https://www.selleckchem.com/products/nvp-2.html After the selection of the input variables to calculate the correct UVI, the deep learning model based on the TensorFlow set with the optimum number of layers and number of nodes was designed and implemented, and learning was executed via the data set. After the data set was converted to the mobile deep learning model to operate under the mobile environment, the converted data were loaded on the mobile device. The proposed method enabled providing UV information at the user's location through a mobile device on which the illuminance sensors were loaded even in the environment without UVI measuring equipment. The comparison of the experiment results with the reference device (spectrometer) proved that the proposed method could provide UV information with an accuracy of 90-95% in the summers, as well as in winters.The Danube River is the second longest in Europe and its water quality is important for the communities relying on it, but also for supporting biodiversity in the Danube Delta Biosphere Reserve, a site with high ecological value. This paper presents a methodology for assessing water quality and long-term trends based on water quality indices (WQI), calculated using the weighted arithmetic method, for 15 monitoring stations in the Lower Danube and Danube tributaries in Romania, based on annual means of 10 parameters for the period 1996-2017. A trend analysis is carried out to see how WQIs evolved during the studied period at each station. Principal component analysis (PCA) is applied on sub-indices to highlight which parameters have the highest contributions to WQI values, and to identify correlations between parameters. Factor analysis is used to highlight differences between locations. The results show that water quality has improved significantly at most stations during the studied period, but pollution is higher in some Romanian tributaries than in the Danube. The parameters with the highest contribution to