Optimal transfer learning based nutrient deficiency classification model in ridge gourd (Luffa acutangula).

Area of Science:

• Agricultural Science
• Computer Vision
• Machine Learning

Background:

• Nutrient deficiency in crops like ridge gourd (Luffa acutangula) poses significant challenges to farmers, impacting yield and quality.
• Accurate and early detection of these deficiencies is vital for effective crop management and sustainable agriculture.

Purpose of the Study:

• To develop and evaluate a novel method for classifying nutrient deficiencies in ridge gourd plants.
• To enhance agricultural practices through improved crop health monitoring and targeted interventions.

Main Methods:

• Implementation of the Ring Toss Game Optimization with Deep Transfer Learning-based Nutrient Deficiency Classification (RTGODTL-NDC) framework.
• Utilizing Gabor filters for image pre-processing, SqueezeNet model with Adam optimizer for feature extraction, and a deep hybrid learning model for classification.

Main Results:

• The RTGODTL-NDC method achieved high performance in classifying nutrient deficiencies.
• Demonstrated accuracy of 97.16% and specificity of 98.29% in identifying nutrient deficits in ridge gourd plants.

Conclusions:

• The RTGODTL-NDC framework offers a robust solution for accurate nutrient deficiency detection in ridge gourd.
• This approach has the potential to significantly improve crop management, leading to better agricultural health and resource utilization.