• Miss.Surbhi Atul Purwat
• Nandkishor G. Dharashive
• Rohini B. Late

Skin diseases affect millions of people worldwide and require accurate diagnosis for effective treatment. Traditional diagnostic methods often depend on expert dermatologists and manual examination, which may lead to delays and errors. This proposed system introduces a Genetic Algorithm Optimized Stacking Approach for Skin Disease Detection using deep learning techniques. The system combines multiple models including ResNet50, DenseNet121, and CNN through an ensemble stacking framework optimized by a Genetic Algorithm. Image preprocessing techniques such as resizing, normalization, and augmentation improve data quality and model performance. The proposed model is trained on the DermNet dataset containing more than 19,000 images across 23 skin disease classes. Experimental results demonstrate improved classification accuracy and Top-5 accuracy compared to individual models. The system provides an efficient and reliable solution for automated skin disease diagnosis and supports healthcare professionals in decision-making.

Skin Disease Detection, Deep Learning, Genetic Algorithm, Ensemble Learning

"Deep Learning Based Skin Disease Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 9, page no.b125-b131, September-2026, Available :http://www.jetir.org/papers/JETIR2609114.pdf

"Deep Learning Based Skin Disease Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 9, page no. ppb125-b131, September-2026, Available at : http://www.jetir.org/papers/JETIR2609114.pdf