EAGNet: A method for automatic extraction of agricultural greenhouses from high spatial resolution remote sensing images based on hybrid multi-attention

Li, Hongzhou; Gan, Yuhang; Yu-jie, WU; Guo, Li

doi:10.1016/j.compag.2022.107431

Cited by 15 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cycling test was applied to sample sensors which are emphasized above as G2S, W1S, B2C, and W1C. Electrical resistances of the sensors were examined after each 2 1 , 2 2 , 2 3 , 2 4 , 2 5 , 2 6 , 2 7 , 2 8 , 2 9 , and 2 10 bending cycles, separately. Figure 9(a) shows the repeatability of the sensors particularly electrical resistance change after sensors subjected to repeated bending/cyclic.…”

Section: Results Of the Printed E-textile Based Humidity Sensors' Per...mentioning

confidence: 99%

“…The bending and cycling test was applied to sensors to simulate movement against wind. The effect of this movement on electrical resistance change was examined after 2 1 , 2 2 , 2 3 , 2 4 , 2 5 , 2 6 , 2 7 , 2 8 , 2 9 , and 2 10 cycles. The cycling test was accomplished by James H. Heal by Titan 2 Strength Tester machine, and BS 4952 (2,4) test method was applied.…”

Section: Measurement Of the Printed E-textile Based Humidity Sensors ...mentioning

confidence: 99%

“…The fact that these products take more or less water than they need damage the crops and soil [7,8]. The purpose of greenhouses at this point is to take the necessary precautions against weather conditions, and provide protection by acting as a cover in the production of fruit trees, and other types of vegetables [9]. Wireless sensor network (WSN) for temperature, humidity, water supply measurement and irrigation systems in agriculture and greenhouses help farmers achieve high yields by reducing costs [10].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Flexible humidity sensor for smart agricultural applications

Tekcin,

Tuzer Hamzaoglu,

Kursun

2023

Flex. Print. Electron.

View full text Add to dashboard Cite

The increase in food production due to the need for food brought by the increasing world population from year to year necessitates production at high quality and in much larger quantities in every season. In order to grow fruit and vegetables efficiently, sensors that measure ambient temperature and humidity are needed in greenhouses. Two different flexible and resistant textile-based humidity sensors that can measure the humidity at higher levels (80%, 90%, and 100% RH) were designed and printed directly on the four different greenhouse fabrics using silver and carbon conductive inks. Fabric thickness, weight, tensile, tear strength, elongation, abrasion, air permeability, water permeability tests for evaluating various physical and mechanical properties of specimen fabrics to be used for the sensor were carried out. In addition, depending on the humidity value in the environment, the sensor performance was tested based on sensor electrical resistance measurements with respect to repeated bending/cyclic tests, rubbing, UV exposure/ weatherability (against UV and raining) tests. Moreover, some important features of the sensors such as hysteresis, repeatability, response time have been also examined. Statistical analyses showed that the sensor designs and type of conductive inks had significant effects on the performance of the humidity sensors and the best sensor performance was obtained with the polypropylene coated fabric using design II and silver based conductive ink. The fabricated textile based flexible humidity sensors detect the change in relative humidity levels from 80%RH to 100%RH accurately and achieve good durability, and repeatability even after prolonged UV exposure and raining. Thus, the developed textile-based flexible humidity sensor might be useful for future smart agricultural applications.

show abstract

Section: Results Of the Printed E-textile Based Humidity Sensors' Per...mentioning

confidence: 99%

Section: Measurement Of the Printed E-textile Based Humidity Sensors ...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Flexible humidity sensor for smart agricultural applications

Tekcin,

Tuzer Hamzaoglu,

Kursun

2023

Flex. Print. Electron.

View full text Add to dashboard Cite

show abstract

“…Recall indicates the percentage of correctly classified WW pixels over all actual WW, calculated as follows [51]:…”

Section: Confusion Matrix Winter Wheat Non-winter Wheatmentioning

confidence: 99%

“…F1-score is the weighted average of precision and recall. The value range is 0-1, and the larger the value, the higher the model accuracy, which is calculated as follows [51]:…”

Section: Confusion Matrix Winter Wheat Non-winter Wheatmentioning

confidence: 99%

A Spatial Distribution Extraction Method for Winter Wheat Based on Improved U-Net

et al. 2023

View full text Add to dashboard Cite

This paper focuses on the problems of omission, misclassification, and inter-adhesion due to overly dense distribution, intraclass diversity, and interclass variability when extracting winter wheat (WW) from high-resolution images. This paper proposes a deep supervised network RAunet model with multi-scale features that incorporates a dual-attention mechanism with an improved U-Net backbone network. The model mainly consists of a pyramid input layer, a modified U-Net backbone network, and a side output layer. Firstly, the pyramid input layer is used to fuse the feature information of winter wheat at different scales by constructing multiple input paths. Secondly, the Atrous Spatial Pyramid Pooling (ASPP) residual module and the Convolutional Block Attention Module (CBAM) dual-attention mechanism are added to the U-Net model to form the backbone network of the model, which enhances the feature extraction ability of the model for winter wheat information. Finally, the side output layer consists of multiple classifiers to supervise the results of different scale outputs. Using the RAunet model to extract the spatial distribution information of WW from GF-2 imagery, the experimental results showed that the mIou of the recognition results reached 92.48%, an improvement of 2.66%, 4.15%, 1.42%, 2.35%, 3.76%, and 0.47% compared to FCN, U-Net, DeepLabv3, SegNet, ResUNet, and UNet++, respectively. The superiority of the RAunet model in high-resolution images for WW extraction was verified in effectively improving the accuracy of the spatial distribution information extraction of WW.

show abstract

Comprehensive comparison of modified deep convolutional neural networks for automated detection of external and middle ear conditions

Akyol

2024

Neural Comput & Applic

View full text Add to dashboard Cite

Otitis media disease, a frequent childhood ailment, could have severe repercussions, including mortality. This disease induces permanent hearing loss, commonly seen in developing countries with limited medical resources. It is estimated that approximately 21,000 people worldwide die from reasons related to this disease each year. The main aim of this study is to develop a model capable of detecting external and middle ear conditions. Experiments were conducted to find the most successful model among the modified deep convolutional neural networks within two scenarios. According to the results, the modified EfficientNetB7 model could detect normal, chronic otitis media, earwax, myringosclerosis cases with high accuracy in Scenario 2. This model offers average values of 99.94% accuracy, 99.86% sensitivity, 99.95% specificity, and 99.86% precision. An expert system based on this model is expected to provide a second opinion to doctors in detecting external and middle ear conditions, particularly in primary healthcare institutions and hospitals lacking field specialists.

show abstract

EAGNet: A method for automatic extraction of agricultural greenhouses from high spatial resolution remote sensing images based on hybrid multi-attention

Cited by 15 publications

References 31 publications

Flexible humidity sensor for smart agricultural applications

Flexible humidity sensor for smart agricultural applications

A Spatial Distribution Extraction Method for Winter Wheat Based on Improved U-Net

Comprehensive comparison of modified deep convolutional neural networks for automated detection of external and middle ear conditions

Contact Info

Product

Resources

About