Percorrer por data de Publicação, começado por "2025-11-10"
A mostrar 1 - 4 de 4
Resultados por página
Opções de ordenação
- Air pollution forecasting using autoencoders: A classification-based prediction of NO2, PM10, and SO2 concentrationsPublication . Rodríguez-García, María Inmaculada; Carrasco-García, María Gema; Cubillas Fernández, Paloma Rocío; Ribeiro, Conceição; Cardoso, Pedro; Turias, Ignacio. J.This study aims to evaluate and compare the performance of Autoencoders (AEs) and Sparse Autoencoders (SAEs) in forecasting the next-hour concentration levels of various air pollutants—specifically NO2(t + 1), PM10(t + 1), and SO2(t + 1)—in the Bay of Algeciras, a highly complex region located in southern Spain. Hourly data related to air quality, meteorological conditions, and maritime traffic were collected from 2017 to 2019 across multiple monitoring stations distributed throughout the bay, enabling the analysis of diverse forecasting scenarios. The output variable was segmented into four distinct, non-overlapping quartiles (Q1–Q4) to capture different concentration ranges. AE models demonstrated greater accuracy in predicting moderate pollution levels (Q2 and Q3), whereas SAE models achieved comparable performance at the lower and upper extremes (Q1 and Q4). The results suggest that stacking AE layers with varying degrees of sparsity—culminating in a supervised output layer—can enhance the model’s ability to forecast pollutant concentration indices across all quartiles. Notably, Q4 predictions, representing peak concentrations, benefited from more complex SAE architectures, likely due to the increased difficulty associated with modelling extreme values.
- Molecular hallmarks of neurodegeneration in polyglutamine spinocerebellar ataxiasPublication . Nóbrega, Clévio; Marcelo, Adriana; Vieira da Conceição, André Filipe; Encarnação Estevam, Bernardo Alexandre; Rajado, Ana Teresa; Albuquerque Andrade de Matos, Carlos Adriano; Vilhena Catarino Brito, David; Torquato Afonso, Inês; Antunes Codêsso, José Miguel; Koppenol, Rebekah; Costa, Rafael Gomes da; Afonso Reis, Ricardo António; Paulino, Rodrigo; Gomes, TiagoPolyglutamine spinocerebellar ataxias (PolyQ SCAs) comprise a group of six inherited rare neurodegenerative diseases. They are caused by abnormal mutation of a CAG tract in six otherwise unrelated genes, leading to a complex cascade of molecular events that culminate in neuronal death. Based on decades of research in these diseases, this review identifies and categorizes the distinctive hallmarks involved in the molecular pathogenesis of PolyQ SCAs. We organized these molecular signatures into three groups: (i) primary hallmarks, which directly refer to the transcription and translation of the abnormally expanded gene and protein, respectively; (ii) secondary hallmarks, which include alterations in pathways and organelles that are implicated in the disease pathogenesis; and iii) end-stage hallmarks, which highlight the final events of the pathogenesis cascade in PolyQ SCAs. This framework is expected to provide a platform for understanding the complex network of molecular mechanisms involved in these diseases and to guide current and future efforts in developing therapies.
- Editorial: tissue crosstalk in obesity and diabetes: a focus on skeletal musclePublication . De Sousa-Coelho, Ana Luísa; Estêvão, Maria Dulce da Mota Antunes de Oliveira ; Patti, Mary Elizabeth; Lerin, CarlesIn the complex biological system of higher organisms, the maintenance of metabolic homeostasis requires intricate crosstalk among different tissues and organs. Such inter-organ communication, including classical hormones, other peptides, and extracellular vesicles (EVs), allows one tissue to affect metabolic pathways in a distant tissue. Dysregulation of this communication contributes to human pathologies, including obesity, diabetes, liver diseases, and certain cancers. This Research Topic aimed to shed light onto the complex tissue crosstalk underlying metabolic diseases, specifically obesity and type 2 diabetes (T2D). It highlights the latest scientific evidence exploring such interactions among different tissues, with a specific focus on the role of skeletal muscle and its secretion of myokines and EVs that contribute to the regulation of metabolism in liver, adipose tissue, and other organs.
- Air pollution forecasting using autoencoders: a classification-based prediction of NO2, PM10, and SO2 concentrationsPublication . Rodríguez-García, María Inmaculada; Carrasco-García, María Gema; Fernández, Paloma Rocío Cubillas; Ribeiro, Conceição; Cardoso, Pedro; Turias, Ignacio. J.This study aims to evaluate and compare the performance of Autoencoders (AEs) and Sparse Autoencoders (SAEs) in forecasting the next-hour concentration levels of various air pollutants—specifically NO2(t + 1), PM10(t + 1), and SO2(t + 1)—in the Bay of Algeciras, a highly complex region located in southern Spain. Hourly data related to air quality, meteorological conditions, and maritime traffic were collected from 2017 to 2019 across multiple monitoring stations distributed throughout the bay, enabling the analysis of diverse forecasting scenarios. The output variable was segmented into four distinct, non-overlapping quartiles (Q1–Q4) to capture different concentration ranges. AE models demonstrated greater accuracy in predicting moderate pollution levels (Q2 and Q3), whereas SAE models achieved comparable performance at the lower and upper extremes (Q1 and Q4). The results suggest that stacking AE layers with varying degrees of sparsity—culminating in a supervised output layer—can enhance the model’s ability to forecast pollutant concentration indices across all quartiles. Notably, Q4 predictions, representing peak concentrations, benefited from more complex SAE architectures, likely due to the increased difficulty associated with modelling extreme values.