This study deployed k-means clustering to formulate earthquake categories based on magnitude and consequence,using global earthquake data spanning from 1900 to 2021.Based on patterns within the historical data,numeric...This study deployed k-means clustering to formulate earthquake categories based on magnitude and consequence,using global earthquake data spanning from 1900 to 2021.Based on patterns within the historical data,numeric boundaries were extracted to categorize the magnitude,deaths,injuries,and damage caused by earthquakes into low,medium,and high classes.Following a future earthquake incident,the classification scheme can be utilized to assign earthquakes into appropriate categories by inputting the magnitude,number of fatalities and injuries,and monetary estimates of total damage.The resulting taxonomy provides a means of classifying future earthquake incidents,thereby guiding the allocation and deployment of disaster management resources in proportion to the specific characteristics of each incident.Furthermore,the scheme can serve as a reference tool for auditing the utilization of earthquake management resources.展开更多
Medical image reconstruction aims to acquire high-quality medical images for clinical usage at minimal cost and risk to the patients.Deep learning and its applications in medical imaging,especially in image reconstruc...Medical image reconstruction aims to acquire high-quality medical images for clinical usage at minimal cost and risk to the patients.Deep learning and its applications in medical imaging,especially in image reconstruction have received considerable attention in the literature in recent years.This study reviews records obtained elec-tronically through the leading scientific databases(Magnetic Resonance Imaging journal,Google Scholar,Scopus,Science Direct,Elsevier,and from other journal publications)searched using three sets of keywords:(1)Deep learning,image reconstruction,medical imaging;(2)Medical imaging,Deep learning,Image reconstruction;(3)Open science,Open imaging data,Open software.The articles reviewed revealed that deep learning-based re-construction methods improve the quality of reconstructed images qualitatively and quantitatively.However,deep learning techniques are generally computationally expensive,require large amounts of training datasets,lack decent theory to explain why the algorithms work,and have issues of generalization and robustness.The challenge of lack of enough training datasets is currently being addressed by using transfer learning techniques.展开更多
文摘This study deployed k-means clustering to formulate earthquake categories based on magnitude and consequence,using global earthquake data spanning from 1900 to 2021.Based on patterns within the historical data,numeric boundaries were extracted to categorize the magnitude,deaths,injuries,and damage caused by earthquakes into low,medium,and high classes.Following a future earthquake incident,the classification scheme can be utilized to assign earthquakes into appropriate categories by inputting the magnitude,number of fatalities and injuries,and monetary estimates of total damage.The resulting taxonomy provides a means of classifying future earthquake incidents,thereby guiding the allocation and deployment of disaster management resources in proportion to the specific characteristics of each incident.Furthermore,the scheme can serve as a reference tool for auditing the utilization of earthquake management resources.
基金This research was made possible through the Dutch organization NWO-WOTRO(Grants No.W 07.303.101:‘A sustainable MRI system to diagnose hydrocephalus in Uganda’).
文摘Medical image reconstruction aims to acquire high-quality medical images for clinical usage at minimal cost and risk to the patients.Deep learning and its applications in medical imaging,especially in image reconstruction have received considerable attention in the literature in recent years.This study reviews records obtained elec-tronically through the leading scientific databases(Magnetic Resonance Imaging journal,Google Scholar,Scopus,Science Direct,Elsevier,and from other journal publications)searched using three sets of keywords:(1)Deep learning,image reconstruction,medical imaging;(2)Medical imaging,Deep learning,Image reconstruction;(3)Open science,Open imaging data,Open software.The articles reviewed revealed that deep learning-based re-construction methods improve the quality of reconstructed images qualitatively and quantitatively.However,deep learning techniques are generally computationally expensive,require large amounts of training datasets,lack decent theory to explain why the algorithms work,and have issues of generalization and robustness.The challenge of lack of enough training datasets is currently being addressed by using transfer learning techniques.
