Forecasting of Automobile Sales Based on Support Vector Regression Optimized by the Grey Wolf Optimizer Algorithm

With the development of the Internet and big data, more and more consumer behavior data are used in different forecasting problems, which greatly improve the performance of prediction. As the main travel tool, the sales of automobiles will change with the variations of the market and the external environment. Accurate prediction of automobile sales can not only help the dealers adjust their marketing plans dynamically but can also help the economy and the transportation sector make policy decisions. The automobile is a product with high value and high involvement, and its purchase decision can be affected by its own attributes, economy, policy and other factors. Furthermore, the sample data have the characteristics of various sources, great complexity and large volatility. Therefore, this paper uses the Support Vector Regression (SVR) model, which has global optimization, a simple structure, and strong generalization abilities and is suitable for multi-dimensional, small sample data to predict the monthly sales of automobiles. In addition, the parameters are optimized by the Grey Wolf Optimizer (GWO) algorithm to improve the prediction accuracy. First, the grey correlation analysis method is used to analyze and determine the factors that affect automobile sales. Second, it is used to build the GWO-SVR automobile sales prediction model. Third, the experimental analysis is carried out by using the data from Suteng and Kaluola in the Chinese car segment, and the proposed model is compared with the other four commonly used methods. The results show that the GWO-SVR model has the best performance of mean absolute percentage error (MAPE) and root mean square error (RMSE). Finally, some management implications are put forward for reference.

Protective Efficacy of Inactivated Vaccine against SARS-CoV-2 Infection in Mice and Non-Human Primates.

The ongoing coronavirus disease 2019 (COVID-19) pandemic caused more than 96 million infections and over 2 million deaths worldwide so far. However, there is no approved vaccine available for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the disease causative agent. Vaccine is the most effective approach to eradicate a pathogen. The tests of safety and efficacy in animals are pivotal for developing a vaccine and before the vaccine is applied to human populations. Here we evaluated the safety, immunogenicity, and efficacy of an inactivated vaccine based on the whole viral particles in human ACE2 transgenic mouse and in non-human primates. Our data showed that the inactivated vaccine successfully induced SARS-CoV-2-specific neutralizing antibodies in mice and non-human primates, and subsequently provided partial (in low dose) or full (in high dose) protection of challenge in the tested animals. In addition, passive serum transferred from vaccine-immunized mice could also provide full protection from SARS-CoV-2 infection in mice. These results warranted positive outcomes in future clinical trials in humans.

Biochemical and antigenic characterization of the structural proteins and their post-translational modifications in purified SARS-CoV-2 virions of an inactivated vaccine candidate.

In the face of COVID-19 pandemic caused by the newly emerged SARS-CoV-2, an inactivated, Vero cell-based, whole virion vaccine candidate has been developed and entered into phase III clinical trials within six months. Biochemical and immunogenic characterization of structural proteins and their post-translational modifications in virions, the end-products of the vaccine candidate, would be essential for the quality control and process development of vaccine products and for studying the immunogenicity and pathogenesis of SARS-CoV-2. By using a panel of rabbit antisera against virions and five structural proteins together with a convalescent serum, the spike (S) glycoprotein was shown to be N-linked glycosylated, PNGase F-sensitive, endoglycosidase H-resistant and cleaved by Furin-like proteases into S1 and S2 subunits. The full-length S and S1/S2 subunits could form homodimers/trimers. The membrane (M) protein was partially N-linked glycosylated; the accessory protein 3a existed in three different forms, indicative of cleavage and dimerization. Furthermore, analysis of the antigenicity of these proteins and their post-translationally modified forms demonstrated that S protein induced the strongest antibody response in both convalescent and immunized animal sera. Interestingly, immunization with the inactivated vaccine did not elicit antibody response against the S2 subunit, whereas strong antibody response against both S1 and S2 subunits was detected in the convalescent serum. Moreover, vaccination stimulated stronger antibody response against S multimers than did the natural infection. This study revealed that the native S glycoprotein stimulated neutralizing antibodies, while bacterially-expressed S fragments did not. The study on S modifications would facilitate design of S-based anti-SARS-CoV-2 vaccines.

Low toxicity and high immunogenicity of an inactivated vaccine candidate against COVID-19 in different animal models.

The ongoing COVID-19 pandemic is causing huge impact on health, life, and global economy, which is characterized by rapid spreading of SARS-CoV-2, high number of confirmed cases and a fatality/case rate worldwide reported by WHO. The most effective intervention measure will be to develop safe and effective vaccines to protect the population from the disease and limit the spread of the virus. An inactivated, whole virus vaccine candidate of SARS-CoV-2 has been developed by Wuhan Institute of Biological Products and Wuhan Institute of Virology. The low toxicity, immunogenicity, and immune persistence were investigated in preclinical studies using seven different species of animals. The results showed that the vaccine candidate was well tolerated and stimulated high levels of specific IgG and neutralizing antibodies. Low or no toxicity in three species of animals was also demonstrated in preclinical study of the vaccine candidate. Biochemical analysis of structural proteins and purity analysis were performed. The inactivated, whole virion vaccine was characterized with safe double-inactivation, no use of DNases and high purity. Dosages, boosting times, adjuvants, and immunization schedules were shown to be important for stimulating a strong humoral immune response in animals tested. Preliminary observation in ongoing phase I and II clinical trials of the vaccine candidate in Wuzhi County, Henan Province, showed that the vaccine is well tolerant. The results were characterized by very low proportion and low degree of side effects, high levels of neutralizing antibodies, and seroconversion. These results consistent with the results obtained from preclinical data on the safety.