The measurement, monitoring, modeling and forecasting of atmospheric phenomena such as temperature, precipitation, humidity, speed, wind direction, among others, requires the installation and maintenance of a network of meteorological stations for the development of this activity. Depending on its purposes and scope, this network will be more or less sophisticated in the capture and transmission of information. The present work proposes to formulate a methodology to establish the minimum network of meteorological stations necessary for the recording of temperature, as well as the thermal zones of the Colombian territory as a function of altitude. For this purpose, first, the Dynamic Time Warping (DTW) algorithm was used as a technique to calculate the similarity between time series. From the results obtained with DTW, a hierarchical grouping was developed to determine the station clusters. Finally, the thermal zones, 10 in total as a result of the clustering, were the result of selecting those stations that were within the interquartile range with respect to the altitude coordinate. From an initial network of 452 stations, an optimal network of 230 stations was arrived at. Daily historical temperature records from the network of meteorological stations managed by the Institute of Environmental Studies (IDEAM) were the input with which this methodology was implemented.

This work is framed in the domain of software engineering. Specifically, it is situated in the subdomain of user interface evaluation. The context of the same comprises the phenomenon of visual attention and its evaluation through indicators that allow evaluating the quality of these interfaces. Specifically, it presents a model for the prediction of visual attention based on saliency maps, machine learning and biometric data. Its objective is to serve as a support to promote the usability of user interfaces. Experiments carried out with the eye tracker by the Institute for Cognitive Sciences at the University of Osnabrück and the University Medical Center in Hamburg-Eppendorf, among which free visualization tasks on user interfaces such as web pages, formed the input with which the model was developed. Its general structure consists of two elements: a convolutional neural network and Guided Grad-CAM (a convolutional layer visualization method). Biometric components were used to train the network: images whose size was set as a function of the foveal radius and the user's distance from the interface. The natural units of information (nats) were used as a measure to evaluate the accuracy of the model.