Abstract
Throughout this article the execution of the motion planning for a robotic manipulator by means of Reinforcement Learning methods is studied. Towards this, an implementation based on a Wire and loop game is used as an example case to be solved. The loop is controlled in a single plane as the endeffector of the manipulator. The modeling of the problem and the process of training the agent is detailed. This allowed for the verification of the capacity of a learning based method, having produced, under the considered abstractions, satisfying results by gaining the capability of completing the path imposed by the wire in 23 seconds.

Abstract
Managing company knowledge and using it effectively is more than ever a strong competitive advantage in the business world. The scientific area of knowledge management and knowledge management systems have been intensively studied in the last years; however, we still see the unstructured implementation of knowledge management systems in organizations, the misalignment of knowledge management systems from the business model and the frustration non-use, lack of systems integration and/or non-return on investment made either in technology or spent on heavy implementation processes. The state-of-the-art conducted during this study, showed that most knowledge management systems alignment models in the business context have a strong focus on the organizational dimension, e.g., culture, organizational processes, organizational structure, and leadership, having been identified only three models that also cover, simultaneous, the technological and strategic dimension. Our final objective in this study is, following the research survey methodology, to develop a proposed framework for the strategic alignment of knowledge management systems that can support company managers in their decision-making, and to contribute to the development of scientific knowledge in this area.

Abstract
Traffic flow forecasting is an essential component of an intelligent transportation system to mitigate congestion. Recurrent neural networks, particularly gated recurrent units and long short-term memory, have been the stateof-the-art traffic flow forecasting models for the last few years. However, a more sophisticated and resilient model is necessary to effectively acquire long-range correlations in the time-series data sequence under analysis. The dominant performance of transformers by overcoming the drawbacks of recurrent neural networks in natural language processing might tackle this need and lead to successful time-series forecasting. This article presents a multi-head attention based transformer model for traffic flow forecasting with a comparative analysis between a gated recurrent unit and a long-short term memory-based model on PeMS dataset in this context. The model uses 5 heads with 5 identical layers of encoder and decoder and relies on Square Subsequent Masking techniques. The results demonstrate the promising performance of the transform-based model in predicting long-term traffic flow patterns effectively after feeding it with substantial amount of data. It also demonstrates its worthiness by increasing the mean squared errors and mean absolute percentage errors by (1.25 - 47.8)% and (32.4 - 83.8)%, respectively, concerning the current baselines.

Abstract
This study explores the resistive switching phenomena present in 4 mu m(2) amorphous Indium-Gallium-Zinc Oxide (IGZO) memristors. Despite being extensively reported in the literature, not many studies detail the mechanisms that dominate conduction on the different states of IGZO-based devices. In this article, we demonstrate that resistive switching occurs due to the modulation of the Schottky barrier present at the bottom interface of the device. Furthermore, thermionic field emission and field emission regimes are identified as the dominant conduction mechanisms at the high resistive state of the device, while the bulk-limited ohmic conduction is found at the low resistive state. Due to the high complexity associated with creating compact models of resistive switching, a data-driven model is drafted taking systematic steps. (C) 2022 Author(s).

Abstract
The instruments developed for the upcoming Extremely Large Telescopes (ELTs) will need efficient adaptive optics (AO) systems to correct the effects of the atmospheric turbulence and allow imaging at the highest angular resolution. One of the most important requirements for ELT AO-assisted instruments will be to deliver diffraction-limited images in a significant part of the sky. For that, the instruments will be equipped with laser guide stars (LGSs) providing most of the information required by AO instruments. But even with LGSs, AO systems still require the use of natural guide stars (NGSs) to compensate for image motion (jitter) and some low order aberrations. These NGSs are eventually limiting the fraction of the sky that can be achieved by AO systems, the so-called sky coverage (SC). We first present the SC assessment methods used for high angular resolution monolithic optical and near-infrared integral field spectrograph (HARMONI) and multiconjugate adaptive optics relay/multi-AO imaging camera for deep observations (MAORY/MICADO), that are both instruments for the ELT of the European Southern Observatory (ESO). They are based on a semianalytical description of the main contributors in the AO error budget, allowing for a fast estimation of the residual jitter. As such, these methods are well suited for statistical estimation of the SC on multiple science fields and/or to efficiently explore the system parameter space. We then compute the SC of the two instruments in cosmological fields from the cosmic assembly near-IR deep extragalactic legacy survey catalog. The goal is to provide an insight on the possibilities given by two different types of tomographic AO systems, i.e., laser tomography AO with HARMONI and multiconjugate AO with MAORY, on the same telescope. In particular, we show that HARMONI and MAORY/MICADO are complementary, meaning that the overall SC of ESO's ELT is much improved for applications common to both systems. (C) The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License.

Abstract
With the increasing penetration of distributed generations (DGs) in three-phase distribution networks, the traditional radial passive distribution networks are gradually transformed into active distribution networks (ADNs) with DGs, accompanied by a dramatic increase in operational scenarios. To fast analyze the massive scenarios of ADNs, this brief proposes a multi-scenario-based power flow analytical method based on the multi-dimensional holomorphic embedding method. First, DGs are partitioned according to their spatial correlation, and then a power flow analytical method is cast for unbalanced three-phase ADNs. Finally, the method is applied to the ADN power flow analysis for multiple scenarios. Comparisons with other power flow calculation methods validate the high efficiency and computational tractability of the proposed method.