Machine Learning-Based Classification of Infected Date Palm Leaves Caused by Dubas Insects: A Comparative Analysis of Feature Extraction Methods and Classification Algorithms

Kursun, Ramazan; Yasin, Elham Tahsin; Koklu, Murat

doi:10.1109/asyu58738.2023.10296641

Cited by 4 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These metrics are essential for calculating performance indicators such as accuracy, precision, recall, and the F1 score. Analyzing a confusion matrix is crucial for understanding classifier errors and the overall performance of the model, which can assist in improving the model and adjusting its parameters [26][27][28]. Fig.…”

Section: E Confusion Matrix and Performance Metricsmentioning

confidence: 99%

Classification of Sugarcane Leaf Disease with AlexNet Model

KURSUN,

YASIN,

KOKLU

2024

icisna

View full text Add to dashboard Cite

This study evaluates the influence of activation functions on the performance of the AlexNet deep learning model in classifying sugarcane diseases. Two popular activation functions, ReLU and LeakyReLU, were compared in terms of classification accuracy and computational efficiency. The ReLU function, known for its simplicity and speed, achieved an accuracy of 87.90% with a total training and testing time of 47 minutes. In contrast, LeakyReLU, which allows a small gradient when the input is negative and hence provides continuity in the learning process, obtained a higher accuracy of 90.67%, albeit at a higher computational cost, taking 54 minutes for the training and testing phase. These results highlight the trade-off between model accuracy and computational time in the deployment of deep learning models for agricultural applications. The study suggests that while LeakyReLU can lead to more accurate models, ReLU remains a competitive choice when efficiency is paramount. Future research should focus on optimizing the balance between accuracy and speed, potentially through the tuning of LeakyReLU parameters or the development of hybrid models.

show abstract

Section: E Confusion Matrix and Performance Metricsmentioning

confidence: 99%

Classification of Sugarcane Leaf Disease with AlexNet Model

KURSUN,

YASIN,

KOKLU

2024

icisna

View full text Add to dashboard Cite

show abstract

“…Additionally, plant disease recognition systems optimized for smartphones have been developed, showcasing their effectiveness in identifying leaf diseases when incorporating offline training and data augmentation methods. Overall, these studies highlight the potential of deep learning techniques, such as CNNs [17][18][19], in transforming plant disease identification and classification and providing accurate and efficient solutions for mitigating the impact of plant diseases on agriculture and human livelihoods [20,21].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Classification of Mulberry Leaf Diseases

YASIN,

KURSUN,

KOKLU

2024

icisna

View full text Add to dashboard Cite

This research examines the potential of machine learning methods in the classification of Mulberry leaf diseases. By applying SqueezeNet's deep feature extraction, the study aimed to identify disease patterns efficiently. The dataset used in the study consisted of ten distinct classes of Mulberry leaf diseases, which was divided into an 80% training set and a 20% testing set. The Support Vector Machine (SVM) supervised machine learning algorithm was used to classify the diseases, and the classification model achieved an accuracy of 77.5%. The results of the study demonstrate the effectiveness of machine learning approaches in aiding the detection and management of Mulberry leaf diseases, which can contribute to advancements in agricultural disease monitoring and mitigation strategies.

show abstract

Fisheye freshness detection using common deep learning algorithms and machine learning methods with a developed mobile application

Yildiz,

Yasin,

Koklu

2024

Eur Food Res Technol

View full text Add to dashboard Cite

Fish is commonly ingested as a source of protein and essential nutrients for humans. To fully benefit from the proteins and substances in fish it is crucial to ensure its freshness. If fish is stored for an extended period, its freshness deteriorates. Determining the freshness of fish can be done by examining its eyes, smell, skin, and gills. In this study, artificial intelligence techniques are employed to assess fish freshness. The author’s objective is to evaluate the freshness of fish by analyzing its eye characteristics. To achieve this, we have developed a combination of deep and machine learning models that accurately classify the freshness of fish. Furthermore, an application that utilizes both deep learning and machine learning, to instantly detect the freshness of any given fish sample was created. Two deep learning algorithms (SqueezeNet, and VGG19) were implemented to extract features from image data. Additionally, five machine learning models to classify the freshness levels of fish samples were applied. Machine learning models include (k-NN, RF, SVM, LR, and ANN). Based on the results, it can be inferred that employing the VGG19 model for feature selection in conjunction with an Artificial Neural Network (ANN) for classification yields the most favorable success rate of 77.3% for the FFE dataset. Graphical Abstract

show abstract

Machine Learning-Based Classification of Infected Date Palm Leaves Caused by Dubas Insects: A Comparative Analysis of Feature Extraction Methods and Classification Algorithms

Cited by 4 publications

References 23 publications

Classification of Sugarcane Leaf Disease with AlexNet Model

Classification of Sugarcane Leaf Disease with AlexNet Model

Machine Learning-Based Classification of Mulberry Leaf Diseases

Fisheye freshness detection using common deep learning algorithms and machine learning methods with a developed mobile application

Contact Info

Product

Resources

About