Fant 9855 publikasjoner. Viser side 111 av 395:
2011
Potato plant disease detection: leveraging hybrid deep learning models
Agriculture, a crucial sector for global economic development and sustainable food production, faces significant challenges in detecting and managing crop diseases. These diseases can greatly impact yield and productivity, making early and accurate detection vital, especially in staple crops like potatoes. Traditional manual methods, as well as some existing machine learning and deep learning techniques, often lack accuracy and generalizability due to factors such as variability in real-world conditions. This study proposes a novel approach to improve potato plant disease detection and identification using a hybrid deep-learning model, EfficientNetV2B3+ViT. This model combines the strengths of a Convolutional Neural Network - EfficientNetV2B3 and a Vision Transformer (ViT). It has been trained on a diverse potato leaf image dataset, the “Potato Leaf Disease Dataset”, which reflects real-world agricultural conditions. The proposed model achieved an accuracy of 85.06, representing an 11.43 improvement over the results of the previous study. These results highlight the effectiveness of the hybrid model in complex agricultural settings and its potential to improve potato plant disease detection and identification.
BioMed Central (BMC)
2025
2007
2017
2002
2013
Background
Quantitative measurements of cerebrospinal fluid to blood clearance has previously not been established for neurological diseases. Possibly, variability in cerebrospinal fluid clearance may affect the underlying disease process and may possibly be a source of under- or over-dosage of intrathecally administered drugs. The aim of this study was to characterize the cerebrospinal fluid to blood clearance of the intrathecally administered magnetic resonance imaging contrast agent gadobutrol (Gadovist, Bayer Pharma AG, GE). For this, we established a population pharmacokinetic model, hypothesizing that cerebrospinal fluid to blood clearance differs between cerebrospinal fluid diseases.
Methods
Gadobutrol served as a surrogate tracer for extra-vascular pathways taken by several brain metabolites and drugs in cerebrospinal fluid. We estimated cerebrospinal fluid to blood clearance in patients with different cerebrospinal fluid disorders, i.e. symptomatic pineal and arachnoid cysts, as well as tentative spontaneous intracranial hypotension due to cerebrospinal fluid leakage, idiopathic intracranial hypertension, or different types of hydrocephalus (idiopathic normal pressure hydrocephalus, communicating- and non-communicating hydrocephalus). Individuals with no verified cerebrospinal fluid disturbance at clinical work-up were denoted references.
Results
Population pharmacokinetic modelling based on 1,140 blood samples from 161 individuals revealed marked inter-individual variability in pharmacokinetic profiles, including differences in absorption half-life (time to 50% of tracer absorbed from cerebrospinal fluid to blood), time to maximum concentration in blood and the maximum concentration in blood as well as the area under the plasma concentration time curve from zero to infinity. In addition, the different disease categories of cerebrospinal fluid diseases demonstrated different profiles.
Conclusions
The present observations of considerable variation in cerebrospinal fluid to blood clearance between individuals in general and across neurological diseases, may suggest that defining cerebrospinal fluid to blood clearance can become a useful diagnostic adjunct for work-up of cerebrospinal fluid disorders. We also suggest that it may become useful for assessing clearance capacity of endogenous brain metabolites from cerebrospinal fluid, as well as measuring individual cerebrospinal fluid to blood clearance of intrathecal drugs.
2022
2004
2005
2004
2001
POP model intercomparison study. Stage II. Comparison of mass balance estimates and sensitivity studies. DRAFT. EMEP/MSC-E Technical Report, 4/2005
2005
POP model intercomparison study. Stage II. Comparison of mass balance estimates and sensitivity studies. EMEP/MSC-E Technical Report, 5/2006
2006
POP model intercomparison study. Stage 1. Comparison of descriptions of main processes determining POP behaviour in various environmental compartments. EMEP MSC-E Technical Report, 1/2004
2004
2007
2006
2008
Polycyclic Aromatic Hydrocarbons Not Declining in Arctic Air Despite Global Emission Reduction
Two decades of atmospheric measurements of polycyclic aromatic hydrocarbons (PAHs) were conducted at three Arctic sites, i.e., Alert, Canada; Zeppelin, Svalbard; and Pallas, Finland. PAH concentrations decrease with increasing latitude in the order of Pallas > Zeppelin > Alert. Forest fire was identified as an important contributing source. Three representative PAHs, phenanthrene (PHE), pyrene (PYR), and benzo[a]pyrene (BaP) were selected for the assessment of their long-term trends. Significant decline of these PAHs was not observed contradicting the expected decline due to PAH emission reductions. A global 3-D transport model was employed to simulate the concentrations of these three PAHs at the three sites. The model predicted that warming in the Arctic would cause the air concentrations of PHE and PYR to increase in the Arctic atmosphere, while that of BaP, which tends to be particle-bound, is less affected by temperature. The expected decline due to the reduction of global PAH emissions is offset by the increment of volatilization caused by warming. This work shows that this phenomenon may affect the environmental occurrence of other anthropogenic substances, such as more volatile flame retardants and pesticides.
2019