Abstract
Digital Twin (DT) is recognized as a key enabling technology of Industry 4.0 and 5.0 and can be used in collaborative networks formed to fulfillment of complex tasks of the manufacturing industry. In the last years, the variety and complexity of DTs have been significantly increasing with new technologies and smarter solutions. The current definition of DT, such as cognitive, hybrid, and others, embraces a wide range of solutions with different aspects. In this sense, this article discusses DT definitions and presents a five-dimensional analytical framework to classify the different proposals. Finally, to better understand the proposal, we analyzed 12 articles using the analytical framework. We argue this research may help researchers and practitioners to better understand digital twins and compare different solutions.

Abstract
Road transportation emissions have increased in the last few decades and have been the primary source of pollutants in urban areas with ever-growing populations. In this context, it is important to have effective measures to monitor road emissions in regions. Creating an emission inventory over a region that can map the road emission based on the vehicle trips can be helpful for this. In this work, we show that it is possible to use raw GPS data to measure levels of pollution in a region. By transforming the data using feature engineering and calculating the vehicle-specific power (VSP), we show the areas with higher emissions levels made by a fleet of taxis in Porto, Portugal. The Uber H3 grid system is used to decompose the city into hexagonal grids to sample nearby data points into a region. We validate our experiments on real-world sensor datasets deployed in several city regions, showing the correlation with VSP and true values for several pollutants attesting to the method's usefulness.

Abstract
Background and Objective: Convolutional neural networks are widely used to detect radiological findings in chest radiographs. Standard architectures are optimized for images of relatively small size (for exam-ple, 224 x 224 pixels), which suffices for most application domains. However, in medical imaging, larger inputs are often necessary to analyze disease patterns. A single scan can display multiple types of radi-ological findings varying greatly in size, and most models do not explicitly account for this. For a given network, whose layers have fixed-size receptive fields, smaller input images result in coarser features, which better characterize larger objects in an image. In contrast, larger inputs result in finer grained features, beneficial for the analysis of smaller objects. By compromising to a single resolution, existing frameworks fail to acknowledge that the ideal input size will not necessarily be the same for classifying every pathology of a scan. The goal of our work is to address this shortcoming by proposing a lightweight framework for multi-scale classification of chest radiographs, where finer and coarser features are com-bined in a parameter-efficient fashion. Methods: We experiment on CheXpert, a large chest X-ray database. A lightweight multi-resolution (224 x 224, 4 48 x 4 48 and 896 x 896 pixels) network is developed based on a Densenet-121 model where batch normalization layers are replaced with the proposed size-specific batch normalization. Each input size undergoes batch normalization with dedicated scale and shift parameters, while the remaining parameters are shared across sizes. Additional external validation of the proposed approach is performed on the VinDr-CXR data set. Results: The proposed approach (AUC 83 . 27 +/- 0 . 17 , 7.1M parameters) outperforms standard single-scale models (AUC 81 . 76 +/- 0 . 18 , 82 . 62 +/- 0 . 11 and 82 . 39 +/- 0 . 13 for input sizes 224 x 224, 4 48 x 4 48 and 896 x 896, respectively, 6.9M parameters). It also achieves a performance similar to an ensemble of one individual model per scale (AUC 83 . 27 +/- 0 . 11 , 20.9M parameters), while relying on significantly fewer parameters. The model leverages features of different granularities, resulting in a more accurate classifi-cation of all findings, regardless of their size, highlighting the advantages of this approach. Conclusions: Different chest X-ray findings are better classified at different scales. Our study shows that multi-scale features can be obtained with nearly no additional parameters, boosting performance. (c) 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )

Abstract
Trajectory clustering is one of the most important issues in mobility patterns data mining. It is applied in several cases such as hot-spots detection, urban transportation control, animal migration movements, and tourist visiting routes among others. In this paper, we describe how to identify the most frequent trajectories from raw GPS data. By making use of the Ramer-Douglas-Peucker (RDP) mechanism we simplify the trajectories in order to obtain fewer points to check without losing information. We construct a similarity matrix by using the Fréchet distance metric and then employ density-based clustering to find the most similar trajectories. We perform experiments over three real-world datasets collected in the city of Porto, Portugal, and in Beijing China, and check the results of the most frequent trajectories for the top-k origins x destinations for the moves. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Children represent a specific group of road traffic accident (RTA) victims. Performing a personal injury assessment (PIA) on a child presents a significant challenge, especially when assessing permanent disabilities and needs. However, medico-legal recommendations for PIA in such cases are lacking. The main objective of this study was to analyse the differences between children and a young- and middle-aged adult population of RTA victims to contribute to the development of relevant guidelines. Secondary objectives were to identify and characterize specifics of children's posttraumatic damages regarding: (i) temporary and permanent outcomes; and (ii) medico-legal damage parameters in the Portuguese context. We performed a retrospective study of RTA victims by comparing two groups (n = 114 each) matched for acute injury severity (SD = 0.01): G1 (children) and G2 (young- and middle-aged adults). Logistic regression was used to estimate the odds ratios. G1 presented a greater chance of evolving without or with less severe body, functional and situational outcomes (three-dimensional assessment methodology), and with lower permanent functional disability values than G2. Our findings suggest that childhood trauma generally has a better prognosis than trauma in young- and middle-aged adults. This study generated evidence on the subject and highlighted the most significant difficulties encountered by medico-legal experts when performing PIA in children.

Abstract
Distributed Machine Learning, in which data and learning tasks are scattered across a cluster of computers, is one of the answers of the field to the challenges posed by Big Data. Still, in an era in which data abounds, decisions must still be made regarding which specific data to use on the training of the model, either because the amount of available data is simply too large, or because the training time or complexity of the model must be kept low. Typical approaches include, for example, selection based on data freshness. However, old data are not necessarily outdated and might still contain relevant patterns. Likewise, relying only on recent data may significantly decrease data diversity and representativity, and decrease model quality. The goal of this paper is to compare different heuristics for selecting data in a distributed Machine Learning scenario. Specifically, we ascertain whether selecting data based on their characteristics (meta-features), and optimizing for maximum diversity, improves model quality while, eventually, allowing to reduce model complexity. This will allow to develop more informed data selection strategies in distributed settings, in which the criteria are not only the location of the data or the state of each node in the cluster, but also include intrinsic and relevant characteristics of the data. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.