Effective Techniques for the Analysis of Hyperspectral Images to Detect Black Sigatoka Disease Based on Unique Learning Principles | Chapter 3 | Emerging Issues in Agricultural Sciences Vol. 5

 The present study evaluates cutting distributed edge brilliance methods accompanying unique learning hypotheses for hyperspectral imaging-located early detection of the black sigatoka ailment. We go over the knowledge characteristics of the techniques secondhand, which will aid researchers in better understanding the conditions for the essential data and choosing a design that will work for their research needs. With the constant progress of development, artificial intelligence be able good progress in the analysis and recognition of figures, which has further triggered some investigators to explore the region of combining machine learning and deep education with hyperspectral countenances and achieve some progress. The current synthetic methods for controlling plant afflictions have an adverse effect on the surroundings and raise the cost of production. Creating efficient crop care strategies demands accurate and early disease discovery of the disease.  A set of hyperspectral representations of banana leaves inoculated accompanying a conidial suspension of black sigatoka tumor (Pseudocercospora fijiensis) was used to train and validate machine intelligence models. Support vector machine (SVM), multilayer perceptron (MLP), affecting animate nerve organs networks, N-way incomplete least square–discriminant analysis (NPLS-DA), and prejudiced least square–penalized logistic regression (PLS-PLR) were picked due to their extreme predictive power. When the ghostly signatures of the misclassified leaves were distinguished with the average spectra of the athletic and diseased leaves, the correspondences and differences that explained their wrong classification could be noticed. The models were assessed utilizing the metrics of AUC, precision, sympathy, prediction, and F1 score. The exploratory outcomes demonstrate that the PLS-PLR, SVM, and MLP models authorize the successful and well reliable early detection of evil sigatoka disease, positioning ruling class as robust and very reliable HSI classification orders for the early detection of plant ailment and allowing for the evaluation of synthetic and biological control of phytopathogens.

Author(s) Details:

Jorge Ugarte Fajardo,
Maestría en Inteligencia de Negocios, Universidad Tecnológica Ecotec, Guayaquil 092302, Ecuador.

María Maridueña-Zavala,
ESPOL Polytechnic University, Escuela Superior Politécnica del Litoral, ESPOL, Centro de Investigaciones Biotecnológicas del Ecuador (CIBE), Guayaquil 090902, Ecuador.

Juan Cevallos-Cevallos,
ESPOL Polytechnic University, Escuela Superior Politécnica del Litoral, ESPOL, Centro de Investigaciones Biotecnológicas del Ecuador (CIBE), Guayaquil 090902, Ecuador and Facultad de Ciencias de la Vida (FCV), ESPOL Polytechnic University, Escuela Superior Politécnica del Litoral, ESPOL, Guayaquil 090902, Ecuador.

Daniel Ochoa Donoso,
Facultad de Ingeniería Eléctrica y Computación (FIEC), ESPOL Polytechnic University, Escuela Superior Politécnica del Litoral, ESPOL, Guayaquil 0909022, Ecuador.

Please see the link here: https://stm.bookpi.org/EIAS-V5/article/view/11136

A Novel Approach for Predicting Disease in Plant Using Hybrid Deep Convolutional Neural Network | Chapter 5 | Current Approaches in Science and Technology Research Vol. 8

 Agriculture is India's most important economic industry. The detection of plant diseases is a key concern in the agriculture industry. An accurate and speedier identification of plant diseases, resulting in significant reductions in economic losses. Manually monitoring plant leaf disease is a highly important task that takes a long time. As a result, an automated solution is required for plant disease detection. Deep learning is quickly becoming the industry standard for picture classification. Researchers have been able to improve the accuracy of object detection thanks to recent advances in Deep Neural Networks. Researchers have already built a few architectures for effective plant disease classification, including the Faster Region-based Convolutional Neural Network (Faster R-CNN), Region-based Fully Convolutional Network (R-FCN), and Single Shot Multibox Detector (SSD). The well-known Deep Convolutional Neural Network architectures for generic Image categorization are Alex Net, Google Net, and VGG-16. When many diseases afflict the same leaf, however, this architecture does not perform well.

To address this, this study proposes a Hybrid Deep Convolutional Neural Network architecture with segmentation, which consists of five convolutional layers, five pooling layers, and two fully connected layers. Deep convolutional neural networks are extensively employed to assess visual imagery and are frequently utilised in image categorization behind the scenes. The input photos are fed to the CNN in the proposed Faster-RCNN system, increasing the accuracy of images to forecast illnesses from plant leaves.

Author (s) Details

R. Jayavadivel
Department of Computer Science and Engineering, Lovely Professional University, Jalandhar-Delhi, G. T. Road, Phagwara, Punjab, India.

V. Chandrasekar
Department of Computer Science and Engineering, Malla Reddy College of Engineering and Technology, Secunderabad, Telangana State, India.

V. Shanmugavalli
Department of Computer Science and Engineering, Vivekanandha College of Engineering for Women, India.

View Book :- https://stm.bookpi.org/CASTR-V8/article/view/1946