Abstract

Abstract
Stellar orbits at the Galactic Center provide a very clean probe of the gravitational potential of the supermassive black hole. They can be studied with unique precision, beyond the confusion limit of a single telescope, with the near-infrared interferometer GRAVITY. Imaging is essential to search the field for faint, unknown stars on short orbits which potentially could constrain the black hole spin. Furthermore, it provides the starting point for astrometric fitting to derive highly accurate stellar positions. Here, we present G(R), a new imaging tool specifically designed for Galactic Center observations with GRAVITY. The algorithm is based on a Bayesian interpretation of the imaging problem, formulated in the framework of information field theory and building upon existing works in radio-interferometric imaging. Its application to GRAVITY observations from 2021 yields the deepest images to date of the Galactic Center on scales of a few milliarcseconds. The images reveal the complicated source structure within the central 100mas around Sgr A*, where we detected the stars S29 and S55 and confirm S62 on its trajectory, slowly approaching Sgr A*. Furthermore, we were able to detect S38, S42, S60, and S63 in a series of exposures for which we offset the fiber from Sgr A*. We provide an update on the orbits of all aforementioned stars. In addition to these known sources, the images also reveal a faint star moving to the west at a high angular velocity. We cannot find any coincidence with any known source and, thus, we refer to the new star as S300. From the flux ratio with S29, we estimate its K-band magnitude as m(K)(S300)similar or equal to 19.0 - 19.3. Images obtained with CLEAN confirm the detection. To assess the sensitivity of our images, we note that fiber damping reduces the apparent magnitude of S300 and the effect increases throughout the year as the star moves away from the field center. Furthermore, we performed a series of source injection tests. Under favorable circumstances, sources well below a magnitude of 20 can be recovered, while 19.7 is considered the more universal limit for a good data set.

Abstract
Nowadays, Artificial Intelligence (AI) and its subfields, Machine Learning (ML) and Deep Learning (DL), are used for a variety of medical applications. It can help clinicians track the patient's illness cycle, assist with diagnosis, and offer appropriate therapy alternatives. Each approach employed may address one or more AI problems, such as segmentation, prediction, recognition, classification, and regression. However, the amount of AI-featured research on Inherited Retinal Diseases (IRDs) is currently limited. Thus, this study aims to examine artificial intelligence approaches used in managing Inherited Retinal Disorders, from diagnosis to treatment. A total of 20,906 articles were identified using the Natural Language Processing (NLP) method from the IEEE Xplore, Springer, Elsevier, MDPI, and PubMed databases, and papers submitted from 2010 to 30 October 2021 are included in this systematic review. The resultant study demonstrates the AI approaches utilized on images from different IRD patient categories and the most utilized AI architectures and models with their imaging modalities, identifying the main benefits and challenges of using such methods.

Abstract
Technology has been transforming the tourism industry and placing greater emphasis on offering differentiating and immersive tourist experiences. Tourists have assumed the position of content generators who interact with the regions and communities they visit, rather than mere passive visitors. This chapter explores the role of new technological advances (e.g., artificial intelligence, augmented reality, Internet of Things, big data) in the development of enriching experiences, having as a central element the positioning of the Douro River as a unique heritage element that is important to know and explore. The chapter explores a set of entrepreneurial initiatives in the Douro River that use technology to provide enriching experiences to its visitors in areas as distinct as river tourism, creative tourism, enotourism, or museology. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Network security encloses a wide set of technologies dealing with intrusions detection. Despite the massive adoption of signature-based network intrusion detection systems (IDSs), they fail in detecting zero-day attacks and previously unseen vulnerabilities exploits. Behaviour-based network IDSs have been seen as a way to overcome signature-based IDS flaws, namely through the implementation of machine-learning-based methods, to tolerate new forms of normal network behaviour, and to identify yet unknown malicious activities. A wide set of machine learning methods has been applied to implement behaviour-based IDSs with promising results on detecting new forms of intrusions and attacks. Innovative machine learning techniques have emerged, namely deep-learning-based techniques, to process unstructured data, speed up the classification process, and improve the overall performance obtained by behaviour-based network intrusion detection systems. The use of realistic datasets of normal and malicious networking activities is crucial to benchmark machine learning models, as they should represent real-world networking scenarios and be based on realistic computers network activity. This paper aims to evaluate CSE-CIC-IDS2018 dataset and benchmark a set of deep-learning-based methods, namely convolutional neural networks (CNN) and long short-term memory (LSTM). Autoencoder and principal component analysis (PCA) methods were also applied to evaluate features reduction in the original dataset and its implications in the overall detection performance. The results revealed the appropriateness of using the CSE-CIC-IDS2018 dataset to benchmark supervised deep learning models. It was also possible to evaluate the robustness of using CNN and LSTM methods to detect unseen normal activity and variations of previously trained attacks. The results reveal that feature reduction methods decreased the processing time without loss of accuracy in the overall detection performance.

Abstract
The subjectiveness of multimedia content description has a strong negative impact on tag-based information retrieval. In our work, we propose enhancing available descriptions by adding semantically related tags. To cope with this objective, we use a word embedding technique based on the Word2Vec neural network parameterized and trained using a new dataset built from online newspapers. A large number of news stories was scraped and pre-processed to build a new dataset. Our target language is Portuguese, one of the most spoken languages worldwide. The results achieved significantly outperform similar existing solutions developed in the scope of different languages, including Portuguese. Contributions include also an online application and API available for external use. Although the presented work has been designed to enhance multimedia content annotation, it can be used in several other application areas.