Maize seeds forecasting with hybrid directional and bi‐directional long short‐term memory models

• Published in: Food science & nutrition 2024-02, Vol.12 (2), p.786-803
• Main Authors: Isik, Hakan, Tasdemir, Sakir, Taspinar, Yavuz Selim, Kursun, Ramazan, Cinar, Ilkay, Yasar, Ali, Yasin, Elham Tahsin, Koklu, Murat
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial intelligence; Classification; Corn; Cultivars; Datasets; Deep learning; Discriminant analysis; Forecasting; hybrid CNN; Image classification; Long short-term memory; Machine learning; maize seeds; Morphology; Neural networks; Original; purification; Seeds; Success; Support vector machines; Transfer learning; Trees
• ISSN: 2048-7177; 2048-7177
• DOI: 10.1002/fsn3.3783

The purity of the seeds is one of the important factors that increase the yield. For this reason, the classification of maize cultivars constitutes a significant problem. Within the scope of this study, six different classification models were designed to solve this problem. A special dataset was created to be used in the models designed for the study. The dataset contains a total of 14,469 images in four classes. Images belong to four different maize types, BT6470, CALIPOS, ES_ARMANDI, and HIVA, taken from the BIOTEK company. AlexNet and ResNet50 architectures, with the transfer learning method, were used in the models created for the image classification. In order to improve the classification success, LSTM (Directional Long Short‐Term Memory) and BiLSTM (Bi‐directional Long Short‐Term Memory) algorithms and AlexNet and ResNet50 architectures were hybridized. As a result of the classifications, the highest classification success was obtained from the ResNet50+BiLSTM model with 98.10%. A special dataset was created to be used in the models designed for the study. The dataset contains a total of 14,469 images in four classes. Images belong to four different maize types, BT6470, CALIPSO, ES_ARMANDI, and HIVA, taken from the BIOTEK company. AlexNet and ResNet50 architectures, with the transfer learning method, were used in the models created for the image classification. In order to improve the classification success, LSTM (directional long short‐term memory) and BiLSTM (Bi‐directional long short‐term memory) algorithms and AlexNet and ResNet50 architectures were hybridized.