The COVID-19 pandemic has had a significant impact on the world, highlighting the importance of the accurate prediction of infection numbers. Given that the transmission of SARS-CoV-2 is influenced by temporal and spatial factors, numerous researchers have employed neural networks to address this issue. Accordingly, we propose a whale optimization algorithm–bidirectional long short-term memory (WOA-BILSTM) model for predicting cumulative confirmed cases. In the model, we initially input regional epidemic data, including cumulative confirmed, cured, and death cases, as well as existing cases and daily confirmed, cured, and death cases. Subsequently, we utilized the BILSTM as the base model and incorporated WOA to optimize the specific parameters. Our experiments employed epidemic data from Beijing, Guangdong, and Chongqing in China. We then compared our model with LSTM, BILSTM, GRU, CNN, CNN-LSTM, RNN-GRU, DES, ARIMA, linear, Lasso, and SVM models. The outcomes demonstrated that our model outperformed these alternatives and retained the highest accuracy in complex scenarios. In addition, we also used Bayesian and grid search algorithms to optimize the BILSTM model. The results showed that the WOA model converged fast and found the optimal solution more easily. Thus, our model can assist governments in developing more effective control measures.

Building a reasonable green industry evaluation index system is the key to green industry evaluation. According to the connotation of green industry, the criterion of eliminating information duplication index and the criterion of screening the index with the largest quality coefficient of approximate classification, the evaluation index system of green industry by using the method of R clustering-roughness analysis is constructed in this paper. The main innovations and characteristics are as follows: Firstly, the evaluation indexes are clustered into criteria by the method of deviation squares to ensure that the response information of different indexes after screening is not duplicated. Secondly, rough set analysis is used to solve the approximate classification quality coefficients of similar indexes in R clustering, and one of the indexes with the smallest correlation degree is selected. Ensure that the selected indicators having the greatest impact on the green industry evaluation. Thirdly, through R clustering and rough set analysis, the index system of green industry evaluation is constructed, which includes 22 indexes including green production, green consumption and green environment.

Abstract. The development of the incremental PPP projects and the stock PPP projects are uneven and there are very few successful cases of the stock PPP projects. To explore the reason, we built the evaluation indicator system according the different demands of different participants of PPP firstly, then adjusted the indicators system according to the characteristics of the increment and stock projects. That is an indicators system based on multiple participation. Lastly, used the AHP-fuzzy comprehensive evaluation method to evaluate the chosen cases and found the efficiency of the stock PPP project lower than the incremental one. The reason is that the lack of support policy and the incomplete of laws cause the risk and the management of stock project higher.