WEL-ODKC: weighted extreme learning optimal diagonal-kernels convolution model for accurate classification of skin lesions

ABSTRACT

This paper presents a new model, the Weighted Extreme Learning Machine optimized Diagonal-Kernels Convolution (WELM-ODKC), for automatic skin cancer detection that addresses imbalanced data and eliminates inter-operator variability. The model combines the WELM and the Enhanced Remora Optimization Algorithm (EROA) with the Diagonal-Kernels Convolution Neural Network (DKCNN) to enhance the weight function and accurately predict skin lesion class. The model was evaluated on the MNIST HAM10000 and PAD-UFES-20 datasets and outperformed other existing skin cancer classification methods such as SVM BWO, CNN, DGC-NB, and GWO-CNN. The accuracy, recall, precision, and F1-score were used to evaluate the performance of WEL-ODKC, and the results show a high accuracy during training and validation. The proposed model efficiently classifies different types of skin cancer images from the two baseline datasets and provides promising results for automatic skin cancer detection.

KEYWORDS:

• Skin cancer
• weighted extreme learning machine (WELM)
• enhanced remora optimization algorithm (EROA)
• diagonal-kernels convolution neural network (DKCNN)
• accuracy

Disclosure statement

No potential conflict of interest was reported by the author(s).

Human and animal rights

This article does not contain any studies with human or animal subjects performed by any of the authors.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Additional information

Notes on contributors

V. Auxilia Osvin Nancy

V. Auxilia Osvin Nancy (Auxilia Osvin Nancy Vincent) obtained her bachelor's degree in Information Technology (B.Tech) from Sri Balaji Chockalingam Engineering College, Madras University. Then she obtained her Master's degree in Information Technology (M.Tech) from Sathyabama University. From 2008 to 2020, she worked as an assistant professor in the SA Engineering College. She is currently doing a PhD in Computer Science at the SRM Institute of Science and Technology, majoring in deep learning. She has published papers related to the research work. Her specializations include deep learning, machine learning, and digital video and image processing.

P. Prabhavathy

Dr. P. Prabhavathy (Prabhavathy Pachaiyappan) received a bachelor's degree in computer science from Tagore Engineering College, affiliated with Anna University, in 2005. She completed an M.E. at Crescent Engineering College in 2010 and a Ph.D. at Anna University in 2017. From 2011 to 2020, she worked as a teaching fellow at Anna University. She is currently an Assistant Professor (Selection Grade) in the Department of Computer Science and Engineering at the SRM Institute of Science and Technology. She has published many research articles in reputed journals. Her research interests are in networking, data processing systems, and mobile computing.

Meenakshi S. Arya

Dr. Meenakshi S. Arya (Meenakshi Sumeet Arya) is an experienced academician with a demonstrated history of working in the education management industry. Skilled in machine learning, deep learning, big data analytics, algorithms, data structures, and C++ (a programming language). Strong education professional with Ph.D. (Computer Science and Engineering), Jaypee University of Information Technology, Solan, Feb 2014. M.Tech.(Computer Engineering), University of Pune, College of Engineering, Pune, May 2010; B.Tech.(Computer Science and Technology), S.N.D.T. Women's University, Mumbai, Institute of Technology for Women, May 2003. She had many publications, and she is currently working as a professor and associate director in the School of Artificial Intelligence at MIT (World Peace University).