Residents'perception of sustainable tourism in protected mountain areas:the case of Asturias

Spain is the country with the most Biosphere Reserves in the world,52,and Asturias,with 7,ranks first among the single-province Autonomous Communities.The tourist interest in these natural spaces is increasing,but little or nothing is known about how the residents of these natural spaces perceive the tourist impacts.The main objective of this research was to evaluate the residents’perceived changes in protected mountain areas in Asturias concerning the environmental,sociocultural,and economic dimensions related to tourism activity with survey methods and various quantitative tools.The findings obtained were the following:firstly,there were significant differences between the residents’sociodemographic characteristics and their perceptions of tourism impacts;secondly,there were positive relationships between the residents’perceived tourism economic,environmental and sociocultural impacts and their general attitude towards tourism development;and thirdly,the more positive the residents’attitude towards tourism development,the more likely residents actively support its further development.The findings indicate the willingness of residents to get involved and participate in the tourism activity,so policymakers should implicate residents in decisionmaking on local tourism development.In conclusion,long-term monitoring of residents’evolution of their perceptions and attitudes is necessary to achieve sustainable tourism development.

A federated learning scheme meets dynamic differential privacy

Federated learning is a widely used distributed learning approach in recent years,however,despite model training from collecting data become to gathering parameters,privacy violations may occur when publishing and sharing models.A dynamic approach is pro-posed to add Gaussian noise more effectively and apply differential privacy to federal deep learning.Concretely,it is abandoning the traditional way of equally distributing the privacy budget e and adjusting the privacy budget to accommodate gradient descent federation learning dynamically,where the parameters depend on computation derived to avoid the impact on the algorithm that hyperparameters are created manually.It also incorporates adaptive threshold cropping to control the sensitivity,and finally,moments accountant is used to counting the∈consumed on the privacy‐preserving,and learning is stopped only if the∈_(total)by clients setting is reached,this allows the privacy budget to be adequately explored for model training.The experimental results on real datasets show that the method training has almost the same effect as the model learning of non‐privacy,which is significantly better than the differential privacy method used by TensorFlow.