Abstract
Intelligent optimization algorithms have advantages in dealing with complex nonlinear problems accompanied by good flexibility and adaptability. In this paper, the FCBF (Fast Correlation-Based Feature selection) method is used to filter irrelevant and redundant features in order to improve the quality of cancer classification. Then, we perform classification based on SVM (Support Vector Machine) optimized by PSO (Particle Swarm Optimization) combined with ABC (Artificial Bee Colony) approaches, which is represented as PA-SVM. The proposed PA-SVM method is applied to nine cancer datasets, including five datasets of outcome prediction and a protein dataset of ovarian cancer. By comparison with other classification methods, the results demonstrate the effectiveness and the robustness of the proposed PA-SVM method in handling various types of data for cancer classification.
Highlights
Owing to no obvious early symptoms of cancer, most of patients are diagnosed at an advanced stage [1], which usually results in high costs with a poorer prognosis
ABC (Artificial Bee Colony) approaches, which is represented as PA-SVM
By comparison with other classification methods, the results demonstrate the effectiveness and the robustness of the proposed PA-SVM method in handling various types of data for cancer classification
Summary
Owing to no obvious early symptoms of cancer, most of patients are diagnosed at an advanced stage [1], which usually results in high costs with a poorer prognosis. The probability of recurrence or metastasis after surgery is higher than 90% after five years, as cancer treatment is not thorough. The problem of completely clearing the remaining cancer cells is not solved, and the recurrence rate and mortality rate of cancer are still quite high. If we can make full use of available human expression profiles and realize repeatable diagnoses, there is no doubt that it will bring great convenience to cancer patients. A large number of irrelevant and redundant values exist in expression profiles. The high dimensionality and small sample bring great difficulties to the data processing. Researchers have proposed various methods [4,5,6,7,8] to deal with these problems
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
