TY - JOUR ID - 137356 TI - An Empirical Study of Nail Fungus Classification Using Deep and Traditional Machine Learning Methods JO - Journal of Bioengineering Research JA - JBR LA - en SN - 2645-5633 AU - Izadi, Vahid AU - Morovati, Mehdi AU - Ranjbaran, Golshid AU - Homayounmajd, Shahabedin AD - Department of Mechanical Engineering and Engineering Science, University of North Carolina at Charlotte, Charlotte, USA AD - Department of Electrical and Computer, Science and Research Branch, Islamic Azad University, Tehran, Iran Y1 - 2021 PY - 2021 VL - 3 IS - 3 SP - 16 EP - 23 KW - Deep Learning KW - Feature Extraction KW - Conventional Machine Learning KW - Nail Fungus DO - 10.22034/jbr.2021.295687.1043 N2 - Some of the main human health hazards occur through the consumption of fungus. It is detrimental to food and threatens human health. Fungus’s symptom is not clear, making them extremely harmful to human and food resources. Over the past few decades, many studies have been conducted on the early detection of fungus existence in biological systems. Fungus’s symptom is not clear, making them extremely harmful to human and food resources. Over the past few decades, many studies have been conducted on the early detection of fungus existence in biological systems. In this paper, we study and implement machine learning methods that can detect and classify fungus using nail finger fungus images. Our study shows that the neural network-based method and more importantly deep learning method using state-of-the-art CNN models have higher predictive performance compared to that of other machine learning approaches.Keywords: Deep Learning, Feature Extraction, Conventional Machine Learning, Nail Fungus UR - https://www.journalbe.com/article_137356.html L1 - https://www.journalbe.com/article_137356_86044f08c1415fc7334979a50a49b45c.pdf ER -