scholarly journals Identification of Tomato Leaf Diseases Using Deep Convolutional Neural Networks

2021 ◽  
Vol 12 (4) ◽  
pp. 1-22
Author(s):  
Ganesh Bahadur Singh ◽  
Rajneesh Rani ◽  
Nonita Sharma ◽  
Deepti Kakkar
Keyword(s):  
Production Rate ◽  
Cost Effective ◽  
Tomato Leaf ◽  
Identification Accuracy ◽  
Deep Convolutional Neural Networks ◽  
Tomato Crop ◽  
Target Spot ◽  
Proposed Model ◽  
Crop Diseases ◽  
Crop Disease

Crop disease is a major issue now days; as it drastically reduces food production rate. Tomato is cultivated in major part of the world. The most common diseases that affect tomato crops are bacterial spot, early blight, septoria leaf spot, late blight, leaf mold, target spot, etc. In order to increase the production rate of tomato, early identification of diseases is highly required. The existing work contains very less accurate system for identification of tomato crop diseases. The goal of our work is to propose cost effective and efficient deep learning model inspired from Alexnet for identification of tomato crop diseases. To validate the performance of proposed model, experiments have also been done on standard pretrained models. The plantVillage dataset is used for the same, which contains 18,160 images of diseased and non-diseased tomato leaf. The disease identification accuracy of proposed model is compared with standard pretrained models and found that proposed model gave more promising results for tomato crop diseases identification.

scholarly journals Identification of Tomato Leaf Diseases using Deep Convolutional Neural Networks

2021 ◽  
Vol 12 (4) ◽  
pp. 0-0
Keyword(s):  
Production Rate ◽  
Cost Effective ◽  
Tomato Leaf ◽  
Identification Accuracy ◽  
Deep Convolutional Neural Networks ◽  
Tomato Crop ◽  
Target Spot ◽  
Proposed Model ◽  
Crop Diseases ◽  
Crop Disease

Crop disease is a major issue now days; as it drastically reduces food production rate. Tomato is cultivated in major part of the world. The most common diseases that affect tomato crops are bacterial spot, early blight, septoria leaf spot, late blight, leaf mold, target spot, etc. In order to increase the production rate of tomato, early identification of diseases is highly required. The existing work contains very less accurate system for identification of tomato crop diseases. The goal of our work is to propose cost effective and efficient deep learning model inspired from Alexnet for identification of tomato crop diseases. To validate the performance of proposed model, experiments have also been done on standard pretrained models. The plantVillage dataset is used for the same, which contains 18,160 images of diseased and non-diseased tomato leaf. The disease identification accuracy of proposed model is compared with standard pretrained models and found that proposed model gave more promising results for tomato crop diseases identification.

scholarly journals Tomato Leaf Disease Diagnosis Based on Improved Convolution Neural Network by Attention Module

Agriculture ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 651
Author(s):  
Shengyi Zhao ◽  
Yun Peng ◽  
Jizhan Liu ◽  
Shuo Wu
Keyword(s):  
Neural Network ◽  
High Performance ◽  
Model Comparison ◽  
Research Direction ◽  
Disease Diagnosis ◽  
Tomato Leaf ◽  
Identification Accuracy ◽  
Main Research ◽  
Proposed Model ◽  
Complex Features

Crop disease diagnosis is of great significance to crop yield and agricultural production. Deep learning methods have become the main research direction to solve the diagnosis of crop diseases. This paper proposed a deep convolutional neural network that integrates an attention mechanism, which can better adapt to the diagnosis of a variety of tomato leaf diseases. The network structure mainly includes residual blocks and attention extraction modules. The model can accurately extract complex features of various diseases. Extensive comparative experiment results show that the proposed model achieves the average identification accuracy of 96.81% on the tomato leaf diseases dataset. It proves that the model has significant advantages in terms of network complexity and real-time performance compared with other models. Moreover, through the model comparison experiment on the grape leaf diseases public dataset, the proposed model also achieves better results, and the average identification accuracy of 99.24%. It is certified that add the attention module can more accurately extract the complex features of a variety of diseases and has fewer parameters. The proposed model provides a high-performance solution for crop diagnosis under the real agricultural environment.

scholarly journals Graph contextualized attention network for predicting synthetic lethality in human cancers

2021 ◽  
Author(s):  
Yahui Long ◽  
Min Wu ◽  
Yong Liu ◽  
Jie Zheng ◽  
Chee Keong Kwoh ◽  
...  
Keyword(s):  
Synthetic Lethality ◽  
Critical Role ◽  
Design Feature ◽  
Cost Effective ◽  
Attention Network ◽  
New Genes ◽  
Lab Experiments ◽  
Proposed Model ◽  
Multiple Feature ◽  
Wet Lab

Abstract Motivation Synthetic Lethality (SL) plays an increasingly critical role in the targeted anticancer therapeutics. In addition, identifying SL interactions can create opportunities to selectively kill cancer cells without harming normal cells. Given the high cost of wet-lab experiments, in silico prediction of SL interactions as an alternative can be a rapid and cost-effective way to guide the experimental screening of candidate SL pairs. Several matrix factorization-based methods have recently been proposed for human SL prediction. However, they are limited in capturing the dependencies of neighbors. In addition, it is also highly challenging to make accurate predictions for new genes without any known SL partners. Results In this work, we propose a novel graph contextualized attention network named GCATSL to learn gene representations for SL prediction. First, we leverage different data sources to construct multiple feature graphs for genes, which serve as the feature inputs for our GCATSL method. Second, for each feature graph, we design node-level attention mechanism to effectively capture the importance of local and global neighbors and learn local and global representations for the nodes, respectively. We further exploit multi-layer perceptron (MLP) to aggregate the original features with the local and global representations and then derive the feature-specific representations. Third, to derive the final representations, we design feature-level attention to integrate feature-specific representations by taking the importance of different feature graphs into account. Extensive experimental results on three datasets under different settings demonstrated that our GCATSL model outperforms 14 state-of-the-art methods consistently. In addition, case studies further validated the effectiveness of our proposed model in identifying novel SL pairs. Availability Python codes and dataset are freely available on GitHub (https://github.com/longyahui/GCATSL) and Zenodo (https://zenodo.org/record/4522679) under the MIT license.

A Method of Environmental Sound Classification Based on Residual Networks and Data Augmentation

2021 ◽  
pp. 2150018
Author(s):  
Jinfang Zeng ◽  
Youming Li ◽  
Yu Zhang ◽  
Da Chen
Keyword(s):  
Neural Networks ◽  
Data Augmentation ◽  
Machine Learning Techniques ◽  
Deep Convolutional Neural Networks ◽  
Mel Frequency Cepstral Coefficients ◽  
Environmental Sound ◽  
Sound Classification ◽  
Learning Techniques ◽  
Proposed Model ◽  
Audio Data

Environmental sound classification (ESC) is a challenging problem due to the complexity of sounds. To date, a variety of signal processing and machine learning techniques have been applied to ESC task, including matrix factorization, dictionary learning, wavelet filterbanks and deep neural networks. It is observed that features extracted from deeper networks tend to achieve higher performance than those extracted from shallow networks. However, in ESC task, only the deep convolutional neural networks (CNNs) which contain several layers are used and the residual networks are ignored, which lead to degradation in the performance. Meanwhile, a possible explanation for the limited exploration of CNNs and the difficulty to improve on simpler models is the relative scarcity of labeled data for ESC. In this paper, a residual network called EnvResNet for the ESC task is proposed. In addition, we propose to use audio data augmentation to overcome the problem of data scarcity. The experiments will be performed on the ESC-50 database. Combined with data augmentation, the proposed model outperforms baseline implementations relying on mel-frequency cepstral coefficients and achieves results comparable to other state-of-the-art approaches in terms of classification accuracy.

scholarly journals METHODOLOGICAL APPROACH TO CREATING A MODEL OF COST-EFFECTIVE MECHANISM FOR MANAGING INNOVATIVE ACTIVITY OF HOTEL ORGANIZATIONS

2021 ◽  
pp. 68-76
Author(s):  
T. P. Levchenko ◽  
M. B. Moldazhanov ◽  
V. V. Purichi ◽  
I. V. Strishkina
Keyword(s):  
Innovation Management ◽  
Methodological Approach ◽  
Cost Effective ◽  
Innovative Activity ◽  
Effective Management ◽  
Management Mechanism ◽  
Effective Mechanism ◽  
Scenario Modeling ◽  
Proposed Model ◽  
Activity Management

The transition of hotel organizations to a qualitatively new level of development can be ensured by the formation and use of a cost-effective innovation management mechanism. The article attempts to create a model of a cost-effective management mechanism that could take into account the multifaceted relationships of indicators and indicators of innovative activity. The operation of this mechanism implies the use of indicative control tools, as well as factor and scenario modeling. The author considers the mechanism from the perspective of implementing five interconnected blocks: subjects, goals and tasks, objects, processes and resulting effects. The content of the resulting effects of the implementation of innovative processes based on the calculation of integral indicators of innovative activity and its elements. Based on the proposed model of a cost-effective mechanism for managing the innovative activity of hotel organizations, an analysis of trends in the level of innovative activity was carried out at using the example of three hotel in Sochi, their graphical interpretation is presented. As part of the presented model, scenario modeling of innovative activity management was carried out as one of its tools, a graph of the ratio of indicators of innovative activity of hotel organizations in Sochi was built.

scholarly journals An Enhanced Faster-RCNN Based Deep Learning Model for Crop Diseases Detection and Classification

2019 ◽  
Vol 8 (6) ◽  
pp. 4714-4719
Keyword(s):  
Neural Network ◽  
Vital Role ◽  
Convolution Neural Network ◽  
Plant Phenotyping ◽  
Early Disease ◽  
Early Disease Detection ◽  
Proposed Model ◽  
Crop Diseases ◽  
Deep Learning Model ◽  
State Of Art

Recently Plant phenotyping has gained the attention of many researchers such that it plays a vital role in the context of enhancing agricultural productivity. Indian economy highly depends on agriculture and this factor elevates the importance of early disease detection of the crops within the agricultural fields. Addressing this problem several researchers have proposed Computer Vision and Pattern recognition based mechanisms through which they have attempted to identify the infected crops in the early stages.in this scenario, CNN convolution neural network-based architecture has demonstrated exceptional performance when compared with state-of-art mechanisms. This paper introduces an enhanced RCNN recurrent convolution neural network-based architecture that enhances the prediction accuracy while detecting the crop diseases in early stages. Based on the simulative studies is observed that the proposed model outperforms when compared with CNN and other state-of-art mechanisms.

scholarly journals Effects of Tomato Leaf Curl Virus on Growth and Yield Parameters of Tomato Crop

2021 ◽  
Vol 39 (1) ◽  
pp. 79-83
Author(s):  
Yasir Iftikhar ◽  
◽  
Mustansar Mubeen ◽  
Ashara Sajid ◽  
Mohamed Ahmad Zeshan ◽  
...  
Keyword(s):  
Disease Severity ◽  
Disease Incidence ◽  
Tomato Leaf ◽  
Growth And Yield ◽  
Tomato Crop ◽  
Tomato Leaf Curl Virus ◽  
Yield Parameters ◽  
Tomato Leaf Curl ◽  
Leaf Curl Virus ◽  
Leaf Curl

Iftikhar, Y., M. Mubeen, A. Sajid, M.A. Zeshan, Q. Shakeel, A. Abbas, S. Bashir, M. Kamran and H. Anwaar. 2021. Effects of Tomato Leaf Curl Virus on Growth and Yield Parameters of Tomato Crop. Arab Journal of Plant Protection, 39(1): 79-83. Tomato is an important vegetable crop, belongs to the family Solanaceae and is the second most consumed vegetable following potatoes. The tomato crop is grown all over the world in both summer and winter seasons, and plant viruses are a major threat to tomato production. Among these viruses, tomato leaf curl virus (TLCV) causes considerable yield loss to tomato crop. This virus is transmitted by a whitefly (Bemisia tabaci) vector. In this study, the effect of TLCV infection, on the following tomato growth and yield parameters, was evaluated: plant leaf number and area, plant biomass, plant height, root length, and plant stem diameter and yield. Tomato plants were transplanted in wellprepared plots with 4 replications. The control group was covered with polyethene bag to avoid whitefly infestation. Plants were scored on the 15th and 30th day after inoculation and TLCV disease severity was recorded. Analysis of variance (ANOVA) showed the significant differences between the healthy and infected tomato plants. Moreover, growth and yield parameters were reduced with the increase in disease incidence, disease severity and whitefly infestation. Disease severity was increased with the increase in temperature during the growing season. It can be concluded from this study that TLCV significantly affects growth and yield of the tomato crop. Keywords: Tomato, Tomato leaf curl virus, TLCV, disease incidence, disease severity.

An analytical model for predicting noise radiated by switch reluctance electric motors

2021 ◽  
Vol 263 (2) ◽  
pp. 4100-4110
Author(s):  
Murat Inalpolat ◽  
Bahadir Sarikaya ◽  
Enes Timur Ozdemir ◽  
Hyun Ku Lee
Keyword(s):  
Magnetic Energy ◽  
Cost Effective ◽  
Torque Ripple ◽  
Air Gap ◽  
Sound Power ◽  
Electromagnetic Forces ◽  
Phase Switching ◽  
Proposed Model ◽  
Torque Ripples

Switch reluctance motors (SRM) have become a prominent alternative for electric vehicles in recent years due to their simple, high power density architecture and cost-effective manufacturability. Despite its potential, NVH problems have been one of the biggest challenges for SRM's implementation. Vibration and noise generated by the SRM are mainly caused by phase switching related torque ripple, unbalanced electromagnetic forces from air gap variations and lamination problems. Our proposed model is an analytical noise radiation prediction model which relates geometrical, material and electrical design inputs to radiated sound power. The electromagnetic part of the model is nonlinear with saturation and provides back-emf and flux linkage by receiving design inputs. The computed magnetic energy, radial and tangential rotor forces are utilized as excitation sources to a continuous shell dynamic model to obtain the steady-state vibration response. Finally, surface velocities obtained from the shell model are used to calculate sound power. Utilizing a shell structure provides axial, radial and tangential information on the casing by considering the effect of magneto-restrictive forces of laminations, torque ripples and unbalanced electromagnetic forces. The effect of air gap, lamination error, and stator and rotor geometry on sound radiation are studied through an example case study.

scholarly journals Coupling Quasi-Two-Dimensional Friction Model and Discrete Vapor Cavity Model for Simulation of Transient Cavitating Flows in Pipeline Systems

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Qiang Sun ◽  
Yuebin Wu ◽  
Ying Xu ◽  
Liang Chen ◽  
Tae Uk Jang
Keyword(s):  
Cost Effective ◽  
Friction Model ◽  
Experimental Results ◽  
Complex Nature ◽  
Two Dimensional ◽  
Cavity Model ◽  
Cavitating Flows ◽  
Vapor Cavity ◽  
Proposed Model ◽  
Pipeline Systems

Accurate simulation of cavitating flows in pipeline systems is important for cost-effective surge protection. However, this is still a challenge due to the complex nature of the problem. This paper presents a numerical model that combines the discrete vapor cavity model (DVCM) with the quasi-two-dimensional (quasi-2D) friction model to simulate transient cavitating flows in pipeline systems. The proposed model is solved by the method of characteristics (MOC), and the performance is investigated through a numerical case study formulated based on a laboratory pipeline reported in the literature. The results obtained by the proposed model are compared with those calculated by the classic one-dimensional (1D) friction model with the DVCM and the corresponding experimental results provided by the literature, respectively. The comparison shows that the pressure peak, waveform, and phase of pressure pulsations predicted by the proposed model are closer to the experimental results than those obtained by the classic 1D model. This demonstrates that the proposed model that combines the quasi-2D friction model with the DVCM has provided a solution to more accurately simulate transient cavitating flows in pipeline systems.

Sign in / Sign up

Export Citation Format

Share Document