Agriculture is an essential factor in the development of a country. For the power coming from agriculture to be effective, it is necessary to get productive results from agriculture. One of the most significant features that increase productivity in agriculture is that agriculture is done consciously. Knowing what kind of message, the planted material gives according to its shape and condition is of great importance for the efficiency of agriculture. This study aimed to detect diseases on tomato leaves using artificial intelligence techniques. The study extracted features from tomato leaf images using ResNet-50, DarkNet-53, GoogleNet, AlexNet, and MobileNet-V2 models. In this study, dimensionality reduction was performed using the mRMR (Minimum Redundancy Maximum Relevance) method to reduce the number of features and increase the performance rate by selecting essential features. Support Vector Machines (SVM) algorithm was used to classify diseases on tomato leaves. As a result of the analysis, we obtained an accuracy value of 88.9% by combining ResNet-50, MobileNet-V2, and DarkNet-53 pre-trained network architectures, which have high accuracy rates. Afterward, dimensionality reduction was performed using mRMR on this combined data, and as a result, the success rate was measured as 93.1%. As a result of the literature review, it was concluded that this study showed an effective and high performance for tomato leaf disease detection.
Artificial Intelligence Conscious Agriculture CNN mRMR Classification
Birincil Dil | İngilizce |
---|---|
Konular | Bilgisayar Sistem Yazılımı |
Bölüm | Research Articles |
Yazarlar | |
Yayımlanma Tarihi | 29 Haziran 2024 |
Gönderilme Tarihi | 3 Haziran 2024 |
Kabul Tarihi | 26 Haziran 2024 |
Yayımlandığı Sayı | Yıl 2024 |