scholarly journals Citrus Huanglongbing Detection Based on Multi-Modal Feature Fusion Learning

2021 ◽  
Vol 12 ◽  
Author(s):  
Dai Fan ◽  
Fengcheng Wang ◽  
Dongzi Yang ◽  
Shaoming Lin ◽  
Xin Chen ◽  
...  
Keyword(s):  
Information Fusion ◽  
Feature Fusion ◽  
Hyperspectral Data ◽  
Source Information ◽  
Citrus Greening Disease ◽  
Citrus Huanglongbing ◽  
Rgb Images ◽  
Citrus Leaves ◽  
Image Network ◽  
Better Than

Citrus Huanglongbing (HLB), also named citrus greening disease, occurs worldwide and is known as a citrus cancer without an effective treatment. The symptoms of HLB are similar to those of nutritional deficiency or other disease. The methods based on single-source information, such as RGB images or hyperspectral data, are not able to achieve great detection performance. In this study, a multi-modal feature fusion network, combining a RGB image network and hyperspectral band extraction network, was proposed to recognize HLB from four categories (HLB, suspected HLB, Zn-deficient, and healthy). Three contributions including a dimension-reduction scheme for hyperspectral data based on a soft attention mechanism, a feature fusion proposal based on a bilinear fusion method, and auxiliary classifiers to extract more useful information are introduced in this manuscript. The multi-modal feature fusion network can effectively classify the above four types of citrus leaves and is better than single-modal classifiers. In experiments, the highest accuracy of multi-modal network recognition was 97.89% when the amount of data was not very abundant (1,325 images of the four aforementioned types and 1,325 pieces of hyperspectral data), while the single-modal network with RGB images only achieved 87.98% recognition and the single-modal network using hyperspectral information only 89%. Results show that the proposed multi-modal network implementing the concept of multi-source information fusion provides a better way to detect citrus HLB and citrus deficiency.

Multi-Source Information Fusion Based on Kalman Filtering

2015 ◽  
Vol 727-728 ◽  
pp. 863-866
Author(s):  
Meng Meng Zhou ◽  
G.M. Gao ◽  
Hong Bo Yang
Keyword(s):  
Kalman Filtering ◽  
Information Fusion ◽  
Attitude Determination ◽  
Low Frequency ◽  
Fusion Method ◽  
Source Information ◽  
Satellite Platform ◽  
Pointing Accuracy ◽  
Micro Vibration ◽  
Better Than

Thehigh-frequency angular micro-vibration on satellite platform results in theoptical axis pointing decreasing accuracy. The Kalman filtering based on attitudeinformation fusion method is presented to solve this case and improve the pointing accuracy of attitude determination. Thesimulation results indicate that the estimated accuracy of Kalman filteringattitude information fusion method is better than the result only fromconventional low frequency sensor. Accordingly, the attitude information fusionmethod is verified and accuracy.

scholarly journals Effect of Adjuvants on Oxytetracycline Uptake upon Foliar Application in Citrus

Antibiotics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 677
Author(s):  
Nabil Killiny ◽  
Faraj Hijaz ◽  
Pedro Gonzalez-Blanco ◽  
Shelley E. Jones ◽  
Myrtho O. Pierre ◽  
...  
Keyword(s):  
Foliar Application ◽  
Foliar Spray ◽  
Bacterial Pathogen ◽  
Water Addition ◽  
Candidatus Liberibacter ◽  
Citrus Huanglongbing ◽  
Liberibacter Asiaticus ◽  
Trunk Injection ◽  
Citrus Leaves ◽  
Target Effects

Recently in Florida, foliar treatments using products with the antibiotics oxytetracycline and streptomycin have been approved for the treatment of citrus Huanglongbing (HLB), which is caused by the putative bacterial pathogen ‘Candidatus Liberibacter asiaticus’. Herein, we assessed the levels of oxytetracycline and ‘Ca. L. asiaticus’ titers in citrus trees upon foliar applications with and without a variety of commercial penetrant adjuvants and upon trunk injection. The level of oxytetracycline in citrus leaves was measured using an oxytetracycline ELISA kit and ‘Ca. L. asiaticus’ titer was measured using quantitative PCR. Low levels of oxytetracycline were taken up by citrus leaves after foliar sprays of oxytetracycline in water. Addition of various adjuvants to the oxytetracycline solution showed minimal effects on its uptake by citrus leaves. The level of oxytetracycline in leaves from trunk-injected trees was higher than those treated with all foliar applications. The titer of ‘Ca. L. asiaticus’ in the midrib of leaves from trees receiving oxytetracycline by foliar application was not affected after four days and thirty days of application, whereas the titer was significantly reduced in oxytetracycline-injected trees thirty days after treatment. Investigation of citrus leaves using microscopy showed that they are covered by a thick lipidized cuticle. Perforation of citrus leaf cuticle with a laser significantly increased the uptake of oxytetracycline, decreasing the titer of ‘Ca. L. asiaticus’ in citrus leaves upon foliar application. Taken together, our findings indicate that trunk injection is more efficient than foliar spray even after the use of adjuvants. Our conclusion could help in setting useful recommendations for the application of oxytetracycline in citrus to improve tree health, minimize the amount of applied antibiotic, reduce environmental exposure, and limit off-target effects.

scholarly journals Spectroscopic and deep learning-based approaches to identify and quantify cerebral microhemorrhages

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Christian Crouzet ◽  
Gwangjin Jeong ◽  
Rachel H. Chae ◽  
Krystal T. LoPresti ◽  
Cody E. Dunn ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prussian Blue ◽  
Processing Speed ◽  
Digital Pathology ◽  
Ground Truth ◽  
Individual Variability ◽  
Rgb Images ◽  
Cerebral Microhemorrhages ◽  
Phasor Analysis ◽  
Better Than

AbstractCerebral microhemorrhages (CMHs) are associated with cerebrovascular disease, cognitive impairment, and normal aging. One method to study CMHs is to analyze histological sections (5–40 μm) stained with Prussian blue. Currently, users manually and subjectively identify and quantify Prussian blue-stained regions of interest, which is prone to inter-individual variability and can lead to significant delays in data analysis. To improve this labor-intensive process, we developed and compared three digital pathology approaches to identify and quantify CMHs from Prussian blue-stained brain sections: (1) ratiometric analysis of RGB pixel values, (2) phasor analysis of RGB images, and (3) deep learning using a mask region-based convolutional neural network. We applied these approaches to a preclinical mouse model of inflammation-induced CMHs. One-hundred CMHs were imaged using a 20 × objective and RGB color camera. To determine the ground truth, four users independently annotated Prussian blue-labeled CMHs. The deep learning and ratiometric approaches performed better than the phasor analysis approach compared to the ground truth. The deep learning approach had the most precision of the three methods. The ratiometric approach has the most versatility and maintained accuracy, albeit with less precision. Our data suggest that implementing these methods to analyze CMH images can drastically increase the processing speed while maintaining precision and accuracy.

Sign in / Sign up

Export Citation Format

Share Document