Hybrid AI method achieves 99.17% accuracy in solar panel defect detection

Researchers have developed a hybrid approach for automated solar panel defect detection, combining handcrafted features with deep learning. The method utilizes Local Binary Pattern, Histogram of Gradients, and Gabor filters for handcrafted features, and DenseNet-169 for deep features. When concatenated and fed into classifiers like Support Vector Machines (SVM), Extreme Gradient Boost (XGBoost), and Light Gradient-Boosting Machine (LGBM), this hybrid framework demonstrated superior performance. Notably, the DenseNet-169 combined with Gabor filters and an SVM classifier achieved an accuracy of 99.17%, outperforming other systems and offering a robust solution for continuous monitoring and fault detection in solar panel systems. AI

IMPACT This hybrid AI approach offers a highly accurate and efficient method for automated solar panel monitoring, potentially improving energy efficiency and reducing maintenance costs in solar power generation.

RANK_REASON Research paper detailing a novel hybrid AI method for defect detection. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• DenseNet-169
• Histogram of Gradients
• LightGBM
• Local binary patterns
• Muhammad Junaid Asif
• support vector machine
• XGBoost

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →