Related references
Note: Only part of the references are listed.
Article
Engineering, Mechanical
Zohreh Mousavi et al.
Summary: This study proposes a novel vibration-based method for damage detection of real systems using Dictionary Learning (DL) based on a FE model and real intact state under different uncertainties. The method is validated using real measurements from an experimental offshore jacket model, and the results show higher accuracy in the case of changing working load.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
JoonHo Lee et al.
Summary: Unsupervised domain adaptation (UDA) aims to improve prediction performance in the target domain by minimizing the divergence between the source and target domains. This paper proposes a novel UDA method, called Model Uncertainty-based UDA (MUDA), which learns domain-invariant features to minimize domain divergence. MUDA utilizes a Bayesian framework and Monte Carlo dropout sampling to evaluate model uncertainty. Experimental results on image recognition tasks demonstrate the superiority of MUDA over existing state-of-the-art methods. MUDA is also extended to multi-source domain adaptation problems.
Article
Mechanics
Ioannis W. Kokkinakis et al.
Summary: This study examines the effects of nuclear blasts on humans inside buildings in moderately damaged areas. The results show that the forces exerted by the gusts of wind created inside the rooms can lift and throw a person off the ground, posing a risk of severe injury or death. However, there are specific areas within the rooms where individuals can avoid exposure to the highest wind forces.
Article
Computer Science, Artificial Intelligence
JoonHo Lee et al.
Summary: In this paper, a novel source-free unsupervised domain adaptation (UDA) method is proposed, which only uses a pre-trained source model and unlabeled target images for training. The method captures aleatoric uncertainty through data augmentation and trains the feature generator with two consistency objectives to improve the robustness of the adapted model to image perturbations. Experimental results on popular UDA benchmark datasets demonstrate that the proposed method is comparable or even superior to vanilla UDA methods.
Article
Multidisciplinary Sciences
V. M. Fernandez-Pacheco et al.
Summary: Air pollution is a significant concern in industrial or densely populated areas. Despite legislation, fixed-point air quality monitoring stations cannot provide information on the spatial evolution of pollutants. This research introduces a Computational Fluid Dynamics model to simulate pollutant dispersion in a large urban environment, specifically Gijon, Spain. The model examines the influence of terrain on pollutant dispersion and investigates the sources of diffuse industrial pollution in the city. It enables the identification of contaminated areas and the analysis of particle concentration variations. This research validates a methodology for generating numerical models to observe the spatial evolution of pollutants, which can be applied to future research on improving air quality in highly polluted environments.
SCIENTIFIC REPORTS
(2023)
Article
Environmental Sciences
Theodosios Kassandros et al.
Summary: A novel machine learning approach is proposed to enhance the dispersion modelling of road dust in urban areas. The approach combines various data sources such as road condition measurements, air quality forecasts, meteorological data, and road maintenance information through a ML based data fusion procedure. The results show that this approach improves the current model's capabilities and can be applied to a wide range of similar tasks.
ATMOSPHERIC ENVIRONMENT
(2023)
Article
Mathematics
Nicholas Christakis et al.
Summary: This paper presents the development of a novel algorithm called RUN-ICON for unsupervised learning. It aims to improve the reliability and confidence of unsupervised clustering by leveraging the K-means++ method and introducing novel metrics. The algorithm has notable characteristics such as robustness, high-quality clustering, automation, and flexibility, and extensive testing has demonstrated its capability to determine the optimal number of clusters under different scenarios. It will soon undergo rigorous testing in real-world scenarios to further prove its effectiveness.
Article
Geosciences, Multidisciplinary
Elena Fillola et al.
Summary: A machine learning emulator was developed to simulate Lagrangian particle dispersion models (LPDMs) footprints based on meteorological inputs. The emulator showed good performance in predicting the range and magnitude of footprints, providing a potential solution for large-scale applications.
GEOSCIENTIFIC MODEL DEVELOPMENT
(2023)
Article
Environmental Sciences
Mira Hulkkonen et al.
Summary: This study utilizes machine learning algorithms and techniques, such as ensemble learning, competitive learning, and unsupervised clustering, to analyze the changes in air pollution. By training models and predicting clusters, it becomes possible to accurately identify changes in ambient pollutants due to altered emissions. The results of the study demonstrate the feasibility of using machine learning for multivariate analysis and yield meaningful insights.
ATMOSPHERIC POLLUTION RESEARCH
(2022)
Review
Environmental Sciences
Mariya Pantusheva et al.
Summary: This article reviews the use of computational fluid dynamics (CFD) models to study air pollution dispersion in urban environments over the past decade. The review identifies issues such as the lack of specification of model aspects in some studies and the absence of verification and validation according to accepted standards. The findings provide insights into current research trends and identify areas for future improvement.
Article
Immunology
Maogui Hu et al.
Summary: The study found that there is a high transmission risk of COVID-19 among train passengers, but this risk varies significantly with co-travel time and seat location. As co-travel time increases, the risk of infection also increases, and measures should be taken to reduce transmission risk, such as increasing seat distance, reducing passenger density, and using personal hygiene protection.
CLINICAL INFECTIOUS DISEASES
(2021)
Article
Engineering, Chemical
Siyao Shao et al.
Summary: The lack of quantitative risk assessment of airborne transmission of COVID-19 under practical settings leads to uncertainties and inconsistencies in preventive measures. Ventilation design is critical for reducing the risk of particle encounters, inappropriate design can create hot spots with higher risks and enhance particle deposition causing surface contamination. Faceted particles from normal breathing are correlated with breathing depth.
JOURNAL OF AEROSOL SCIENCE
(2021)
Article
Mechanics
Talib Dbouk et al.
Summary: This study examines the impact of weather seasonality on virus transmission dynamics, introduces a new Airborne Infection Rate (AIR) index, and provides data evidence on how weather seasonality leads to two pandemic outbreaks per year.
Article
Construction & Building Technology
Elvire Katramiz et al.
Summary: The study found that infected individuals using lower PV flow rates in tandem seating and higher flow rates in face-to-face seating can achieve minimal exposure levels in an office setting. Additionally, the average inhaled intake fraction was 31% lower for face-to-face seating during coughing and 86% lower during breathing compared to tandem seating.
BUILDING AND ENVIRONMENT
(2021)
Article
Physics, Multidisciplinary
Meshal Shutaywi et al.
Summary: Grouping objects based on similarities is crucial in machine learning, with k-means and kernel k-means being popular clustering methods. This study extends previous work by introducing a weighted majority voting method based on NMI, and proposing an unsupervised weighting function based on the Silhouette index to improve clustering without the need for a training set.
Article
Environmental Sciences
Shushuai Mao et al.
Summary: A novel approach combining parameter sensitivity analysis and optimization methods was proposed to optimize source inversion performance by improving empirical schemes. Results showed significant improvements in predicting air pollutant concentrations and accuracy in source parameters through optimization of dispersion coefficients under different atmospheric conditions. The study provides valuable insights for obtaining accurate source information and enhancing air pollution management and emergency response.
ENVIRONMENTAL POLLUTION
(2021)
Article
Environmental Sciences
B. R. Rowe et al.
Summary: The paper develops a simple model to assess the inhaled flow rate of aerosol particles of respiratory origin and its connection to the probability of developing airborne diseases. It demonstrates that outdoor contamination risk is generally significantly lower than indoor risk, except for specific meteorological and topographical situations. The research sheds light on COVID19 spreading patterns in mountain valleys with temperature inversions compared to other less impacted areas.
ENVIRONMENTAL RESEARCH
(2021)
Article
Engineering, Environmental
Guannan Geng et al.
Summary: The study introduces a near real-time air pollutant database named Tracking Air Pollution in China (TAP), which combines ground observations, satellite AOD, and other data sources to provide daily 10 km resolution PM2.5 data. The database utilizes a two-stage machine learning model to estimate PM2.5 concentrations, improving performance at high pollution levels and filling gaps in AOD data. The availability of daily PM2.5 data for tracking changes over time and long-term records since 2000 will support policy assessments and health impact studies.
ENVIRONMENTAL SCIENCE & TECHNOLOGY
(2021)
Article
Thermodynamics
Manoj Kumar Satheesan et al.
BUILDING SIMULATION
(2020)
Article
Construction & Building Technology
Elvire Katramiz et al.
BUILDING AND ENVIRONMENT
(2020)
Article
Critical Care Medicine
Rajiv Dhand et al.
AMERICAN JOURNAL OF RESPIRATORY AND CRITICAL CARE MEDICINE
(2020)
Article
Mechanics
Talib Dbouk et al.
Editorial Material
Construction & Building Technology
Cees van Rijn et al.
Article
Mechanics
Mohamed Abuhegazy et al.
Article
Mechanics
Talib Dbouk et al.
Article
Environmental Sciences
Rochelle Schneider et al.
Article
Computer Science, Information Systems
Xuesong Yan et al.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2019)
Article
Multidisciplinary Sciences
Dmitry Krotov et al.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2019)
Article
Biochemical Research Methods
Z. Mousavi et al.
JOURNAL OF NEUROSCIENCE METHODS
(2019)
Article
Computer Science, Artificial Intelligence
Pasi Franti et al.
PATTERN RECOGNITION
(2019)
Article
Construction & Building Technology
Shuo-Jun Mei et al.
SUSTAINABLE CITIES AND SOCIETY
(2019)
Review
Chemistry, Multidisciplinary
Yves Rybarczyk et al.
APPLIED SCIENCES-BASEL
(2018)
Article
Engineering, Chemical
V. Golkarfard et al.
ADVANCED POWDER TECHNOLOGY
(2014)
Article
Multidisciplinary Sciences
G. E. Hinton et al.
