Abstract
Real Estate Agents perform the tedious job of selecting and filtering pictures of houses manually on a daily basis, in order to choose the most suitable ones for their websites and provide a better description of the properties they are selling. However, this process consumes a lot of time, causing delays in the advertisement of homes and reception of proposals. In order to expedite and automate this task, Computer Vision solutions can be employed. Deep Learning, which is a subfield of Machine Learning, has been highly successful in solving image recognition problems, making it a promising solution for this particular context. Therefore, this paper proposes the application of Vision Transformers to indoor room classification. The study compares various image classification architectures, ranging from traditional Convolutional Neural Networks to the latest Vision Transformer architecture. Using a dataset based on well-known scene classification datasets, their performance is analyzed. The results demonstrate that Vision Transformers are one of the most effective architectures for indoor classification, with highly favorable outcomes in automating image recognition and selection in the Real Estate industry.

Abstract
We present new astrometric and polarimetric observations of flares from Sgr A* obtained with GRAVITY, the near-infrared interferometer at ESO's Very Large Telescope Interferometer (VLTI), bringing the total sample of well-covered astrometric flares to four and polarimetric flares to six. Of all flares, two are well covered in both domains. All astrometric flares show clockwise motion in the plane of the sky with a period of around an hour, and the polarization vector rotates by one full loop in the same time. Given the apparent similarities of the flares, we present a common fit, taking into account the absence of strong Doppler boosting peaks in the light curves and the EHT-measured geometry. Our results are consistent with and significantly strengthen our model from 2018. First, we find that the combination of polarization period and measured flare radius of around nine gravitational radii (9R(g) similar to 1.5R(ISCO), innermost stable circular orbit) is consistent with Keplerian orbital motion of hot spots in the innermost accretion zone. The mass inside the flares' radius is consistent with the 4.297 x 10(6) M-circle dot measured from stellar orbits at several thousand R-g. This finding and the diameter of the millimeter shadow of Sgr A* thus support a single black hole model. Second, the magnetic field configuration is predominantly poloidal (vertical), and the flares' orbital plane has a moderate inclination with respect to the plane of the sky, as shown by the non-detection of Doppler-boosting and the fact that we observe one polarization loop per astrometric loop. Finally, both the position angle on the sky and the required magnetic field strength suggest that the accretion flow is fueled and controlled by the winds of the massive young stars of the clockwise stellar disk 1-5 '' from Sgr A*, in agreement with recent simulations.

Abstract
In chronic shoulder pain, adaptations in the nervous system such as in motoneuron excitability, could contribute to impairments in scapular muscles, perpetuation and recurrence of pain and reduced improvements during rehabilitation. The present cross-sectional study aims to compare trapezius neural excitability between symptomatic and asymptomatic subjects. In 12 participants with chronic shoulder pain (symptomatic group) and 12 without shoulder pain (asymptomatic group), the H reflex was evoked in all trapezius muscle parts, through C3/4 nerve stimulation, and the M-wave through accessory nerve stimulation. The current intensity to evoke the maximum H reflex, the latency and the maximum peak-to-peak amplitude of both the H reflex and M-wave, as well as the ratio between these two variables, were calculated. The percentage of responses was considered. Overall, M-waves were elicited in most participants, while the H reflex was elicited only in 58-75% or in 42-58% of the asymptomatic and symptomatic participants, respectively. A comparison between groups revealed that the symptomatic group presented a smaller maximum H reflex as a percentage of M-wave from upper trapezius and longer maximal H reflex latency from the lower trapezius (p < 0.05). Subjects with chronic shoulder pain present changes in trapezius H reflex parameters, highlighting the need to consider trapezius neuromuscular control in these individuals' rehabilitation.

Abstract
In recent years, Artificial Intelligence (AI) provided essential tools to enhance the productivity of activities related to civil engineering, particularly in design, construction, and maintenance. In this framework, the present work proposes a novel AI computer vision methodology for automatically identifying the corrosion phenomenon on roofing systems of large-scale industrial buildings. The proposed method can be incorporated into computational packages for easier integration by the industry to enhance the inspection activities' performance. For this purpose, a dedicated image database with more than 8k high-resolution aerial images was developed for supervised training. An Unmanned Aerial Vehicle (UAV) was used to acquire remote georeferenced images safely and efficiently. The corrosion anomalies were manually annotated using a segmentation strategy summing up 18,381 instances. These anomalies were identified through instance segmentation using the Mask based Region-Convolution Neural Network (Mask R-CNN) framework adjusted to the created dataset. Some adjustments were performed to enhance the performance of the classification model, particularly defining an adequate input image size, data augmentation strategy, Intersection over a Union (IoU) threshold during training, and type of backbone network. The inferences show promising results, with correct detections even under complex backgrounds, poor illumination conditions, and instances of significantly reduced dimensions. Furthermore, in scenarios without a roofing system, the model proved reliable, not producing any false positive occurrences. The best model achieved metrics' values equal to 65.1% for the bounding box detection Average Precision (AP) and 59.2% for the mask AP, considering an IoU of 50%. Regarding classification metrics, the precision and recall were equal to 85.8% and 84.0%, respectively. The developed methodology proved to be extremely valuable for guiding infrastructure managers in taking physically informed decisions based on the real assets condition.

Abstract
Glaucoma is a disease that arises from increased intraocular pressure and leads to irreversible partial or total loss of vision. Due to the lack of symptoms, this disease often progresses to more advanced stages, not being detected in the early phase. The screening of glaucoma can be made through visualization of the retina, through retinal images captured by medical equipment or mobile devices with an attached lens to the camera. Deep learning can enhance and increase mass glaucoma screening. In this study, domain transfer learning technique is important to better weight initialization and for understanding features more related to the problem. For this, classic convolutional neural networks, such as ResNet50 will be compared with Vision Transformers, in high and low-resolution images. The high-resolution retinal image will be used to pre-trained the network and use that knowledge for detecting glaucoma in retinal images captured by mobile devices. The ResNet50 model reached the highest values of AUC in the high-resolution dataset, being the more consistent model in all the experiments. However, the Vision Transformer proved to be a promising technique, especially in low-resolution retinal images. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Abstract
When the price of the energy shared within an energy community is based on a local energy market, it is the responsibility of each participant to bid adequately so that participating provides a larger benefit than not participating. Alternatively, centralized energy community bill minimization may be an option, but a mechanism to share the collective benefits among the members is needed. This mechanism should be fair and easy to explain, no members should be harmed with respect to their individual optimal behavior and should provide the right economic signal. This paper analyses and compares some common pricing mechanisms for the internal compensation for the energy shared among the members of an energy community centrally managed. Simple case examples are used to identify those pricing mechanisms that are fairer and provide the righter economic signals to the participants.