Abstract
This paper presents a literature review of the importance of virtual technology for rehabilitation for people with ASD (Autism Spectrum Disorder). ASD is diagnosed as a neurological disability characterized by a range of physical and mental disorders and whose first symptoms appear during early childhood. People with autism deal with issues with social communication, behavior, and attention skills. As a sensitive disturbance, adapted technology allows to re-learn skills stimulating procedures about how to proceed, communicate or behave without difficulties in unexpected environments. The use of technology in educational contexts, home or at school, helps prevent and teach younger people with ASD. Considering different technologies as more appropriate methods, Virtual Reality (VR) applications and personalized environments provide better simulation and comfortable environments. As the main advantage of VR, complete immersion and interactive experience promotes constant learning for people with autism. This systematic review details the benefits of VR studies and compares the benefits of different interactive technologies according to the deficits of several individuals. The use of technology versus the traditional path on therapies helps obtain better and faster results over time. Finally, it explains how VR can be recognized as a tool to help develop cognitive, verbal and nonverbal skills and recognizes technology as a good ally to face fears or reactions by ASD people.

Abstract
In this paper, we describe the study of the kinetics and efficiency of the refractive index matching mechanism created by highly concentrated glycerol solutions in human normal and pathological colorectal mucosa tissues. Considering thewavelength range between 200 and 1000 nm, higher efficiency was obtained for the pathological mucosa, which shows a decreasing efficiency with increasing wavelength. The normal mucosa presents similar values in the deep-ultraviolet and in the near-infrared. Minimal efficiency values of 1% and 1.5% were obtained in the normal and pathological mucosa at 266 nm (combined absorption of DNA/RNA and myoglobin/hemoglobin bands at 260 and 274 nm) and local maxima of 2.9% and 3.8% were obtained in the same tissues at 570 nm. The diffusion time of glycerol was estimated as 417.3 +/- 5.2 s in normal mucosa and 504.9 +/- 3.8 s in pathological mucosa, suggesting that less molecules are necessary in the pathological tissue to produce a higher magnitude RI matching.

Abstract

Abstract
Nowadays, the robotic welding joint estimation, or weld seam tracking, has improved according to the new developments on computer vision technologies. Typically, the advances are focused on solving inaccurate procedures that advent from the manual positioning of the metal parts in welding workstations, especially in SMEs. Robotic arms, endowed with the appropriate perception capabilities, are a viable solution in this context, aiming for enhancing the production system agility whilst not increasing the production set-up time and costs. In this regard, this paper proposes a local perception pipeline to estimate joint welding points using small-sized/low-cost 3D cameras, following an eyes-on-hand approach. A metrological 3D camera comparison between Intel Realsene D435, D415, and ZED Mini is also discussed, proving that the proposed pipeline associated with standard commercial 3D cameras is viable for welding operations in an industrial environment.

Abstract
There are currently several techniques for automatic calibration of inertial sensors. This paper describes a subset of these algorithms that could be used in a manipulator and should allow for its prompt use. A robotic manipulator specifically developed for the study of over-sensored systems is used to realistically test the performance of the implemented methods. The results of these methods show that the accelerometers and the gyroscopes were properly calibrated. However, the magnetometers suffer from variable interferences and therefore could not be calibrated.

Abstract
The recent Covid-19 pandemic and the fact that wearing masks in public is now mandatory in several countries, created challenges in the use of face recognition systems (FRS). In this work, we address the challenge of masked face recognition (MFR) and focus on evaluating the verification performance in FRS when verifying masked vs unmasked faces compared to verifying only unmasked faces. We propose a methodology that combines the traditional triplet loss and the mean squared error (MSE) intending to improve the robustness of an MFR system in the masked-unmasked comparison mode. The results obtained by our proposed method show improvements in a detailed step-wise ablation study. The conducted study showed significant performance gains induced by our proposed training paradigm and modified triplet loss on two evaluation databases.