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.

Transcription of handwritten text can be speed-up by using off-line Handwritten Text Recognition techniques, that allow the obtention of an initial draft transcription of an image with handwritten text. However, this draft transcription usually contains errors that must be amended by the transcriber by providing a feedback signal. The usual approach is post-edition, where each error is corrected without modifying the rest of the current transcription. A more sophisticated approach can employ the current modification to provide a new whole transcription, hopefully with less errors. Apart from that, feedback can be provided in different modalities: keyboard input, on-line handwritten text, or speech. Each of these modalities presents different features with respect to ambiguity, derived errors, and final transcription time. In this work we study how the different modalities behave in the assisted transcription of a historical handwritten text document in Spanish and we evaluate their transcription productivity.

Automatic transcription of historical documents is becoming an important research topic, specially because of the increasing number of digitised historical documents that libraries and archives are publishing. However, state-of-the-art handwritten text recognition systems are far from being perfect. Therefore, to have perfect transcriptions, human expert revision is required to really produce a transcription of standard quality. In this context, an interactive assistive scenario, where the automatic system and the human transcriber cooperate to generate the perfect transcription, would allow for a more effective approach. In this paper we present a multimodal interactive transcription system where user feedback is provided by means of touchscreen pen strokes, traditional keyboard and mouse operations. The combination of both the main and the feedback data stream is based on the use of Confusion Networks derived from the output of the on-line and off-line handwritten text recognition systems. The use of the proposed combination help to optimise overall performance and usability.

Transcription of handwritten historical documents is one of the main topics in document analysis systems, due to cultural reasons. State-of-the-art handwritten text recognition systems allow to speed up the transcription task. Currently, this automatic transcription is far from perfect, and human expert revision is required in order to obtain the actual transcription. In this context, crowdsourcing emerged as a powerful tool for massive transcription at a relatively low cost, since the supervision effort of professional transcribers may be dramatically reduced. However, current transcription crowdsourcing platforms are mainly limited to the use of non-mobile devices, since the use of keyboards in mobile devices is not friendly enough for most users. This work presents the alternative of using speech dictation of handwritten text lines as transcription source in a crowdsourcing platform. The experiments explore how an initial handwritten text recognition hypothesis can be improved by using the contribution of speech recognition from several speakers, providing as a final result a better hypothesis to be amended by a professional transcriber with less effort.

Transcription of historical documents is an interesting task for libraries in order to make available their funds. In the lasts years, the use of Handwritten Text Recognition allowed paleographs to speed up the manual transcription process, since they are able to correct on a draft transcription. Another alternative is obtaining the draft transcription by dictating the contents to an Automatic Speech Recognition system. When both sources (image and speech) are available, a multimodal combination is possible, and an iterative process can be used in order to refine the final hypothesis. In this work, a multimodal combination based on confusion networks is presented. Results on two different sets of data, with different difficulty level, show that the proposed technique provides similar or better draft transcriptions than a previously proposed approach, allowing for a faster transcription process.