Transfer Learning Approach Leveraging EfficientNetV2L to Enhance ‎Skin Disease Prediction through Data Augmentation

Soufiane HAMIDA; Oussama El Gannour; Bouchaib Cherradi

Article Details

Transfer Learning Approach Leveraging EfficientNetV2L to Enhance ‎Skin Disease Prediction through Data Augmentation

Authors:

Soufiane HAMIDA | Oussama El Gannour | Bouchaib Cherradi

Publisher:

African Journal of Management, Engineering and Technology

Journal:

African Journal of Management, Engineering and Technology Vol.2 Issue 1, pp.11-23

Document Type:

Article

Publication Date:

4/2024

Document Language:

English

Document ID (Org No.):

2001840139

Abstract:

 Data imbalance is a common challenge in machine learning, particularly in medical image analysis tasks such as skin disease prediction. Melanoma, a type of skin cancer, is a prime example of a rare disease where the number of positive cases (minority class) is significantly smaller than the negative cases (majority class). This imbalance can lead to biased models that perform poorly in predicting rare diseases. Data augmentation techniques offer a solution by artificially increasing the number of minority class samples, thereby addressing the imbalance issue and improving the generalization of transfer learning models. In this paper, we focus on the application of data augmentation to balance the dataset for skin disease prediction. We specifically evaluate the performance of the Tuned EfficientNetV2L based classifier, a state-of-the-art model known for its efficiency and effectiveness in image classification tasks. Our experiments are conducted on a comprehensive collection of medical images and associated data of skin lesions sourced from various sources. These images represent diverse skin conditions, including both common and rare diseases, to ensure the robustness of our evaluation. To assess the performance of our approach, we employ various performance evaluation metrics such as accuracy, precision, and recall. These metrics provide insights into the classifier's ability to correctly classify skin lesions, especially rare diseases like melanoma.

Article Details

Transfer Learning Approach Leveraging EfficientNetV2L to Enhance ‎Skin Disease Prediction through Data Augmentation

Authors: Soufiane HAMIDA | Oussama El Gannour | Bouchaib Cherradi

Publisher: African Journal of Management, Engineering and Technology

Journal: African Journal of Management, Engineering and Technology Vol.2 Issue 1, pp.11-23

Document Type: Article

Publication Date: 4/2024

Document Language: English

Document ID (Org No.): 2001840139

Issues

Authors:

Soufiane HAMIDA | Oussama El Gannour | Bouchaib Cherradi

Publisher:

African Journal of Management, Engineering and Technology

Journal:

African Journal of Management, Engineering and Technology Vol.2 Issue 1, pp.11-23

Document Type:

Article

Publication Date:

4/2024

Document Language:

English

Document ID (Org No.):

2001840139