Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Intelligent Underwater Object Detection and Image Restoration for Autonomous Underwater Vehicles

  • Fayaz, Sheezan
  • Parah, Shabir A.
  • Qureshi, G.J.
  • Del Ser, Javier
  • Khan Muhammad,
  • Lloret, Jaime|||0000-0002-0862-0533
[EN] Unmanned Underwater Vehicles (UUVs) have been reliable and economical technological solutions to perform undersea monitoring tasks in comparison to manned vehicles. However, in many situations, UUV is unable to fulfill complex undersea research tasks since target objects appear distorted due to light absorption and scattering. Besides, ocean surveying undergoes severe power requirements compared to terrestrial systems because of battery-driven low-storage vehicles like Unmanned Underwater Vehicles (UUVs). Therefore, limited power supply, motion resistance of water medium, and distorted target object appearance can delay the mission and reduce the efficiency of UUV in their underwater operations. Considering the resource-constrained undersea monitoring setup, we propose an intelligent two-stage framework for expeditious monitoring of underwater scenes. First, an effective deep neural network is employed for underwater object/region of interest (ROI) detection. Then the detected ROI is restored using an efficient restoration method, thereby improving the visual quality of the degraded images and aiding the navigating and monitoring tasks of UUVs. Our method has been objectively and subjectively assessed using 9 evaluation metrics and our key results reveal mAP of 94.35% and an Underwater Color Image Quality Evaluation (UCIQE) score of 3.09, surpassing state-of-the-art methods for object detection. Furthermore, the execution time of 0.550 secs is required for object detection and dehazing, making this proposal suitable for UUVs to perform automatic undersea object detection and dehazing within operational running requirements., This work was supported in part by the Department of Electronics and Instrumentation Technology, funded by the Indian Government through Science and Heritage Research Initiative (SHRI) scheme under Grant DST/TDT/SHRI-33/2018. The work of J. Del Ser was supported by the Basque Government through ELKARTEK and EMAITEK funds, and in part by the Consolidated Research Group MATHMODE under Grant IT1456 22.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Impact of outdoor air pollution on severity and mortality in COVID-19 pneumonia

  • García-García, Fernando
  • Bronte, Olaia
  • Lee, Dae-Jin
  • Urrutia Landa, Isabel
  • Uranga, Ane
  • Nieves Ermecheo, Mónica
  • Quintana, José María
  • Arostegui, Inmaculada
  • Zalacain, Rafael
  • Ruiz-Iturriaga, Ainhize
  • Serrano, Laura
  • Menéndez, Rosario
  • Mendez, R
  • Torres, Antoni
  • Martínez-Minaya, Joaquín|||0000-0002-1016-8734
[EN] The relationship between exposure to air pollution and the severity of coronavirus disease 2019 (COVID-19) pneumo-nia and other outcomes is poorly understood. Beyond age and comorbidity, risk factors for adverse outcomes including death have been poorly studied. The main objective of our study was to examine the relationship between exposure to outdoor air pollution and the risk of death in patients with COVID-19 pneumonia using individual-level data. The sec-ondary objective was to investigate the impact of air pollutants on gas exchange and systemic inflammation in this dis-ease. This cohort study included 1548 patients hospitalised for COVID-19 pneumonia between February and May 2020 in one of four hospitals. Local agencies supplied daily data on environmental air pollutants (PM10, PM2.5, O3, NO2, NO and NOX) and meteorological conditions (temperature and humidity) in the year before hospital admission (from Jan-uary 2019 to December 2019). Daily exposure to pollution and meteorological conditions by individual postcode of residence was estimated using geospatial Bayesian generalised additive models. The influence of air pollution on pneumonia severity was studied using generalised additive models which included: age, sex, Charlson comorbidity index, hospital, average income, air temperature and humidity, and exposure to each pollutant. Additionally, general-ised additive models were generated for exploring the effect of air pollution on C-reactive protein (CRP) level and SpO2/FiO2 at admission. According to our results, both risk of COVID-19 death and CRP level increased significantly with median exposure to PM10, NO2, NO and NOX, while higher exposure to NO2, NO and NOX was associated with lower SpO2/FiO2 ratios. In conclusion, after controlling for socioeconomic, demographic and health-related variables, we found evidence of a significant positive relationship between air pollution and mortality in patients hospitalised for COVID-19 pneumonia. Additionally, inflammation (CRP) and gas exchange (SpO2/FiO2) in these patients were signif-icantly related to exposure to air pollution., This research work was partially funded by the Spanish Respiratory and Thoracic Surgery Association (SEPAR) [grant number 004-2021].This research was also partially funded by the Department of Education of the Basque Government through an Artificial Intelligence in BCAM grant [grant number 00432-2019], the Mathematical Modelling Applied to Health' strategy, the BERC 2018-2021 & amp; 2022-2025 programmes and the Consolidated Research Group MATHMODE [IT1456-22]; and by the Spanish Ministry of Science, Innovation and Universities under BCAM Severo Ochoa accreditation SEV-2017-0718, as well as by the Spanish State Research Agency (AEI) through project S3M1P4R [PID2020-115882RB-I00].