Classification Optimization of Skin Cancer Using the Adaboost Algorithm
International Journal of Artificial Intelligence in Medical Issues · 2023
DOI: 10.56705/ijaimi.v1i1.86 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Artificial Intelligence in Medical Issues, 2023. Verfasst von Sumiyatun und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Early detection of melanoma skin cancer is crucial in improving prognosis and saving lives. This research aimed to optimize the classification of melanoma images using the Adaboost algorithm. Employing a dataset of 10,000 melanoma images, the study combined the Canny method for image segmentation, Hu Moments for feature extraction, and the Adaboost algorithm for classification. The 5-fold cross-validation results revealed an average accuracy of 61.52%. While the precision consistently surpassed recall, indicating the model's conservative nature in predicting positive cases. The outcomes align with previous research, emphasizing the challenges in melanoma classification. This study contributes to the domain by showcasing the potential and areas of improvement for machine learning in early melanoma detection. Future research is recommended to explore hybrid models and diversify data sources for enhanced robustness and generalizability.
Zitieren
APA
Sumiyatun, & Maulidinnawati, A. (2023). Classification Optimization of Skin Cancer Using the Adaboost Algorithm. International Journal of Artificial Intelligence in Medical Issues. https://doi.org/10.56705/ijaimi.v1i1.86
Vancouver
Sumiyatun, Maulidinnawati A. Classification Optimization of Skin Cancer Using the Adaboost Algorithm. International Journal of Artificial Intelligence in Medical Issues. 2023. doi:10.56705/ijaimi.v1i1.86
BibTeX
@article{Sumiyatun2023,
author = {Sumiyatun and Maulidinnawati, Andi},
title = {Classification Optimization of Skin Cancer Using the Adaboost Algorithm},
journal = {International Journal of Artificial Intelligence in Medical Issues},
year = {2023},
doi = {10.56705/ijaimi.v1i1.86}
}
EUVIMED