scholarly journals Plant Disease Identification Using Shallow Convolutional Neural Network

Agronomy ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 2388
Author(s):  
Sk Mahmudul Hassan ◽  
Michal Jasinski ◽  
Zbigniew Leonowicz ◽  
Elzbieta Jasinska ◽  
Arnab Kumar Maji
Keyword(s):  
Deep Learning ◽  
Late Blight ◽  
Early Blight ◽  
Gray Leaf Spot ◽  
Plant Diseases ◽  
Automated Identification ◽  
Average Accuracy ◽  
Proposed Model ◽  
Effective Manner ◽  
Tomato Diseases

Various plant diseases are major threats to agriculture. For timely control of different plant diseases in effective manner, automated identification of diseases are highly beneficial. So far, different techniques have been used to identify the diseases in plants. Deep learning is among the most widely used techniques in recent times due to its impressive results. In this work, we have proposed two methods namely shallow VGG with RF and shallow VGG with Xgboost to identify the diseases. The proposed model is compared with other hand-crafted and deep learning-based approaches. The experiments are carried on three different plants namely corn, potato, and tomato. The considered diseases in corns are Blight, Common rust, and Gray leaf spot, diseases in potatoes are early blight and late blight, and tomato diseases are bacterial spot, early blight, and late blight. The result shows that our implemented shallow VGG with Xgboost model outperforms different deep learning models in terms of accuracy, precision, recall, f1-score, and specificity. Shallow Visual Geometric Group (VGG) with Xgboost gives the highest accuracy rate of 94.47% in corn, 98.74% in potato, and 93.91% in the tomato dataset. The models are also tested with field images of potato, corn, and tomato. Even in field image the average accuracy obtained using shallow VGG with Xgboost are 94.22%, 97.36%, and 93.14%, respectively.

Classification of plant diseases using machine and deep learning

2021 ◽  
Vol 11 (1) ◽  
pp. 491-508
Author(s):  
Monika Lamba ◽  
Yogita Gigras ◽  
Anuradha Dhull
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Plant Disease ◽  
Nearest Neighbor ◽  
Early Recognition ◽  
Activation Function ◽  
Plant Diseases ◽  
Support Vector ◽  
Specificity And Sensitivity ◽  
Proposed Model

Abstract Detection of plant disease has a crucial role in better understanding the economy of India in terms of agricultural productivity. Early recognition and categorization of diseases in plants are very crucial as it can adversely affect the growth and development of species. Numerous machine learning methods like SVM (support vector machine), random forest, KNN (k-nearest neighbor), Naïve Bayes, decision tree, etc., have been exploited for recognition, discovery, and categorization of plant diseases; however, the advancement of machine learning by DL (deep learning) is supposed to possess tremendous potential in enhancing the accuracy. This paper proposed a model comprising of Auto-Color Correlogram as image filter and DL as classifiers with different activation functions for plant disease. This proposed model is implemented on four different datasets to solve binary and multiclass subcategories of plant diseases. Using the proposed model, results achieved are better, obtaining 99.4% accuracy and 99.9% sensitivity for binary class and 99.2% accuracy for multiclass. It is proven that the proposed model outperforms other approaches, namely LibSVM, SMO (sequential minimal optimization), and DL with activation function softmax and softsign in terms of F-measure, recall, MCC (Matthews correlation coefficient), specificity and sensitivity.

scholarly journals Leaf Disease Identification using Convolution Neural Network (CNN)

2020 ◽  
Vol 9 (9) ◽  
pp. 477-481
Keyword(s):  
Neural Network ◽  
Late Blight ◽  
Tomato Plant ◽  
Extraction Methods ◽  
Plant Diseases ◽  
Viral Diseases ◽  
Leaf Disease ◽  
Proposed Model ◽  
Reliable Performance ◽  
First Time

The tomato plant is the most broadly cultivated produce in India. As the Convolutional Neural Network (CNN) which comes under the field of image classification is performing the progressive work, thus using an approach of deep learning which mainly centers on achieving high accuracy of leaf disease of the tomato plant. Therefore, the main objective of this paper is to acquire more reliable performance in the identification of diseases. Amidst various plant diseases that affect leaf comprise of Late blight, bacterial and viral diseases have been chosen to differentiate infected leaves from that of the healthy leaves includes Late blight, bacterial and viral diseases. As we know, none of the other method has been proposed earlier which helps in detecting plant leaf diseases for the first time. Hence the proposed model is designed in such a way that it effectively identifies specific diseases that affect leaves of tomato plants through the use of a dataset containing about 4000 leaf images. CNN achieves an overall accuracy of 96% without implementing any pre-processing and feature extraction methods.

Use of Convolutional Neural Networks in the Diagnosis of Corn Diseases

2021 ◽  
Author(s):  
Paulo Victor Cunha Lima ◽  
Edson Magalhães Costa ◽  
Maria Eliana da Silva Holanda ◽  
Dhian Kelson Leite Oliveira ◽  
Esley Teixeira Espírito Santo ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Visual Observation ◽  
Plant Diseases ◽  
Subjective Perception ◽  
Maize Crop ◽  
Production Chain ◽  
Average Accuracy ◽  
Proposed Model ◽  
Field Practice

The detection of corn (maize) crop diseases is traditionally carried out by farmers, based on their experience accumulated over a period of field practice. However, the visual observation may represent a risk of error due to subjective perception. This article presents an approach based on Deep Learning to identify diseases that affect corn crops. A public database with 3,852 images of maize plant leaves was used, dividedinto four classes: healthy corn, exserohilun leaf spot (northern leaf blight), common corn rust (common rust) and cercosporiosis (cercospora leaf/gray leaf). The proposed model used Convolutional Neural Networks (CNN) techniques for image classification. The four experiments indicated results with an average accuracy above 94.5%. These results in the identification and diagnosis of plant diseases can contribute significantly as atool to the improvement of the production chain that affect corn crops. All data are available at https://github.com/npcaufra/classificacao-doencas-milho .

scholarly journals Traditional Bangladeshi Sports Video Classification Using Deep Learning Method

2021 ◽  
Vol 11 (5) ◽  
pp. 2149
Author(s):  
Moumita Sen Sarma ◽  
Kaushik Deb ◽  
Pranab Kumar Dhar ◽  
Takeshi Koshiba
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Easy Access ◽  
Learning Method ◽  
Cultural Significance ◽  
Sports Video ◽  
Temporal Features ◽  
Average Accuracy ◽  
Proposed Model

Sports activities play a crucial role in preserving our health and mind. Due to the rapid growth of sports video repositories, automatized classification has become essential for easy access and retrieval, content-based recommendations, contextual advertising, etc. Traditional Bangladeshi sport is a genre of sports that bears the cultural significance of Bangladesh. Classification of this genre can act as a catalyst in reviving their lost dignity. In this paper, the Deep Learning method is utilized to classify traditional Bangladeshi sports videos by extracting both the spatial and temporal features from the videos. In this regard, a new Traditional Bangladeshi Sports Video (TBSV) dataset is constructed containing five classes: Boli Khela, Kabaddi, Lathi Khela, Kho Kho, and Nouka Baich. A key contribution of this paper is to develop a scratch model by incorporating the two most prominent deep learning algorithms: convolutional neural network (CNN) and long short term memory (LSTM). Moreover, the transfer learning approach with the fine-tuned VGG19 and LSTM is used for TBSV classification. Furthermore, the proposed model is assessed over four challenging datasets: KTH, UCF-11, UCF-101, and UCF Sports. This model outperforms some recent works on these datasets while showing 99% average accuracy on the TBSV dataset.

scholarly journals Evaluation of tomato genotypes for tolerance to major diseases in Uganda

1970 ◽  
Vol 29 (2) ◽  
pp. 241-258
Author(s):  
I. Ramathani ◽  
G. Ddamulira ◽  
A. Kangire ◽  
P. Wasswa ◽  
A. Tusiime
Keyword(s):  
Late Blight ◽  
Bacterial Wilt ◽  
Early Blight ◽  
Bacterial Speck ◽  
Solanum Lycopersicum L ◽  
Genetic Base ◽  
National Performance ◽  
Tomato Diseases ◽  
Tomato Bacterial Wilt ◽  
Tomato Genotypes

Tomato (Solanum lycopersicum L.) is a priority vegetable in Uganda, but due to its limited genetic base, its cultivated types are prone to a variety of diseases. The objective of this study was to evaluate new tomato genotypes for resistance to major tomato diseases under hotspot conditions in Uganda. Fourty-five tomato genotypes were evaluated for reactions to tomato bacterial wilt, tomato bacterial speck, early blight and late blight. The study was conducted for two rainy seasons in 2019, at the National Crops Resources Research Institute, Namulonge in Uganda. Data for severity and incidence were collected at two-week intervals after transplanting. Twelve genotypes (Nouvella F1, Rambo F1, Commando F1, AVTO1315, AVTO922, AVTO1701, AVTO1219, AVTO1464, MT56, ADV1287A, Pruna and Vega) exhibited high levels of tolerance to bacterial wilt; while bacterial speck presented mild symptoms majorly seen on Vega, Zodiac and AVTO9802. Rhino, AVTO1418, AVTO1314, Eureka, Roma VFN, MT56, Pinktop, Assila F1, Money-maker, AVTO0922 and AVTO1464 were the least affected by early blight; while AVTO1219, AVTO1701, ADV12021, ADV12076 and ADV1287A expressed low AUDPC values for late blight. Overall, AVTO1315 was the best yielder (30.8 metric tonnes ha-1), followed by AVTO0301 (29.0 t ha-1) and Nouvella F1 (26.1 t ha-1). Among the tomato genotypes evaluated, we recommend AVTO1701, AVTO0922, AVTO1464, AVTO0301 AVTO1315, AVTO1219, Pruna, Vega, ADV1287A and MT56 for the national performance trials.

scholarly journals A Deep Learning Enabled Multi-Class Plant Disease Detection Model Based on Computer Vision

AI ◽  
2021 ◽  
Vol 2 (3) ◽  
pp. 413-428
Author(s):  
Arunabha M. Roy ◽  
Jayabrata Bhaduri
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Large Scale ◽  
Plant Disease ◽  
State Of The Art ◽  
Plant Diseases ◽  
Disease Detection ◽  
Detection Model ◽  
Proposed Model ◽  
Apple Plant

In this paper, a deep learning enabled object detection model for multi-class plant disease has been proposed based on a state-of-the-art computer vision algorithm. While most existing models are limited to disease detection on a large scale, the current model addresses the accurate detection of fine-grained, multi-scale early disease detection. The proposed model has been improved to optimize for both detection speed and accuracy and applied to multi-class apple plant disease detection in the real environment. The mean average precision (mAP) and F1-score of the detection model reached up to 91.2% and 95.9%, respectively, at a detection rate of 56.9 FPS. The overall detection result demonstrates that the current algorithm significantly outperforms the state-of-the-art detection model with a 9.05% increase in precision and 7.6% increase in F1-score. The proposed model can be employed as an effective and efficient method to detect different apple plant diseases under complex orchard scenarios.

scholarly journals A Convolutional Neural Network based System to Detect Plant Disease

Webology ◽  
2021 ◽  
Vol 18 (Special Issue 04) ◽  
pp. 944-962
Author(s):  
K. Niha ◽  
Dr.S. Amutha ◽  
Dr. Aisha Banu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Neural Network Model ◽  
Plant Disease ◽  
Performance Metrics ◽  
Plant Diseases ◽  
Detection Accuracy ◽  
Learning Models ◽  
Proposed Model

Disease in plants are a great challenge in the advancement of agriculture which affects farmers yield and the plants. In this modern research deep learning models got a spot light by increasing plant detection accuracy and classification. The proposed CNN (Convolutional Neural Network) model detect seven plant diseases out of healthy leaf, where the dataset considered in this work contain 8685 leaf images from Plant Village Dataset. The proposed modals performance are evaluated with respect to the performance metrics (F1 score, Precision and Recall) and are compared with SVM and ANN. Where the proposed CNN model outperforms the rest with the accuracy of 96.2% and the F1 score greater than 95%. The feasibility of the proposed model in plant detection and classification may provide a solution to the problem faced by farmers.

scholarly journals Classification of tomato leaf diseases using MobileNet v2

2020 ◽  
Vol 9 (2) ◽  
pp. 290
Author(s):  
Siti Zulaikha Muhammad Zaki ◽  
Mohd Asyraf Zulkifley ◽  
Marzuraikah Mohd Stofa ◽  
Nor Azwan Mohammed Kamari ◽  
Nur Ayuni Mohamed
Keyword(s):  
Deep Learning ◽  
Early Stage ◽  
Plant Diseases ◽  
Plant Management ◽  
American Continent ◽  
Vegetable Crop ◽  
Learning Classifier ◽  
Edible Fruit ◽  
Tomato Diseases

<span lang="EN-US">Tomato is a red-colored edible fruit originated from the American continent. There are a lot of plant diseases associated with tomatoes such as leaf mold, late blight, and mosaic virus. Tomato is an important vegetable crop that contributes to the world economically. Despite tremendous efforts in plant management, viral diseases are notoriously difficult to control and eradicate completely. Thus, accurate and faster detection of plant diseases is needed to mitigate the problem at the early stage. A computer vision approach is proposed to identify the disease by capturing the leaf images and detect the possibility of the diseases. A deep learning classifier is utilized to make a robust decision that covers a wide variety of leaf appearances. Compact deep learning architecture, which is MobileNet V2 has been fine-tuned to detect three types of tomato diseases. The algorithm is tested on 4,671 images from PlantVillage dataset. The results show that MobileNet V2 is able to detect the disease up to more than 90% accuracy.</span>

scholarly journals An Enhanced Plant Disease Classifier Model Based on Deep Learning Techniques

2019 ◽  
Vol 9 (1) ◽  
pp. 7159-7164 ◽  
Keyword(s):  
Deep Learning ◽  
Plant Disease ◽  
Low Cost ◽  
Disease Diagnosis ◽  
Plant Diseases ◽  
Disease Detection ◽  
Crop Species ◽  
Learning Techniques ◽  
Proposed Model ◽  
Significant Performance

Plant disease detection is used to detect and identify symptoms of plant diseases. Detection of plant diseases through the naked eye is ineffective, especially because there are numerous diseases. Therefore, there is a need to develop low-cost methods to improve rapidity and accuracy of plant disease diagnosis. This paper presents an effective model for plant disease detection by using our developed deep learning approach. Extensive experiments were performed on the PlantVillage dataset, which contains 54,306 images categorized between 38 different classes containing 14 crop species and 26 diseases. Our proposed model demonstrated significant performance improvement in terms of accuracy, recall, precision, and F1-score compared with the existing model used for plant disease detection.

scholarly journals Epileptic Spike Detection by Recurrent Neural Networks with Self-Attention Mechanism

2021 ◽  
Author(s):  
Kosuke Fukumori ◽  
Noboru Yoshida ◽  
Hidenori Sugano ◽  
Madoka Nakajima ◽  
Toshihisa Tanaka
Keyword(s):  
Machine Learning ◽  
Attention Mechanism ◽  
Automated Identification ◽  
Step Method ◽  
Attention Model ◽  
Manual Search ◽  
Epileptiform Discharges ◽  
Average Accuracy ◽  
Proposed Model ◽  
Electroencephalogram Eeg

Automated identification of epileptiform discharges for the diagnosis of epilepsy can mitigate the burden of the exhaustive manual search in electroencephalogram (EEG). Recent studies have indicated that a two-step method that consists of detection of candidate waveforms with signal processing and pattern matching followed by machine learning-based classification is effective. However, the overall performance depends on the detector of candidates. This paper thus considers a scenario without candidate waveforms, that is, we propose a recurrent neural network (RNN)-based self-attention model that can be fitted from the EEG segments generated without detecting spike candidates. In comparison with the state-of-the-art machine learning models which can be applied for EEG classification (LightGBM and EEGNet), the proposed model achieved higher performance (average accuracy: 90.2 %). This result strongly suggests that the self-attention mechanism is suitable to an automated identification of the epileptiform discharge in the EEG.

Sign in / Sign up

Export Citation Format

Share Document