Detection of Tomato Leaf Diseases Using Transfer Learning Architectures: A Comparative Analysis

Peyal, Hasibul Islam; Shahriar, Saleh Mohammed; Sultana, Abida; Jahan, Ifat; Mondol, Md. Halim

doi:10.1109/acmi53878.2021.9528199

Cited by 20 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transfer learning allows a pre-trained model's learning to be transferred to a new model. Transfer learning is a machine learning approach in which CNNs trained for a task is reused as the starting point for a model on another task (Peyal et al, 2021;Chen et al, 2020).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Tomato Disease Detection Model Based on Densenet and Transfer Learning

BAKR

AbdelGaber

Nasr

et al. 2022

acs

View full text Add to dashboard Cite

Plant diseases are a foremost risk to the safety of food. They have the potential to significantly reduce agricultural products quality and quantity. In agriculture sectors, it is the most prominent challenge to recognize plant diseases. In computer vision, the Convolutional Neural Network (CNN) produces good results when solving image classification tasks. For plant disease diagnosis, many deep learning architectures have been applied. This paper introduces a transfer learning based model for detecting tomato leaf diseases. This study proposes a model of DenseNet201 as a transfer learning-based model and CNN classifier. A comparison study between four deep learning models (VGG16, Inception V3, ResNet152V2 and DenseNet201) done in order to determine the best accuracy in using transfer learning in plant disease detection. The used images dataset contains 22930 photos of tomato leaves in 10 different classes, 9 disorders and one healthy class. In our experimental, the results shows that the proposed model achieves the highest training accuracy of 99.84% and validation accuracy of 99.30%.

show abstract

Section: Methodsmentioning

confidence: 99%

“…CNN has a really encouraging performance in terms of detecting these disorders. Various CNN classification architectures, VGG16, Inception V3 and DenseNet201 were previously used in diseases detection (Venkatesh et al, 2020;Peyal et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Tomato Disease Detection Model Based on Densenet and Transfer Learning

BAKR

AbdelGaber

Nasr

et al. 2022

acs

View full text Add to dashboard Cite

show abstract

“…The voltage, current, battery temperature, average voltage, and the average current were used as the input features and the SOC i% was used as the output. Adam was used as the optimizer, with the benefit of fixing the learning rate of the model itself [27]. An algorithm, regarding the whole process is given in Algorithm 1.…”

Section: Architecture Of the Employed Learning Networkmentioning

confidence: 99%

State of Charge Estimation for Electric Vehicle Battery Management Systems Using the Hybrid Recurrent Learning Approach with Explainable Artificial Intelligence

Shahriar

Bhuiyan²,

Nahiduzzaman³

et al. 2022

Energies

Self Cite

View full text Add to dashboard Cite

Enhancing the accuracy of the battery state of charge (SOC) estimation is essential in developing more effective, dependable, and convenient electric vehicles. In this paper, a hybrid CNN and gated recurrent unit-long short-term memory (CNN-GRU-LSTM) approach, which is a recurrent neural network (RNN) based model with an explainable artificial intelligence (EAI) was used for the battery SOC estimation, where the cell parameters were explicitly synchronized to the SOC. The complexed link between the monitoring signals related to current, voltage, and temperature, and the battery SOC, was established using the deep learning (DL) technique. A LG 18650HG2 li-ion battery dataset was used for training the model so that the battery was subjected to a dynamic process. Moreover, the data recorded at ambient temperatures of −10 °C, 0 °C, 10 °C, and 25 °C are fed into the method during training. The trained model was subsequently used to estimate the SOC instantaneously on the testing datasets. At first, the training process was carried out with all temperature data to estimate the SOC by the trained model at various ambient temperatures. The proposed approach was capable to encapsulate the relationships on time into the network weights and, as a result, it produced more stable, accurate, and reliable estimations of the SOC, compared to that by some other existing networks. The hybrid model achieved a mean absolute error (MAE) of 0.41% to 1.13% for the −10 °C to 25 °C operating temperatures. The EAI was also utilized to explain the battery SOC model making certain decisions and to find out the significant features responsible for the estimation process.

show abstract

“…In terms of identifying these diseases, CNN has pretty positive results. Several CNN classification architectures, including VGG16, Inception V3, and DenseNet201, have been employed in the past to detect diseases (3), (4).…”

Section: Introductionmentioning

confidence: 99%

DenseNet Based Model for Plant Diseases Diagnosis

BAKR

Abdel-Gaber

Nasr

et al. 2022

EJECE

View full text Add to dashboard Cite

The biggest threat to the safety of food is plant diseases. They have the ability to dramatically lower the quantity and quality of agricultural products. Recognizing plant diseases is the biggest issue in the agricultural industries. Convolutional Neural Networks (CNN) are effective in solving image classification problems in computer vision. Numerous deep learning architectures have been used to diagnose plant diseases. This study presents a transfer learning-based model for identifying diseases in plant leaves. In this paper, a CNN classifier based on transfer learning model called DenseNet201 are proposed. An analysis of four deep learning models (VGG16, Inception V3, ResNet152V2, and DenseNet201) done to see which one can detect plant diseases with the greatest degree of accuracy. Web based application developed for plant disease diagnosing from defected leaf image and the proposed model which identify the disease and give the recommended treatment. The used images dataset contains 28310 leaves photos of 3 crops, tomato, potato and pepper divided into 15 different classes, 9 disorders and one healthy class for tomato, 2 disorders and one healthy class for potato and 1 disorder and one healthy for pepper. In our experimental, the results shows that the proposed model achieves the highest training accuracy of 99.44% and validation accuracy of 98.70%.

show abstract

Detection of Tomato Leaf Diseases Using Transfer Learning Architectures: A Comparative Analysis

Cited by 20 publications

References 18 publications

Tomato Disease Detection Model Based on Densenet and Transfer Learning

Tomato Disease Detection Model Based on Densenet and Transfer Learning

State of Charge Estimation for Electric Vehicle Battery Management Systems Using the Hybrid Recurrent Learning Approach with Explainable Artificial Intelligence

DenseNet Based Model for Plant Diseases Diagnosis

Contact Info

Product

Resources

About