A Machine Learning-Based Framework for Oral Cancer Classification Using Ant Bee Colony Optimization with Support Vector Machine Classifier

Oral cancer (OC) the eighth-fastest spreading malignancy that is currently wreaking havoc on humans, is the one with the highest prevalence in the globe. It is a deadly, widespread malignancy with a high mortality rate. The malignant tumor occurs in several oral regions. It might be difficult for a doctor to diagnose oral cancer. In the field of medicine, novel methods are frequently employed for the categorization and early diagnosis of cancer. The early identification of sickness is a crucial task in the medical domain. The use of classification algorithm plays a crucial role in disease classification. Various hybridized versions of machine learning algorithm along with optimization techniques were used to recognize the disease in its earliest stages. In the proposed strategy, SVM classifier of the machine learning technique and ABCO algorithm were used to classify the resulting features of oral cancer which were produced by feature segmentation and feature extraction process. When the generated results were compared to SVM, the hybrid Ant Bee Colony Optimization Support Vector Machine (ABCOSVM) or MOSVM algorithm outperformed with 99.8% accuracy.