Performance Comparison of Base CNN Models in Transfer Learning for Crop Diseases Classification

2021 ◽  
Vol 44 (3) ◽  
pp. 33-38
Author(s):  
Hyoup-Sang Yoon ◽  
◽  
Seok-Bong Jeong
Keyword(s):  
Transfer Learning ◽  
Performance Comparison ◽  
Crop Diseases

The Implementation of A Crop Diseases APP Based on Deep Transfer Learning

2020 ◽  
Author(s):  
Mengji Yang ◽  
Daiwei Li ◽  
Minquan Chen ◽  
Abdelaziz Bouras ◽  
Yiqian Tang ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Crop Diseases

scholarly journals Deep Learning for Early Detection, Identification, and Spatiotemporal Monitoring of Plant Diseases Using Multispectral Aerial Imagery

2021 ◽  
Author(s):  
◽  
Joseph Mbugua
Keyword(s):  
Deep Learning ◽  
Early Detection ◽  
Transfer Learning ◽  
Near Infrared ◽  
Spectral Band ◽  
Classification Systems ◽  
Plant Diseases ◽  
Aerial Imagery ◽  
Classification Models ◽  
Crop Diseases

Production of food crops is hampered by the proliferation of crop diseases which cause huge harvest losses. Current crop-health monitoring programs involve the deployment of scouts and experts to detect and identify crop diseases through visual observation. These monitoring schemes are expensive and too slow to offer timely remedial recommendations for preventing the spread of these crop-damaging diseases. There is thus a need for the development of cheaper and faster methods for identifying and monitoring crop diseases. Recent advances in deep learning have enabled the development of automatic and accurate image classification systems. These advances coupled with the widespread availability of multispectral aerial imagery provide a cost-effective method for developing crop-diseases classification tools. However, large datasets are required to train deep learning models, which may be costly and difficult to obtain. Fortunately, models trained on one task can be repurposed for different tasks (with limited data) using transfer learning technique. The purpose of this research was to develop and implement an end-to-end deep learning framework for early detection and continuous monitoring of crop diseases using transfer learning and high resolution, multispectral aerial imagery. In the first study, the technique was used to compare the performance of five pre-trained deep learning convolutional neural networks (VGG16, VGG19, ResNet50, Inception V3, and Xception) in classifying crop diseases for apples, grapes, and tomatoes. The results of the study show that the best performing crop-disease classification models were those trained on the VGG16 network, while those trained on the ResNet50 network had the worst performance. The other studies compared the performance of using transfer learning and different three-band color combinations to train single- and multiple-crop classification models. The results of these studies show that models combining red, near infrared, and blue bands performed better than models trained with the traditional visible spectral band combination of red, green, and blue. The worst performing models were those combining near infrared, green, and blue bands. This research recommends that further studies be undertaken to determine the best band combinations for training single- and multi-label classification models for both crops and plants and diseases that affect them.

Direct ammonia fueled solid oxide fuel cells: A comprehensive review on challenges, opportunities and future outlooks

2020 ◽  
pp. 70-91 ◽  
Author(s):  
Molla Asmare ◽  
Mustafa Ilbas
Keyword(s):  
Electric Power ◽  
Energy Demand ◽  
Renewable Energy Sources ◽  
Clean Energy ◽  
Performance Comparison ◽  
Optimum Operating ◽  
Practical Implementation ◽  
Human Society ◽  
Energy Access ◽  
Green Fuel

Nowadays, the most decisive challenges we are fronting are perfectly clean energy making for equitable and sustainable modern energy access, and battling the emerging alteration of the climate. This is because, carbon-rich fuels are the fundamental supply of utilized energy for strengthening human society, and it will be sustained in the near future. In connection with this, electrochemical technologies are an emerging and domineering tool for efficiently transforming the existing scarce fossil fuels and renewable energy sources into electric power with a trivial environmental impact. Compared with conventional power generation technologies, SOFC that operate at high temperature is emerging as a frontrunner to convert the fuels chemical energy into electric power and permits the deployment of varieties of fuels with negligible ecological destructions. According to this critical review, direct ammonia is obtained as a primary possible choice and price-effective green fuel for T-SOFCs. This is because T-SOFCs have higher volumetric power density, mechanically stable, and high thermal shocking resistance. Also, there is no sealing issue problem which is the chronic issues of the planar one. As a result, the toxicity of ammonia to use as a fuel is minimized if there may be a leakage during operation. It is portable and manageable that can be work everywhere when there is energy demand. Besides, manufacturing, onboard hydrogen deposition, and transportation infrastructure connected snags of hydrogen will be solved using ammonia. Ammonia is a low-priced carbon-neutral source of energy and has more stored volumetric energy compared with hydrogen. Yet, to utilize direct NH3 as a means of hydrogen carrier and an alternative green fuel in T-SOFCs practically determining the optimum operating temperatures, reactant flow rates, electrode porosities, pressure, the position of the anode, thickness and diameters of the tube are still requiring further improvement. Therefore, mathematical modeling ought to be developed to determine these parameters before planning for experimental work. Also, a performance comparison of AS, ES, and CS- T-SOFC powered with direct NH3 will be investigated and best-performed support will be carefully chosen for practical implementation and an experimental study will be conducted for verification based on optimum parameter values obtained from numerical modeling.

Sign in / Sign up

Export Citation Format

Share Document