forecast volatility of IBOR. The proposed algorithm is composed of three phases. In the first, grey model is used to deal with the original IBOR time series by accumulated generating operation (AGO) and weaken the stochastic volatility in original series. And then, a forecasting model is founded by using ELM to analyze the new IBOR series. Lastly, the predictive value of the original IBOR series can be obtained by inverse accumulated generating operation (IAGO). The new model is applied to forecasting Interbank Offered Rate of China. Compared with the forecasting results of BP and classical ELM, the new model is more efficient to forecasting short- and middle-term volatility of IBOR. [ABSTRACT FROM AUTHOR]

Community group buying is the preferred shopping method for many consumers during the COVID-19 epidemic in China. This new Internet pre-sale mode has a lead- lag effect and non-linear characteristics. Therefore, studying the prediction of community group buying has practical significance. In this paper, the lead-lag term of vector autoregressive model is coupled with the nonlinear term in the GM (1, 1, t α ) model. Then, lead-lag factor τ and nonlinear factor t μ are added in the grey modelling process, and a novel hybrid grey forecasting model of lead-lag and nonlinearity (GAPM) is established by means of optimising the background value. Firstly, the least squares method and derivation method are used to obtain the model parameter values and time response expressions, and the stability of GAPM is studied on the basis of condition number theory of matrices. Secondly, the grey evolutionary algorithm is introduced to obtain the optimal solution of the background value and nonlinear factor, and the weighted geometric average weakening buffer operator is used to preprocess the original data. Finally, the new model is used to fit and predict the daily sales of Orange Optimization Company in Wuhan, China for two consecutive months of community group buying. Results show that the model has good stability and high prediction accuracy. Compared with the other five common grey models that do not consider the lead-lag influence of the system, GAPM has better predictive ability. Therefore, the introduction of the new model constructed by using the lead-lag factor is reasonable and effective in the case of community group buying with lead-lag effect. • On the basis of the characteristics of community group buying, a new lead-lag grey prediction model (GAPM) is proposed. • The stability of GAPM is examined on the basis of condition number theory of matrices. • The WGAWB operator and the GPE algorithm are employed to process raw data and optimize model parameters. • GAPM is used to fit and predict the daily sales of Orange Optimization Company in Wuhan, China for two consecutive months of community group buying. [ABSTRACT FROM AUTHOR]

Many fractional-order grey models are proposed and discussed for electric power generation data analysis, which are helpful in enterprise production and policy scheduling. Considering that time-delay is a universal phenomenon in real life and engineering application, a new and comprehensive conformable fractional grey time-delay model is established by extending classical grey models with the forms of conformable fractional derivative, conformable fractional accumulation and delay parameters. Considering delay data is always unknown, Lagrange interpolation is used to estimate the time-delay data. Compared with linear estimation, high order Lagrange interpolation will provide more detail information in the fitting stage. Furthermore, the optimal and modified models are also disused for predicting the future power generation by the tested data in this paper. The errors between the simulated and real data were analyzed and predicted by autoregression model, which is good at revealing the inner trend for historical residuals. The accuracies of modeling and forecasting can be improved by the optimization algorithm and autoregression error estimation in this paper. The results show the optimal and modified models could be widely used in forecasting electrical time series data, which has high effectiveness and flexibility. The novel model could enrich the connotation of parameters and the physical significance of the traditional fractional grey model. [ABSTRACT FROM AUTHOR]

Carbon dioxide is the crucial factor leading to global warming, which has brought great negative effects on economic development and human life. Accurate prediction of carbon dioxide emissions is of great significance for the evaluation of China's current low-carbon environmental protection policy. However, the traditional forecasting models only consider the regularity of historical data, and seldom consider the addition of new information on the development trend. Then, this paper proposes a novel grey rolling mechanism based on new information priority principle. An average weakening buffer operator is used to process the original sequence and the new information is mined before modeling. The modeling mechanism and steps of the new model are described in detail. Finally, the proposed model is used to predict and analyze the trend of carbon dioxide emissions in China. Compared with other two types of classical prediction models without considering new information priority, the experimental results show that the proposed model demonstrates better simulation and prediction performance and a high stability. The research results provide important reference value for China's relevant environmental sectors to make decisions on energy conservation and emission reduction policies, and also help to enrich and expand the development of grey system theory. [ABSTRACT FROM AUTHOR]