Abstract
Anaphora resolution is one of the problems in natural language processing. It is the process of disambiguating the antecedent of a referring expression from the set of entities in a discourse. The correct interpretation of pronouns plays an important role in the construction of meaning Thus, the resolution of pronominal anaphors remains a very important task for many natural language processing applications. Additionally, it plays an increasingly significant role in computational linguistics. However, a significant amount of work on anaphora resolution is focused on English; anaphora resolution for other languages, including Arabic, is still limited. In this paper, we present a new set of computational and linguistic features to resolve Arabic anaphors using a machine learning approach. In this paper, an in-depth study was conducted on a set of computational and linguistic features to exploit their effectiveness and investigate their effect on anaphora resolution. The aim was to efficiently integrate different feature sets and classification algorithms to synthesize a more accurate classification procedure. Four well-known machine learning algorithms k-nearest neighbor, maximum entropy, decision tree and meta-classifier, were employed as base-classifiers for each of the feature sets. A wide range of comparative experiments on Quran datasets was conducted, the discussion presented, and conclusions were drawn. The experimental results show that our approach gives satisfactory results. (C) 2021 The Authors. Published by Elsevier B.V.

Abstract
In this work we use the concept of paraxial fluids of light to explore quantum turbulence, probing a turbulent regime induced on an optical beam propagating inside a defocusing nonlinear media. For that purpose, we establish a physical analogue of a two-component quantum fluid by making use of orthogonal polarizations and incoherent beam interaction, obtaining a system for which the perturbative excitations follow a modified Bogoliubov-like dispersion relation. This dispersion relation features regions of instability that define an effective range of energy injection and that are easily tuned by manipulating the relative angle of incidence between the two components. Our numerical results support the predictions and show evidence of direct and inverse turbulent cascades expected from weak wave turbulence theories, which may inspire new ways to explore to quantum turbulence with optical analogues.

Abstract
The materials used in the transport industry have been changing in the last decades. The traditional and heavy steel have been switching by the light alloys like aluminum alloys. However, despite their advantages as low density and high corrosion resistance, the manufacturing process, especially fusion welding, is very demanding and challenging. In the transport industry, most of the hyperstatic components made in aluminum alloys are welded manually with the associate financial costs as well as the lack of quality and repeatability. For these reasons, it is urgent to develop new methodologies to automate this process. The present work intends to show a scientific method to automate the welding process of hyperstatic frames, very common in bicycles, made in aluminum alloy. This methodology involves two steps, the first one in which is performed numerical simulations to determine the optimal welding parameters to minimize the distortion and residual stresses. The second step is experimental one, and it is created an automated welding cell with a robot to weld the frames. It has been proved that it is possible to obtain welding aluminum frames with acceptable quality in agreement with the ASME IX standard. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

Abstract
Modern containerized distributed systems, such as big data storage and processing stacks or micro-service based applications, are inherently hard to monitor and optimize, as resource usage does not directly match hardware resources due to multiple virtualization layers. For instance, inter-application traffic is an important factor in as it directly indicates how components interact, it has not been possible to accurately monitor it in an application independent way and without severe overhead, thus putting it out of reach of cloud platforms. In this paper we present an efficient black-box monitoring approach for gathering detailed structural information of collaborating processes in a distributed system that can be queried for various purposes, as it includes both information about processes, containers, and hosts, as well as resource usage and amount of data exchanged. The key to achieving high detail and low overhead without custom application instrumentation is to use a kernel-aided event driven strategy. We validate a prototype implementation by applying it to multi-platform microservice deployments, evaluate its performance with micro-benchmarks, and demonstrate its usefulness for container placement in a distributed data storage and processing stack (i.e., Cassandra and Spark).

Abstract
This paper analyzes the activation of the manual balancing reserve of the Portuguese system and its prices for the period 2015-2017. Standard, logistic and LASSO regression models, causal analysis based on Bayesian networks and random forests are applied. Results show that the variables that better explain the activation of the manual reserve are the imbalances of both renewable generation and demand, but surprisingly forecasted with persistence models based on the last verified measurements (available 15 minutes before the reserve activation), instead of using more elaborated models based on production forecasts. Prices, however, are harder to explain suggesting the need for additional information, such as bidding prices not used in this study.

Abstract
Medical image quality assessment plays an important role not only in the design and manufacturing processes of image acquisition but also in the optimization of decision support systems. This work introduces a new deep ordinal learning approach for focus assessment in whole slide images. From the blurred image to the focused image there is an ordinal progression that contains relevant knowledge for more robust learning of the models. With this new method, it is possible to infer quality without losing ordinal information about focus since instead of using the nominal cross-entropy loss for training, ordinal losses were used. Our proposed model is contrasted against other state-of-the-art methods present in the literature. A first conclusion is a benefit of using data-driven methods instead of knowledge-based methods. Additionally, the proposed model is found to be the top-performer in several metrics. The best performing model scores an accuracy of 94.4% for a 12 classes classification problem in the FocusPath database.