Abstract
The signal processing (SP) landscape has been enriched by recent advances in artificial intelligence (AI) and machine learning (ML), yielding new tools for signal estimation, classification, prediction, and manipulation. Layered signal representations, nonlinear function approximation and nonlinear signal prediction are now feasible at very large scale in both dimensionality and data size. These are leading to significant performance gains in a variety of long-standing problem domains like speech and Image analysis. As well as providing the ability to construct new classes of nonlinear functions (e.g., fusion, nonlinear filtering). This book will help academics, researchers, developers, graduate and undergraduate students to comprehend complex SP data across a wide range of topical application areas such as social multimedia data collected from social media networks, medical imaging data, data from Covid tests etc. This book focuses on AI utilization in the speech, image, communications and yirtual reality domains. © 2021 River Publishers. All rights reserved.

Abstract
[No abstract available]

Abstract
In the areas ofmachine learning / big data, when collecting data, sometimes too many features may be stored. Some of them may be redundant or irrelevant for the problem to be solved, adding noise to the dataset. Feature selection allows to create a subset from the original feature set, according to certain criteria. By creating a smaller subset of relevant features, it is possible to improve the learning accuracy while reducing the amount of data. This means means better results obtained in a shorter learning time. However, feature selection is normally regarded as a very important problem to be solved, as it directly impacts both data analysis and model creation. The problem of optimizing the selected features of a given dataset is not always trivial but, throughout the years, different ways to counter this optimization problem have been presented. This work presents how feature selection fits in the larger context of multi-objective problems as well as a review of how both multi-objective evolutionary algorithms and metaheuristics are being used in order to solve feature selection problems © MIR Labs, www.mirlabs.net/ijcisim/index.html

Abstract
In this article the influence of the maximum partition size on the performance of a discrete version of the Bat Algorithm (BA) is studied. The Bat Algorithm is a population-based meta-heuristic based on swarm intelligence developed for continuous problems with exceptional results. Thus, it has a set of parameters that must be studied in order to enhance the performance of the meta-heuristic. This paper aims to investigate whether the maximum size of the partitions used for the search operations throughout the algorithm should not also be considered as a parameter. First, a literature review was conducted, with special focus on the parameterization of the meta-heuristics and each of the parameters currently used in the algorithm, followed by its implementation in VBA in Microsoft Excel. After a thorough parameterization of the discrete algorithm, different maximum partition sizes were applied to 30 normally distributed instances to draw broader conclusions. In addition, they were also tested for different sizes of the problem to see if they had an influence on the results obtained. Finally, a statistical analysis was carried out, where it was possible to conclude that there was no maximum partition value for which superiority could be proven, and so the size of the partition should be considered a parameter in the bat algorithm and included in the parametrization of BA. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
The transport and logistics sector, which include freight forwarders companies, constitutes a vast network of entities that are central to a good performance in services. With the COVID-19 pandemic and its effects on the global economy, there was a huge shortage in the number of containers available, thus creating the need to optimize the loading of available equipment to avoid waste and maximize profits from each export. The present work presents a novel approach where a set of restrictions were created that, applied in synergy with the Non-Linear GRG algorithm, aim to allocate the boxes in different consecutive lines until forming a wall, and, therefore, the walls complete the container, in order to maximize the occupancy on it. To validate the proposed approach a prototype was developed and studied in real-world problem where the solutions resulted in occupations around 80% to 90%. Thus, we can foresee the importance of the proposed approach in decision-making regarding container consolidation services. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Over the past decades, underwater robotics has enjoyed growing popularity and relevance. While performing a mission, one crucial task for Autonomous Underwater Vehicles (AUVs) is bottom tracking, which should keep a constant distance from the seabed. Since static obstacles like walls, rocks, or shipwrecks can lie on the sea bottom, bottom tracking needs to be extended with obstacle avoidance. As AUVs face a wide range of uncertainties, implementing these essential operations is still challenging. A simple rule-based control method has been proposed in [7] to realize obstacle avoidance. In this work, we propose an alternative AI-based control method using a Long Short-Term Memory network. We compare the performance of both methods using real-world data as well as via a simulator. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.