Abstract
Welding physics is complex, and therefore the welding parametrization is time-consuming. In manual welding, the "hand", the experience, and the best sensor of all (the eyes) can compensate for the difficulties in finding the right settings (welding parameters, robot posture, speed,...) for a specific weld seam. In robotic welding the robotic arm and the sensors are limited, and the parametrization time escalates. This work aims to develop a flexible welding robotized system, through the introduction of (knowledge-based) decision support for welding parametrization in an advanced robotic work cell, in combination with advanced (collision-free) offline programming and advanced sensing. By selecting a specific application area, structural steel, this work will reduce the degree of complexity during the development, paving the way for the introduction of knowledge-based welding in the robotic arc welding sector.

Abstract
Total white blood cells (WBC) count is an important indication for infection diagnosis, in both human and veterinary medicine. State-of-the-art WBC counts are performed by flow cytometry combined with light scattering or impedance measurements, in the clinical analysis laboratory. These technologies are complex and difficult to be miniaturized into a portable point-of-care (POC) system. Spectroscopy is one of the most powerful technologies for POC miniaturization due to its capacity to analyze low sample quantities, little to no sample preparation, and ‘real-time’ results. WBC is in the proportion of 1:1000 to red blood cells (RBC), and the latter dominate visible-near infrared (Vis-NIR) information due to their large quantities and hemoglobin absorbance. WBC are difficult to be detected by traditional spectral analysis because their information is contained within the interference of hemoglobin bands. Herein, we perform a feasibility study for the direct detection of WBC counts in canine blood by Vis-NIR spectroscopy for veterinary applications, benchmarking current chemometrics techniques with self-learning artificial intelligence—a new advanced method for high-accuracy quantification from spectral information. Results show that total WBC counts can be detected by Vis-NIR spectroscopy to an average detection limit of 7.8 ×109 cells/L, with an R2 of 0.9880 between impedance flow cytometry analysis and spectral quantification. This result opens new possibilities for reagent-less POC technology in infection diagnosis. As WBC counts in dogs range from 5 to 45 ×109 cells/L, the detection limit obtained in this research allows concluding that the combined use of spectroscopy with this SL-AI new algorithm is a step towards the existence of portable and miniaturized Spectral POC hemogram analysis.

Abstract
Information and communication technologies provide their users with permanent global connectivity through a wide range of devices and with the Internet as their main support. Currently assuming a very significant economic relevance for a considerable group of countries, the Tourism sector is in the mindset of a digital transformation, in the scope of which a good part of its services is evolving towards ICT and Internet supported versions. In this context, the assurance of universal access to websites (Web accessibility) that support the businesses of organizations in this sector gains special relevance. This article presents an analysis at the level of Web accessibility of 240 websites directly related to the tourism sector, using TAW-Test de Acessibilidad Web evaluation tool. Despite the growing concern to provide more and more inclusive means, the overwhelming majority of websites did not reach the minimum level of accessibility, thus not assuring properly functional access for those who have a disability or limitation. © 2021 AISTI.

Abstract

Abstract

Abstract
Mixed-type data is common in the real world. However, supervised learning algorithms such as support vector machines or neural networks can only process numerical features. One may choose to drop qualitative features, at the expense of possible loss of information. A better alternative is to encode them as new numerical features. Under the constraints of time, budget, and computational resources, we were motivated to search for a general-purpose encoder but found the existing benchmarks to be limited. We review these limitations and present an alternative. Our benchmark tests 16 encoding methods, on 15 regression datasets, using 7 distinct predictive models. The top general-purpose encoders were found to be Catboost, LeaveOneOut, and Target. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.