Prediction of provincial Digital Economy Development Index based on grey combination forecasting model

In this paper, we investigate the optimization of BP neural network. An optimized BP neural network model, adaptive BP neural network based on PSO and PCA algorithms (TPPMA) is proposed to improve the training speed and increase prediction accuracy. By introducing Momentum backpropagation and adaptive learning rate into BP Neural Network, one can reduce the possibility of local optimization. For the architecture of BP Neural Network, the initial connection weight is determined by Particle Swarm Optimization (PSO) and the number of hidden nodes is decided by three-division method. In the model, Principal Component Analysis (PCA) is used to reduce the dimension of the sample. Simulation result demonstrates that TPPMA method is efficient and can get promising results with less time compared with other results.

A high precise wind speed forecasting method is one of current wind power research hotspots. This paper presented a combined wind speed forecasting model based on support vector machine (SVM) optimized by particle swarm optimization (PSO) using historical data of wind speed at the site. The model took the results of back propagation neural network (BPNN), radial basis function neural network (RBFNN), genetic neural network (GNN) and wavelet neural network (WNN) as the inputs, and adopted the actual wind speed as the output. Meanwhile, particle swarm optimization was used to optimize model parameters. Apply this model in hourly prediction of wind speed using historical data from a wind farm in Shanxi Province. It is observed that its prediction accuracy was not only higher than that of any of its single network but higher than traditional linear combined forecasting model and neural network combined forecasting model.

The wind power generation capacity is increasing rapidly every year. There needs to be a corresponding development in the management of wind power. Accurate wind speed forecasting is essential for a wind power management system. However, it is not easy to forecast wind speed precisely since wind speed time series data are usually nonlinear and fluctuant. This paper proposes a novel combined wind speed forecasting model that based on PSR (phase space reconstruction), NNCT (no negative constraint theory) and a novel GPSOGA (a hybrid optimization algorithm that combines global elite opposition-based learning strategy, particle swarm optimization and the genetic algorithm) optimization algorithm. SSA (singular spectrum analysis) is firstly applied to decompose the original wind speed time series into IMFs (intrinsic mode functions). Then, PSR is employed to reconstruct the intrinsic mode functions into input and output vectors of the forecasting model. A combined forecasting model is proposed that contains a CBP (cascade back propagation network), RNN (recurrent neural network), GRU (gated recurrent unit), and CNNRNN (convolutional neural network combined with recurrent neural network). The NNCT strategy is used to combine the output of the four predictors, and a new optimization algorithm is proposed to find the optimal combination parameters. In order to validate the performance of the proposed algorithm, we compare the forecasting results of the proposed algorithm with different models on four datasets. The experimental results demonstrate that the forecasting performance of the proposed algorithm is better than other comparison models in terms of different indicators. The DM (Diebold–Mariano) test, Akaike’s information criterion and the Nash–Sutcliffe efficiency coefficient confirm that the proposed algorithm outperforms the comparison models.

To improve the effectiveness and intelligence of university teaching management evaluation, the particle swarm optimization BP neural network algorithm is applied to the analysis of university teaching management evaluation data. BP neural network is used to model the evaluation index of teaching management, and then particle swarm optimization is used to optimize the weight and threshold of the neural network transfer function to ensure that the output of the BP neural network can obtain the global optimal solution. The experimental results show that the proposed algorithm has a good fit between the predicted value and the actual value of the evaluation object of teaching management in Colleges and universities, and has a strong promotion value.

The crude oil demand is growing rapidly in China, driven by its rapid industrialization and motorization. China has already become the second-largest oil importer nation in the world, after the United States. The dynamic GM(1,1) model of grey theory is used to develop the dynamic GM(M,N) model to forecast the crude oil consumption and production in China. In order to improve the forecasting accuracy, the original GM(1,1) model is improved by using BP Neural Network technique. We analyze the data of the crude oil consumption and production from 1995 to 2008 in China, and forecast China's crude oil consumption and production by this Grey Neural Network forecasting model, which shows that the improved grey forecasting model is of more reliability and higher forecasting accuracy than the original GM (1,1). The forecasting results indicate that China's crude oil consumption and production will continue to increase rapidly in the period of 2009 to 2015.

During the operation of navigation satellites, errors in the broadcast ephemeris orbits are caused by the influence of ingress factors and other factors. To address this phenomenon, this paper examines the use of the computational intelligence (CI) methods to implement track correction and to develop an optimized BP neural network model based on an improved particle swarm algorithm. The model improves the inertia weights and learning factor parameters of the particle swarm optimization (PSO) algorithm to improve the global optimization capability and accelerate the convergence speed. The improved PSO (IPSO) algorithm is used to perform a global optimization search for the hyperparameters of the BP neural network, and then the neural network model is trained by broadcast ephemeris Keplerian root number and regression parameters. The model is validated using the broadcast ephemeris data of the BDS-3 MEO and IGSO satellites, and the mean square error correction rate of multiple satellites with different correction models shows that the error correction rate of the IPSO-BPNN model can reach 70.2–84% and the error correction rate can be improved by 14.2–56.8% compared with the PSO-BPNN model. The proposed algorithm provides an important reference for BDS-3 and other global navigation satellite systems for improving the accuracy of satellite orbit determination.

Purpose China is experiencing an economic revolution focused on reducing carbon emissions (CEs). Various technological research and development (R&D) frameworks also hasten the growth of the digital economy, which then fuels this economic revolution. Nevertheless, several correlation uncertainties in China have been observed between R&D investment and CE reduction with green economic transformation. This phenomenon is attributed to insufficient spatial impact considerations. Design/methodology/approach Therefore, this article explored the spatial impacts of the digital economy and R&D expenditures regarding environmental quality using Chinese-related panel data between 2012 and 2021. This study uses the Moran I index to test whether there is a spatial relevance between regional carbon emissions in China and assess the digital economic advancement level using the entropy weight approach. In addition, this article analyzes the direct and indirect impacts following the partial differentiation approach, and then creates an interaction term between the digital economy and R&D investment to assess the moderating effect for examining the influence of investing in R&D on reducing CO2 levels of the digital economy. Findings A positive spatial relevance between the digital economy and CEs was then highlighted from the empirical findings. The digital economy expansion also demonstrated higher local CEs while negatively impacting nearby regions. Notably, the digital economy concurrently lowered and increased local CEs in the Eastern and Central zones, respectively. Overall, a larger R&D investment directly impacted the capacity of the digital economy in decreasing the carbon emission intensity (CEI) at a regional level. An accelerated digital economy expansion and lower CEI were recorded in the Eastern zone owing to more significant R&D investments. Research limitations/implications China has gradually shifted its focus from reducing CEs to implementing “dual control of carbon” to achieve the “dual carbon” target. Future studies should then involve additional studies concerning the impact mechanism and path selection related to “dual carbon control.” Practical implications Investment in R&D plays a key role in reducing carbon emissions from the digital economy. By fostering innovation and technological advances, R&D investment activities can create more energy-efficient digital infrastructures, develop sustainable practices and optimize resource use. In addition, these R&D investments can facilitate the transition to renewable energy sources, enhance data management systems to minimize waste and promote the adoption of green technologies by businesses and consumers. As the digital economy continues to evolve, prioritizing R&D in this area is critical to achieving long-term sustainable development goals and addressing the pressing challenges of climate change. Stakeholders across industries must therefore recognize the importance of investment in research and development as a strategic approach that not only drives economic growth but also ensures environmental stewardship in an increasingly digital world. Social implications Investments in research and development not only foster innovation and technological progress, but also promote sustainable practices, which can have significant environmental benefits. In addition, they have the potential to create new jobs, improve public health through better air quality and drive economic growth in a manner consistent with climate goals. As society becomes increasingly dependent on digital solutions, it is critical to harness the power of the digital economy to achieve a more sustainable and inclusive society. Originality/value Research development investment is critical to all aspects of regulation. Research on R&D investment can provide direction to local governments in formulating digital economy policies and can be beneficial to local governments in considering regional differences in resource availability. The research and technical innovation strategies in the policies for developing the digital economy can substantially expedite carbon neutrality achievement by 2060.

A combination method of optimization of the background value and optimization of the initial item is proposed. The sequences of the unbiased exponential distribution are simulated and predicted through the optimization of the background value in grey differential equations. The principle of the new information priority in the grey system theory and the rationality of the initial item in the original GM(1,1) model are fully expressed through the improvement of the initial item in the proposed time response function. A numerical example is employed to illustrate that the proposed method is able to simulate and predict sequences of raw data with the unbiased exponential distribution and has better simulation performance and prediction precision than the original GM(1,1) model relatively.

In this paper, a novel approach to damage identification in structures using Particle Swarm Optimization (PSO) combined with Artificial neural network (ANN) is proposed. With recent substantial advances, ANN has been extensively utilized in a wide variety of fields. However, because of the application of backpropagation algorithms based on gradient descent techniques, ANN may be trapped in local minima when seeking the best solution. This may reduce the accuracy of ANN. Therefore, we propose employing an evolutionary algorithm, namely PSO to deal with the local minimum problems of ANN. PSO is employed to improve the training parameters of ANN consisting of weight and bias ratios by reducing the deviation between calculated and desired results. These training parameters are then used to train the network. Since PSO applies global search techniques to look for the best solution, it can assist the network in avoiding local minima by looking for a beneficial starting point. In order to assess the effectiveness of the proposed approach, both numerical and experimental models with different damage scenarios are employed. The results show that ANN-PSO not only significantly reduces computational time compared to PSO but also possibly identifies damages in the considered structures more accurately than ANN and PSO separately.

Increasing the forecast precision of the intake air mass flow of gasoline engines by reducing the effect of hysteresis in the mass air flow sensor, an improved gray forecasting model is constructed by adding a weakening buffer operator and variable background values based on traditional GM(1,1) model, and then combined with the least squares to form a combined forecasting model. In the weakening buffer operator, the background value weighting coefficient is determined based on collected sample data from the mass air flow sensor, utilizing the particle swarm optimization (PSO) algorithm. Some of test data of single-cylinder gasoline engine acceleration condition, deceleration condition and motorcycle China IV emission are simulated. The results show that the improved grey-least squares combined forecasting model can accurately predict the intake air mass flow as well as come up with a solution of prediction mutation, and the prediction accuracy is improved.

Over the years, the logistics development in Tibet has fallen behind the transport. Since the opening of Qinghai-Tibet Railway in 2006, the opportunity for development of modern logistics has been brought to Tibet. The logistics demand analysis and forecasting is a prerequisite for regional logistics planning. By establishing indicator system for logistics demand of agricultural products, agricultural product logistics principal component regression model, gray forecasting model, BP neural network forecasting model are built. Because of the single model’s limitations, quadratic-linear programming model is used to build combination forecasting model to predict the logistics demand scale of agricultural products in Tibet over the next five years. The empirical analysis results show that combination forecasting model is superior to single forecasting model, and it has higher precision, so combination forecasting model will have much wider application foreground and development potential in the field of logistics.

China has already become world's largest coal producer and consumer. China's production in 2006 roughly equaled the combined production of the next four top producers (the United States, India, Australia and Russia). The dynamic GM(1,1) model of grey theory is used to forecast the coal production and consumption in China. In order to improve the forecast accuracy, the original GM(1, 1) models are improved by using Markov-chain. We analyze the data of the coal production and consumption from 1990 to 2007 in China, and forecast China's coal production and consumption by this Grey-Markov forecasting model, which shows that the improved grey forecasting model is of more reliability and higher forecast accuracy than GM (1, 1). And the forecast results indicate that China's coal production and consumption will continue to increase rapidly in the period of 2008 to 2015.

The rapid economic growth in China results in the fast energy consumption and production. The dynamic GM(1,N) model of grey theory is used to develop the dynamic GM(1, N) model to forecast the final energy consumption and production in China. In order to improve the forecast accuracy, the original GM(1, N) models are improved by using two methodologies of equal dimension replenishment and residual modification. We analyze the data of total consumption and production of energy and its composition from 1996 to 2005 in China, and forecast China's energy consumption and production by this grey forecasting model, which shows that the improved grey forecasting model is of more reliability and higher forecast accuracy than GM (1, N).The forecast results indicate that China's final energy consumption and production will increase rapidly in the period of 2006 to 2015.

Prediction and monitoring of the telephone traffic concerned by the telecom operators to predict accurately and reliability of the results directly affect the effectiveness and long-term development of enterprises. Based on the time series type of telephone traffic data for its small term, and characteristics of the trend increasing, for this reason this paper use grey model GM(1,1). The telephone traffic itself has less volatility and a strong seasonal characteristics, this paper presents a new prediction model, combined grey forecast model. The model combined the longitudinal and horizontal data of the projected trend of the data to achieve short-term forecasting and seasonal prediction of binding targets, and thus improve the prediction accuracy. At the same time by the introduction of particle swarm optimizer(PSO) to improve the grey forecast model to compare with the Season Exponent and Grey Forecast method. This paper picked a province of China from 2004 to 2009 the monthly telephone traffic data, through different angles using grey model GM(1,1) to predict and compare the predicted results, the experiment can see the improved grey prediction model have more accurately predict the future telephone traffic.

Overseas students constitute the paramount talent resource for China, and, hence, overseas talent mobility prediction is crucial for the formulation of China’s talent strategy. This study proposes a new model for predicting the number of students studying abroad and returning students, based on the grey system theory, owing to the limited data and uncertainty of the influencing factors. The proposed model introduces change-point detection to determine the number of modeling time points, based on the fractional-order grey prediction model. We employed a change-point detection method to find the change points for determining the model length, based on the principle of new information priority, and used a fractional order accumulated generating operation to construct a grey prediction model. The two real data sets, the annual number of students studying abroad and returning students, were employed to verify the superiority of the proposed model. The results showed that the proposed model outperformed other benchmark models. Furthermore, the proposed model has been employed to predict the tendencies of overseas talent mobility in China by 2025. Further, certain policy recommendations for China’s talent strategy development have been proposed, based on the prediction results.