Abstract
Public databases for glaucoma studies contain color images of the retina, emphasizing the optic papilla. These databases are intended for research and standardized automated methodologies such as those using deep learning techniques. These techniques are used to solve complex problems in medical imaging, particularly in the automated screening of glaucomatous disease. The development of deep learning techniques has demonstrated potential for implementing protocols for large-scale glaucoma screening in the population, eliminating possible diagnostic doubts among specialists, and benefiting early treatment to delay the onset of blindness. However, the images are obtained by different cameras, in distinct locations, and from various population groups and are centered on multiple parts of the retina. We can also cite the small number of data, the lack of segmentation of the optic papillae, and the excavation. This work is intended to offer contributions to the structure and presentation of public databases used in the automated screening of glaucomatous papillae, adding relevant information from a medical point of view. The gold standard public databases present images with segmentations of the disc and cupping made by experts and division between training and test groups, serving as a reference for use in deep learning architectures. However, the data offered are not interchangeable. The quality and presentation of images are heterogeneous. Moreover, the databases use different criteria for binary classification with and without glaucoma, do not offer simultaneous pictures of the two eyes, and do not contain elements for early diagnosis.

Abstract
The Internet of Things (IoT) emerged to describe a network of connected things on a large scale to offer services to a large number of applications in different environments and domains. Middleware is software that seeks to facilitate the management and communication of all these things, providing the necessary functionalities to manage things, to discover, to compose services, and perform communication. For this reason, several proposals for middleware solutions for IoT have been developed. In this article, we conducted a systematic review of the literature to bring together middleware solutions for IoT, identifying the requirements and communication protocols used. In addition, we present some gaps and directions for future research in the development of IoT middleware.

Abstract
Multi-modal Machine Translation (MMT) enables the use of visual information to enhance the quality of translations. The visual information can serve as a valuable piece of context information to decrease the ambiguity of input sentences. Despite the increasing popularity of such a technique, good and sizeable datasets are scarce, limiting the full extent of their potential. Hausa, a Chadic language, is a member of the Afro-Asiatic language family. It is estimated that about 100 to 150 million people speak the language, with more than 80 million indigenous speakers. This is more than any of the other Chadic languages. Despite a large number of speakers, the Hausa language is considered low-resource in natural language processing (NLP). This is due to the absence of sufficient resources to implement most NLP tasks. While some datasets exist, they are either scarce, machine-generated, or in the religious domain. Therefore, there is a need to create training and evaluation data for implementing machine learning tasks and bridging the research gap in the language. This work presents the Hausa Visual Genome (HaVG), a dataset that contains the description of an image or a section within the image in Hausa and its equivalent in English. To prepare the dataset, we started by translating the English description of the images in the Hindi Visual Genome (HVG) into Hausa automatically. Afterward, the synthetic Hausa data was carefully post-edited considering the respective images. The dataset comprises 32,923 images and their descriptions that are divided into training, development, test, and challenge test set. The Hausa Visual Genome is the first dataset of its kind and can be used for Hausa-English machine translation, multi-modal research, and image description, among various other natural language processing and generation tasks.

Abstract
This article presents two single-phase to single-phase three-wire converters based on two-level and three-level neutral-point-clamped legs. The converters present a shared-leg between the grid and load. A space-vector pulsewidth modulation technique considering the harmonic distortion and the semiconductor losses is presented, besides the dc-link voltage-balance technique to balance the neutral-point voltage. The converters can supply the loads with constant amplitude and frequency under grid voltage disturbances. These characteristics make the proposed converters suitable for applications as uninterrupted power supply. The proposed converters are compared to a conventional two-level converter from simulated results for evaluating the semiconductor losses and harmonic distortion. The experimental results are provided to illustrate and validate the operation of the proposed systems.

Abstract
Robotic process automation (RPA) is a recent technology that has recently become increasingly adopted by companies as a solution for employees to focus on higher complexity and more valuable tasks while delegating routine, monotonous and rule-based tasks to their digital colleagues. The increased interest, reflected in the increasing number of articles regarding approaches and test cases, has triggered the necessity for a summary that could extract the more generalisable ideas and concepts about these software robots. This paper used a Systematic Literature Review (SLR) approach to find and synthesise information from articles obtained on this subject. This research identified the most general implementation approaches of successful RPA adoption cases, observed benefits, challenges commonly faced by organisations, characteristics that make processes more suitable for RPA, and research gaps in the current literature. The findings presented in this paper have two purposes. The first is to provide a way for companies and organisations to become more familiar with good practices regarding the adoption of robotic process automation. The second is to foster further research on the subject by complementing the current knowledge and proposing new paths for research. © 2022 D. A. da Silva Costa et al.

Abstract
With the advent of self-driving cars and the push by large companies into fully driverless transportation services, monitoring passenger behaviour in vehicles is becoming increasingly important for several reasons, such as ensuring safety and comfort. Although several human action recognition (HAR) methods have been proposed, developing a true HAR system remains a very challenging task. If the dataset used to train a model contains a small number of actors, the model can become biased towards these actors and their unique characteristics. This can cause the model to generalise poorly when confronted with new actors performing the same actions. This limitation is particularly acute when developing models to characterise the activities of vehicle occupants, for which data sets are short and scarce. In this study, we describe and evaluate three different methods that aim to address this actor bias and assess their performance in detecting in-vehicle violence. These methods work by removing specific information about the actor from the model's features during training or by using data that is independent of the actor, such as information about body posture. The experimental results show improvements over the baseline model when evaluated with real data. On the Hanau03 Vito dataset, the accuracy improved from 65.33% to 69.41%. On the Sunnyvale dataset, the accuracy improved from 82.81% to 86.62%.