Detection of sunn pest-damaged wheat grains using artificial bee colony optimization-based artificial intelligence...

Area of Science:

• Agricultural Science
• Computer Science
• Image Processing

Background:

• Sunn pest infestation significantly impacts wheat quality.
• Accurate identification of damaged wheat grains (SDG) is crucial for the agricultural industry.
• Existing detection methods may lack efficiency and precision.

Purpose of the Study:

• To develop and present artificial intelligence (AI) models for distinguishing sunn pest-damaged wheat grains (SDG) from healthy wheat grains (HWG).
• To evaluate the performance of AI algorithms in classifying wheat grains based on visual features.
• To create a practical and effective detection system for SDG.

Main Methods:

• Acquired images of 300 Svevo durum wheat grains (150 SDG, 150 HWG).
• Extracted 17 visual features (dimension, texture, pattern) using image processing.
• Implemented Artificial Bee Colony (ABC) optimization-based Artificial Neural Network (ANN) and Extreme Learning Machine (ELM) algorithms.
• Utilized Correlation-based Feature Selection (CFS) to identify the most effective features.

Main Results:

• The ABC-based ANN model achieved high accuracy in classifying SDG.
• Mean Absolute Error (MAE) was 0.00174 and Root Mean Square Error (RMSE) was 0.00433 for the ABC-based ANN using five selected features.
• The developed AI detection system was integrated into user-friendly graphical user interface (GUI) software.

Conclusions:

• The modified ANN algorithm combined with CFS significantly enhances the detection accuracy of damaged wheat grains.
• The proposed AI-driven system offers a practical solution for identifying SDG in wheat.
• This technology has the potential to improve quality control in the wheat industry.