Search

To accurately predict the regional spread of Covid-19 infection, this study proposes a novel hybrid model which combines a Long short-term memory (LSTM) artificial recurrent neural network with dynamic behavioral models. Several factors and control strategies affect the virus spread, and the uncertainty arisen from confounding variables underlying the spread of the Covid-19 infection is substantial. The proposed model considers the effect of multiple factors to enhance the accuracy in predicting the number of cases and deaths across the top ten most-affected countries and Australia. The results show that the proposed model closely replicates test data. It not only provides accurate predictions but also estimates the daily behavior of the system under uncertainty. The hybrid model outperforms the LSTM model accounting for limited available data. The parameters of the hybrid models were optimized using a genetic algorithm for each country to improve the prediction power while considering regional properties. Since the proposed model can accurately predict Covid-19 spread under consideration of containment policies, is capable of being used for policy assessment, planning and decision-making., Comment: As requested by the dear moderator, to assess the statistical significance of the reduction in RMSE in hybrid models compared to LSTM, each module was evaluated 500 times after hype-parameter tuning, and the corresponding RMSE distribution was used to estimate 95% confidence interval (CI) and t-test p-values comparing significant differences between different stages

A significant part of the United Nations World Heritage Sites (WHSs) is located in developing countries. These sites attract an increasing number of tourist and income to these countries. Unfortunately, many of these WHSs are in a poor condition due to climatic and environmental impacts; war and tourism pressure, requiring the urgent need for restoration and preservation (Tuan & Navrud, 2007). In this study, we characterise residents from Shiraz city (visitors and non-visitors) willingness to invest in the management of the heritage sites through models for the preservation of heritage and development of tourism as a local resource. The research looks at different categories of heritage sites within Shiraz city, Iran. The measurement instrument is a stated preference referendum task administered state-wide to a sample of 489 respondents, with the payment mechanism defined as a purpose-specific incremental levy of a fixed amount over a set period of years. A Latent Class Binary Logit model, using parametric constraints is used innovatively to deal with any strategic voting such as Yea-sayers and Nay-sayers, as well as revealing the latent heterogeneity among sample members. Results indicate that almost 14% of the sampled population is unwilling to be levied any amount (Nay-sayers) to preserve any heritage sites. Not recognizing the presence of nay-sayers in the data or recognizing them but eliminating them from the estimation will result in biased Willingness to Pay (WTP) results and, consequently, biased policy propositions by authorities. Moreover, it is found that the type of heritage site is a driver of WTP. The results from this study provide insights into the WTP of heritage site visitors and non-visitors with respect to avoiding the impacts of future erosion and destruction and contributing to heritage management and maintenance policies.