Gabriel O. Flores-Aquino, Octavio Gutierrez-Frias, Juan Irving Vasquez
Path planning algorithms fundamentally aim to compute collision-free paths, with many works focusing on finding the optimal distance path. However, for several applications, a more suitable approach is to balance response time, path safety, and path length. In this context, a skeleton map is a useful tool in graph-based schemes, as it provides an intrinsic representation of the free workspace. However, standard skeletonization algorithms are computationally expensive, as they are primarly oriented towards image processing tasks. We propose an efficient path-planning methodology that finds safe paths within an acceptable processing time. This methodology leverages a Deep Denoising Autoencoder (DDAE) based on the U-Net architecture to compute a skeletonized version of the navigation map, which we refer to as SkelUnet. The SkelUnet network facilitates exploration of the entire workspace through one-shot sampling (OSS), as opposed to the iterative or probabilistic sampling used by previous algorithms. SkelUnet is trained and tested on a dataset consisting of 12,500 two-dimensional dungeon maps. The motion planning methodology is evaluated in a simulation environment with an Unmanned Aerial Vehicle (UAV) in 250 previously unseen maps and assessed using several navigation metrics to quantify the navigability of the computed paths. The results demonstrate that using SkelUnet to construct the roadmap offers significant advantages, such as connecting all regions of free workspace, providing safer paths, and reducing processing time.
Carmen Cabrera, Miguel González-Leonardo, Andrea Nasuto
et al.
Urban mobility is central to economic activity, social inclusion, and access to essential services. COVID-19 caused disruptions to mobility globally, yet its long-term impacts in less developed countries remain poorly understood. Using over 170 million anonymised mobile phone records from Meta-Facebook users in Argentina, Chile, and Colombia (March 2020 to May 2022), we find sustained changes in mobility across socioeconomic and rural-urban gradients. We reveal that mobility recorded the sharpest declines and remained below pre-pandemic levels in most high-density and low socio-economic deprivation areas, while low-density and more deprived communities returned to baseline. These differences reflect the scale of the initial mobility shock rather than subsequent recovery rates. Net mobility to urban cores remained consistently below pre-pandemic levels, suggesting a shift in their functional role. By revealing how COVID-19 reinforced mobility-related inequalities, we contribute novel evidence for planners and policymakers seeking to build more inclusive and resilient mobility systems.
Christoffer Loeffler, Andrea Martínez Freile, Tomás Rey Pizarro
This study addresses the growing concern of information asymmetry in consumer contracts, exacerbated by the proliferation of online services with complex Terms of Service that are rarely even read. Even though research on automatic analysis methods is conducted, the problem is aggravated by the general focus on English-language Machine Learning approaches and on major jurisdictions, such as the European Union. We introduce a new methodology and a substantial dataset addressing this gap. We propose a novel annotation scheme with four categories and a total of 20 classes, and apply it on 50 online Terms of Service used in Chile. Our evaluation of transformer-based models highlights how factors like language- and/or domain-specific pre-training, few-shot sample size, and model architecture affect the detection and classification of potentially abusive clauses. Results show a large variability in performance for the different tasks and models, with the highest macro-F1 scores for the detection task ranging from 79% to 89% and micro-F1 scores up to 96%, while macro-F1 scores for the classification task range from 60% to 70% and micro-F1 scores from 64% to 80%. Notably, this is the first Spanish-language multi-label classification dataset for legal clauses, applying Chilean law and offering a comprehensive evaluation of Spanish-language models in the legal domain. Our work lays the ground for future research in method development for rarely considered legal analysis and potentially leads to practical applications to support consumers in Chile and Latin America as a whole.
Hugo Massaroli, Hernan Chaves, Pilar Anania
et al.
Deep learning models have shown strong performance in diagnosing Alzheimer's disease (AD) using neuroimaging data, particularly 18F-FDG PET scans, with training datasets largely composed of North American cohorts such as those in the Alzheimer's Disease Neuroimaging Initiative (ADNI). However, their generalization to underrepresented populations remains underexplored. In this study, we benchmark convolutional and Transformer-based models on the ADNI dataset and assess their generalization performance on a novel Latin American clinical cohort from the FLENI Institute in Buenos Aires, Argentina. We show that while all models achieve high AUCs on ADNI (up to .96, .97), their performance drops substantially on FLENI (down to .82, .80, respectively), revealing a significant domain shift. The tested architectures demonstrated similar performance, calling into question the supposed advantages of transformers for this specific task. Through ablation studies, we identify per-image normalization and a correct sampling selection as key factors for generalization. Occlusion sensitivity analysis further reveals that models trained on ADNI, generally attend to canonical hypometabolic regions for the AD class, but focus becomes unclear for the other classes and for FLENI scans. These findings highlight the need for population-aware validation of diagnostic AI models and motivate future work on domain adaptation and cohort diversification.
According to the Pan American Health Organization, the number of cancer cases in Latin America was estimated at 4.2 million in 2022 and is projected to rise to 6.7 million by 2045. Osteosarcoma, one of the most common and deadly bone cancers affecting young people, is difficult to detect due to its unique texture and intensity. Surgical removal of osteosarcoma requires precise safety margins to ensure complete resection while preserving healthy tissue. Therefore, this study proposes a method for estimating the confidence interval of surgical safety margins in osteosarcoma surgery around the knee. The proposed approach uses MRI and X-ray data from open-source repositories, digital processing techniques, and unsupervised learning algorithms (such as k-means clustering) to define tumor boundaries. Experimental results highlight the potential for automated, patient-specific determination of safety margins.
Olga Zamaraeva, Lorena S. Allegue, Carlos Gómez-Rodríguez
et al.
Automatic grammar coaching serves an important purpose of advising on standard grammar varieties while not imposing social pressures or reinforcing established social roles. Such systems already exist but most of them are for English and few of them offer meaningful feedback. Furthermore, they typically rely completely on neural methods and require huge computational resources which most of the world cannot afford. We propose a grammar coaching system for Spanish that relies on (i) a rich linguistic formalism capable of giving informative feedback; and (ii) a faster parsing algorithm which makes using this formalism practical in a real-world application. The approach is feasible for any language for which there is a computerized grammar and is less reliant on expensive and environmentally costly neural methods. We seek to contribute to Greener AI and to address global education challenges by raising the standards of inclusivity and engagement in grammar coaching.
Nana Mgbechikwere Nwachukwu, Jennafer Shae Roberts, Laura N Montoya
To harness the true potential of Artificial Intelligence (AI) for societal betterment, we need to move away from prioritising corporate interests which exploit Global South workers in the digital age. The unpaid labour and societal harms which are generated by Digital Value Networks (DVNs) disproportionately affect workers in Africa, Latin America, and India and need to be regulated. In this research, we discuss unethical practices to automate Human Intelligence Tasks (HITs) through gig work platforms and the capitalisation of data collection utilising influencers in social media. These are important areas of study in worker and user data practices, where ethical AI could be impactful. We provide suggestions for a path forward focused on responsible AI development.
Eloy Peña-Asensio, Josep M. Trigo-Rodríguez, Albert Rimola
et al.
The extraordinary weather conditions available between February and March 2022 over Spain have allowed us to analyze the brightest fireballs recorded by the monitoring stations of the Spanish Meteor Network (SPMN). We study the atmospheric flight of 15 large meteoroids to determine if they are meteorite dropper events to prepare campaigns to search for freshly fallen extraterrestrial material. We investigate their origins in the Solar System and their dynamic association with parent bodies and meteoroid streams. Employing our Python pipeline 3D-FireTOC, we reconstruct the atmospheric trajectory utilizing ground-based multi-station observations and compute the heliocentric orbit. In addition, we apply an ablation model to estimate the initial and terminal mass of each event. Using a dissimilarity criterion and propagating backward in time, we check the connection of these meteoroids with known complexes and near-Earth objects. We also calculate if the orbits are compatible with recent meteoroid ejections. We find that ~27% of these fireballs are dynamically associated with minor meteoroid streams and exhibit physical properties of cometary bodies, as well as one associated with a near-Earth asteroid. We identify two meteorite-producing events; however, the on-site search was unsuccessful. By considering that these fireballs are mostly produced by cm-sized rocks that might be the fragmentation product of much larger meteoroids, our findings emphasize the idea that the population of near-Earth objects is a source of near-term impact hazards, existing large Earth-colliding meteoroids in the known complexes.
CARMENES is a next-generation instrument being built by a consortium of German and Spanish institutions to carry out a survey of 300 M-type dwarf stars with the goal of detecting exoearths by radial-velocity measurements. To collect relevant information from different on-line catalogues for a given sample of 209 binary or multiple star systems, formed by F, G or K primary star and an M-dwarf (or late-K) companion. To prove if the pair is indeed a physical pair, to obtain different metallicity calibrations in K-band with these binary systems. The data compilation from every star has been done searching in catalogues in VizieR and the literature. In addition, physical pair checking has been done studying the collected proper motions from both stars (primary and secondary) and using two tools from the Virtual Observatory: Aladin and TopCat. From a list of suitable systems, two different types of calibrations had been obtained: spectroscopic and photometric. In order to determine these calibrations, we have considered that metallicity from the primary star, determined by the CARMENES UCM research group, is equal to the secondary star.
Felipe González-Pizarro, Andrea Figueroa, Claudia López
et al.
While there is increasing global attention to data privacy, most of their current theoretical understanding is based on research conducted in a few countries. Prior work argues that people's cultural backgrounds might shape their privacy concerns; thus, we could expect people from different world regions to conceptualize them in diverse ways. We collected and analyzed a large-scale dataset of tweets about the #CambridgeAnalytica scandal in Spanish and English to start exploring this hypothesis. We employed word embeddings and qualitative analysis to identify which information privacy concerns are present and characterize language and regional differences in emphasis on these concerns. Our results suggest that related concepts, such as regulations, can be added to current information privacy frameworks. We also observe a greater emphasis on data collection in English than in Spanish. Additionally, data from North America exhibits a narrower focus on awareness compared to other regions under study. Our results call for more diverse sources of data and nuanced analysis of data privacy concerns around the globe.
Este artigo tem por objetivo analisar os impactos socioambientais provocados pelo processo de verticalização urbana movido na cidade de Campina Grande/PB, no recorte compreendido entre a década de 1960 até o ano de 2012, período em que se tem a construção dos três primeiros edifícios da cidade até o momento auge da verticalização urbana do município. Para tanto, as fontes utilizadas constituem-se de entrevistas obtidas por meio da metodologia em História Oral, fontes fotográficas, jornalísticas e o Plano Diretor Municipal, publicado em 1996 e atualizado em 2006. O campo teórico-metodológico utilizado baseia-se nos expoentes da História Ambiental. Buscamos a partir deste trabalho fomentar uma discussão acerca das transformações urbanas que nos cercam e os seus impactos ao meio ambiente, problematizando, assim, o ideário de “desenvolvimento” e “progresso” que justificam projetos de urbanização.
Genaro J. Martínez, Magali Cárdenas Tapia, Ricardo Antonio Tena Núñez
et al.
Actually, after one year it is recognized that the evolution of COVID-19 is different in each country or region around the world. In this paper, we do a revision to the date about COVID-19 evolution in Mexico, we explain where the main epicenter and states with most high impact. Mexico has a particular geographical position in the American continent because it is a natural bridge between the USA and Latin America, that represents a special point of propagation because between other facts this virus is transported by people of different nationalities migrating to the USA. The research in this paper helps to understand why Mexico is one of the countries with the most high mortality impact by this new virus and how the lockdown works in the population. Finally, we give a practical perspective as this evolution is a complex system.
Thaislayne Nunes de Oliveira, Mônica de Castro Maia Senna
Este artigo tem como objetivo central examinar a trajetória histórica das políticas de controle do câncer de mama feminino no Brasil em diferentes momentos históricos. As primeiras intervenções públicas nessa direção no país surgiram em meados do século XX e visavam ao desenvolvimento do cuidado oncológico de maneira individual. A intensificação das medidas estratégicas para o seu controle ocorreu somente a partir dos anos 2000, com perceptível desenvolvimento de ações coletivas e incentivo à prevenção, de maneira a incidir diretamente no controle da doença. O estudo contou com pesquisa bibliográfica sobre a temática, associada à análise dos documentos oficiais, como: normativas, portarias e legislações nacionais. Os resultados demonstram avanços na estruturação do cuidado da doença, sobretudo pela implantação de políticas, programas e sistemas específicos. Tais avanços estratégicos contribuem positivamente para o controle de riscos e agravos da doença. Mas, apesar desses avanços, a realidade observada ainda permanece em certo descompasso, perceptível pelo elevado e crescente índice de mortalidade.
The Magellanic Clouds were known before Magellan's voyage exactly 500 years ago, and were not given that name by Magellan himself or his chronicler Antonio Pigafetta. They were, of course, already known by local populations in South America, such as the Mapuche and Tupi-Guaranis. The Portuguese called them Clouds of the Cape, and scientific circles had long used the name of Nubecula Minor and Major. We trace how and when the name Magellanic Clouds came into common usage by following the history of exploration of the southern hemisphere and the southern sky by European explorers. While the name of Magellan was quickly associated to the Strait he discovered (within about 20 years only), the Clouds got their final scientific name only at the end of the 19th century, when scientists finally abandoned Latin as their communication language.
André Bargão, Rodrigo Banha da Silva, Sara Ferreira
et al.
Fundado em 1492, o Hospital Real de Todos-os-Santos revelou-se paradigmático em Portugal no que à assistência diz respeito. Inovador nos mais diversos campos merece especial atenção a inspiração arquitetónica renascentista, que se traduziu em novos hábitos no quotidiano hospitalar. De planta cruciforme e integrando quatro pátios, a água esteve presente através de, pelo menos, quatro estruturas hidráulicas/poços, cada uma afecta a um claustro e, consequentemente, às suas dependências térreas, no decorrer dos quase três séculos de
funcionamento deste grande complexo público.
Este texto analisa as estruturas hidráulicas do Hospital Real de Todos-os-Santos descobertas aquando das intervenções arqueológicas na Praça da Figueira na década de 60 e em 1999-2001, integradas nos vários momentos de reformulação arquitetónica do edifício, estudados no âmbito do projeto «Hospital Real de Todos-os-Santos: a Cidade e a Saúde». Além de elemento vital para o seu funcionamento, estas estruturas são um espelho de hábitos e atribuições funcionais dos espaços envolventes.
Arts in general, Museums. Collectors and collecting
Chagas disease American trypanosomiasis is caused by a flagellated parasite: trypanosoma cruzi, transmitted by an insect of the genus Triatoma and also by blood transfusions. In Latin America the number of infected people is approximately 6 million, with a population exposed to the risk of infection of 550000. It is our interest to develop a non-invasive, low-cost methodology, capable of detecting any alteration early on cardiaca produced by T. cruzi. We analyzed the 24 hour RR records in patients with ECG abnormalities (CH2), patients without ECG alterations (CH1) who had positive serological findings for Chagas disease and healthy (Control) matched by sex and age. We found significant differences between the Control, CH1 and CH2 groups that show dysautonomy and enervation of the autonomic nervous system.