Journal
COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING
Volume 25, Issue 7, Pages 794-807Publisher
TAYLOR & FRANCIS LTD
DOI: 10.1080/10255842.2021.1981300
Keywords
Boundaries tuned support vector machines (BT-SVM) classifier; particle swarm optimization; wrapper model algorithm; principal component analysis
Ask authors/readers for more resources
The study focuses on detecting cancer-causing genes in microarray data analysis, utilizing techniques like Improved Supervised Principal Component Analysis and Support Vector Machines, with validation on various experimental datasets. The proposed work was compared with traditional techniques, demonstrating optimum accuracy, recall, precision, and training time.
In recent days, the identified genes which are detecting cancer-causing diseases are plays a crucial part in the microarray data analysis. Huge volume of data required since the disease changed often. Conventional data mining techniques are lacking in space concern and time complexity. Based on big data the proposed work is executed. Using the ISPCA - Improved Supervised Principal Component Analysis, feature extraction is developed in this study. For gene expression, co-variance matrix is generated and through feature selection cancer classification is performed by IPSCA. Further feature selection process by boundaries tuned support vector machines (BT-SVM) classifier and modified particle swarm optimization with novel wrapper model algorithm are performed. The experimentation is carried out by utilizing different datasets like leukaemia, breast cancer dataset, brain cancer, colon, and lung carcinoma from the UCI repository. The proposed work is executed on six benchmark dataset for DNA microarray data in terms of accuracy, recall, and precision to evaluate the performance of the proposed work. For evaluating the proposed work effectiveness, it is compared with various traditional techniques and resulted in optimum accuracy, recall, precision and training time with and without feature selection effectively.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available