PDCNN: FRAMEWORK for Potato Diseases Classification Based on Feed Foreword Neural Network

Hassoon, Israa Mohammed; Qassir, Samar Amil; Riyadh, Musaab

doi:10.21123/bsj.2021.18.2(suppl.).1012

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, the results show that the accuracy of the deep learning proposed was 98% and 100% accuracy in some of the classes [29].To classify potatoes, Hyeon-Seung Lee et al used Mask R-CNN, one of the object identification technologies utilizing deep learning, and were surprised with the result of 93.0% [30]. Furthermore, Israa Mohammed Hassoon et al proposed a PDCNN framework that is very effective in classifying four types of potato tuber diseases including black dot, common scab, potato virus y, and ring rot with 91.3% accuracy [31].…”

Section: Related Workmentioning

confidence: 99%

Improving Potato Diseases Classification Based on Custom ConvNeXtSmall and Combine with the Explanation Model

Luong

2024

IJACSA

View full text Add to dashboard Cite

Potatoes are short-term crops grown for harvesting tubers. It is a type of tuber that grows on roots and is the fourth most common crop after rice, wheat, and corn. Fresh potatoes can also be used in an incredible variety of dishes by baking, boiling, or frying them. Moreover, the paper, textile, wood, and pharmaceutical industries also make extensive use of potato starch. However, soil and climate pollution are highly unfavorable for potato growth and lead to a lot of diseases such as common scab, black scurf, blackleg, dry rot, and pink rot. Thus. several types of research in medicine and computers were started for the early detection, classification, and treatment of potato diseases. In this study, transfer learning and finetuning were applied to potato disease classification based on a custom ConvNeXtSmall model. In addition, Gradient-weighted Class Activation Mapping (i.e., Grad-CAM) is provided for visual explanation in the final result after classification. For potato illness segmentation, k-means clustering was used to enable the difference between healthy and diseased sections based on color and texture. The data was collected from numerous websites and validated by the Bangladesh Agricultural Research Institute (i.e., BARI), including six types of potato diseases and healthy images. With a Convolutional Neural Networks (i.e., CNN) model from the Keras library, our study reached the unexpected validation accuracy, test accuracy, and F1 score in seven classifications of 99.49%, 98.97%, and 98.97%, respectively. Concerning four-class classification, high accuracy values were obtained for most of the models (i.e., 100%).

show abstract

Section: Related Workmentioning

confidence: 99%

Improving Potato Diseases Classification Based on Custom ConvNeXtSmall and Combine with the Explanation Model

Luong

2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…The segmentation carried out in this study aims to take cassava leaves. The segmentation method used is k-means clustering, because the k-means algorithm provides the significant advantage of being simple and quick to apply 35 . The main principle of the K-means algorithm is to divide data into k classes based on distance.…”

Section: Image Segmentationmentioning

confidence: 99%

AlexNet-Based Feature Extraction for Cassava Classification: A Machine Learning Approach

Sholihin,

Fudzee,

Ismail

2023

Baghdad Sci.J

View full text Add to dashboard Cite

Cassava, a significant crop in Africa, Asia, and South America, is a staple food for millions. However, classifying cassava species using conventional color, texture, and shape features is inefficient, as cassava leaves exhibit similarities across different types, including toxic and non-toxic varieties. This research aims to overcome the limitations of traditional classification methods by employing deep learning techniques with pre-trained AlexNet as the feature extractor to accurately classify four types of cassava: Gajah, Manggu, Kapok, and Beracun. The dataset was collected from local farms in Lamongan Indonesia. To collect images with agricultural research experts, the dataset consists of 1,400 images, and each type of cassava has 350 images. Three fully connected (FC) layers were utilized for feature extraction, namely fc6, fc7, and fc8. The classifiers employed were support vector machine (SVM), k-nearest neighbors (KNN), and Naive Bayes. The study demonstrated that the most effective feature extraction layer was fc6, achieving an accuracy of 90.7% with SVM. SVM outperformed KNN and Naive Bayes, exhibiting an accuracy of 90.7%, sensitivity of 83.5%, specificity of 93.7%, and F1-score of 83.5%. This research successfully addressed the challenges in classifying cassava species by leveraging deep learning and machine learning methods, specifically with SVM and the fc6 layer of AlexNet. The proposed approach holds promise for enhancing plant classification techniques, benefiting researchers, farmers, and environmentalists in plant species identification, ecosystem monitoring, and agricultural management.

show abstract

“…The artificial neural network is the cornerstone of artificial intelligence and can solve a wide range of complicated issues that are challenging for people or statistical techniques to handle 1 . Deep learning neural networks have been extensively utilized for classification, detection, and identification 2,3 . which is a strong tool for data forecasting in a range of systems 4,5 .…”

Section: Introductionmentioning

confidence: 99%

An improved neurogenetic model for recognition of 3D kinetic data of human extracted from the Vicon Robot system

Stepanyan,

Hameed

2023

Baghdad Sci.J

View full text Add to dashboard Cite

These days, it is crucial to discern between different types of human behavior, and artificial intelligence techniques play a big part in that. The characteristics of the feedforward artificial neural network (FANN) algorithm and the genetic algorithm have been combined to create an important working mechanism that aids in this field. The proposed system can be used for essential tasks in life, such as analysis, automation, control, recognition, and other tasks. Crossover and mutation are the two primary mechanisms used by the genetic algorithm in the proposed system to replace the back propagation process in ANN. While the feedforward artificial neural network technique is focused on input processing, this should be based on the process of breaking the feedforward artificial neural network algorithm. Additionally, the result is computed from each ANN during the breaking up process, which is based on the breaking up of the artificial neural network algorithm into multiple ANNs based on the number of ANN layers, and therefore, each layer in the original artificial neural network algorithm is assessed. The best layers are chosen for the crossover phase after the breakage process, while the other layers go through the mutation process. The output of this generation is then determined by combining the artificial neural networks into a single ANN; the outcome is then checked to see if the process needs to create a new generation. The system performed well and produced accurate findings when it was used with data taken from the Vicon Robot system, which was primarily designed to record human behaviors based on three coordinates and classify them as either normal or aggressive.

show abstract

PDCNN: FRAMEWORK for Potato Diseases Classification Based on Feed Foreword Neural Network

Cited by 4 publications

References 12 publications

Improving Potato Diseases Classification Based on Custom ConvNeXtSmall and Combine with the Explanation Model

Improving Potato Diseases Classification Based on Custom ConvNeXtSmall and Combine with the Explanation Model

AlexNet-Based Feature Extraction for Cassava Classification: A Machine Learning Approach

An improved neurogenetic model for recognition of 3D kinetic data of human extracted from the Vicon Robot system

Contact Info

Product

Resources

About