A novel deep learning architecture for disease classification in Arabica coffee plants

Ramamurthy, Karthik; Thekkath, Rashmi Dinesh; Batra, Shivam; Chattopadhyay, Sreejan

doi:10.1002/cpe.7625

Cited by 5 publications

(3 citation statements)

References 29 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ramamurthy et al [16] have created a trustworthy method for infestation detection with a low amount of computational complexity. Milke et al [17] suggest a deep learning approach for the independent diagnosis of the condition causing coffee wilt.…”

Section: ░ 2 Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Development of Smart Agriculture to detect the Arabica Coffee Leaf Disease using IAFSA based MSAB with Channel and Spatial Attention Network

Saravanakumar,

Matapurkar,

Shivakanth

et al. 2024

IJEER

View full text Add to dashboard Cite

Plant diseases provide challenges for the agriculture sector, notably to produce Arabica coffee. Recognising issues on Arabica coffee leaves is a first step in avoiding and curing illnesses to prevent crop loss. With the extraordinary advancements achieved in convolutional neural networks (CNN) in recent years, Arabica coffee leaf damage can now be identified without the aid of a specialist. However, the local characteristics that convolutional layers in CNNs record are typically redundant and unable to make efficient use of global data to support the prediction process. The proposed Hybrid Attention UNet, also known as CMSAMB-UNet due to its feature extraction and global modelling capabilities, integrates both the Channel and Spatial Attention Module (CSAM) as well as the Multi-head Self-Attention Block (MSAB). In this study, CMSAMB-UNet is built on Resnet50 to extract multi-level features from plant picture data. Two shallow layers of feature maps are used with CSAM according to local attention. used throughout the feature extraction process to enrich the features and adaptively disregard unwanted features. In order to recreate the spatial feature connection of the input pictures using high-resolution feature maps, two global attention maps produced by MSAB are combined.

show abstract

Section: ░ 2 Related Workmentioning

confidence: 99%

“…As a method of evaluation, the k-fold cross-validation test was also used. The execution speed metrics were concentrated on the execution time, whilst the performance measures were determined using equations (13)(14)(15)(16)(17):…”

Section: Performance Metricsmentioning

confidence: 99%

Development of Smart Agriculture to detect the Arabica Coffee Leaf Disease using IAFSA based MSAB with Channel and Spatial Attention Network

Saravanakumar,

Matapurkar,

Shivakanth

et al. 2024

IJEER

View full text Add to dashboard Cite

show abstract

“…Traditional machine learning methods, such as naïve Bayes [16][17][18], logistic regression [19], and support vector machine [20][21][22], are not suitable for recognizing edible fungi diseases in the fruit body period due to their shortcomings in high computational complexity, slow convergence rate, and difficulty in processing a large number of complex samples [23,24]. In recent years, deep learning methods have been widely studied in crop disease recognition [25][26][27][28][29][30]. For instance, Nurul Nabilah et al [31] took 974 pepper disease images collected by themselves and used traditional methods and deep learning methods for experimental comparison.…”

Section: Introductionmentioning

confidence: 99%

Recognition of Edible Fungi Fruit Body Diseases Based on Improved ShuffleNetV2

et al. 2023

View full text Add to dashboard Cite

Early recognition of fruit body diseases in edible fungi can effectively improve the quality and yield of edible fungi. This study proposes a method based on improved ShuffleNetV2 for edible fungi fruit body disease recognition. First, the ShuffleNetV2+SE model is constructed by deeply integrating the SE module with the ShuffleNetV2 network to make the network pay more attention to the target area and improve the model’s disease classification performance. Second, the network model is optimized and improved. To simplify the convolution operation, the 1 × 1 convolution layer after the 3 × 3 depth convolution layer is removed, and the ShuffleNetV2-Lite+SE model is established. The experimental results indicate that the accuracy, precision, recall, and Macro-F1 value of the ShuffleNetV2-Lite+SE model on the test set are, respectively, 96.19%, 96.43%, 96.07%, and 96.25%, which are 4.85, 4.89, 3.86, and 5.37 percent higher than those before improvement. Meanwhile, the number of model parameters and the average iteration time are 1.6 MB and 41 s, which is 0.2 MB higher and 4 s lower than that before the improvement, respectively. Compared with the common lightweight convolutional neural networks MobileNetV2, MobileNetV3, DenseNet, and EfficientNet, the proposed model achieves higher recognition accuracy, and its number of model parameters is significantly reduced. In addition, the average iteration time is reduced by 37.88%, 31.67%, 33.87%, and 42.25%, respectively. The ShuffleNetV2-Lite+SE model proposed in this paper has a good balance among performance, number of parameters, and real-time performance. It is suitable for deploying on resource-limited devices such as mobile terminals and helps in realization of real-time and accurate recognition of fruit body diseases of edible fungi.

show abstract

Enhancing coffee bean classification: a comparative analysis of pre-trained deep learning models

Hassan

2024

Neural Comput & Applic

View full text Add to dashboard Cite

Coffee bean production can encounter challenges due to fluctuations in global coffee prices, impacting the economic stability of some countries that heavily depend on coffee production. The primary objective is to evaluate how effectively various pre-trained models can predict coffee types using advanced deep learning techniques. The selection of an optimal pre-trained model is crucial, given the growing popularity of specialty coffee and the necessity for precise classification. We conducted a comprehensive comparison of several pre-trained models, including AlexNet, LeNet, HRNet, Google Net, Mobile V2 Net, ResNet (50), VGG, Efficient, Darknet, and DenseNet, utilizing a coffee-type dataset. By leveraging transfer learning and fine-tuning, we assess the generalization capabilities of the models for the coffee classification task. Our findings emphasize the substantial impact of the pre-trained model choice on the model's performance, with certain models demonstrating higher accuracy and faster convergence than conventional alternatives. This study offers a thorough evaluation of pre-trained architectural models regarding their effectiveness in coffee classification. Through the evaluation of result metrics, including sensitivity (1.0000), specificity (0.9917), precision (0.9924), negative predictive value (1.0000), accuracy (1.0000), and F1 score (0.9962), our analysis provides nuanced insights into the intricate landscape of pre-trained models.

show abstract

A novel deep learning architecture for disease classification in Arabica coffee plants

Cited by 5 publications

References 29 publications

Development of Smart Agriculture to detect the Arabica Coffee Leaf Disease using IAFSA based MSAB with Channel and Spatial Attention Network

Development of Smart Agriculture to detect the Arabica Coffee Leaf Disease using IAFSA based MSAB with Channel and Spatial Attention Network

Recognition of Edible Fungi Fruit Body Diseases Based on Improved ShuffleNetV2

Enhancing coffee bean classification: a comparative analysis of pre-trained deep learning models

Contact Info

Product

Resources

About