G
G S Thejas
Researcher at Texas A&M University System
Publications - 3
Citations - 34
G S Thejas is an academic researcher from Texas A&M University System. The author has contributed to research in topics: Feature selection & Data pre-processing. The author has an hindex of 2, co-authored 3 publications receiving 8 citations.
Papers
More filters
Journal ArticleDOI
A hybrid and effective learning approach for Click Fraud detection
TL;DR: The proposed model, CFXGB (Cascaded Forest and XGBoost), is a combination of two learning models used for feature transformation and classification that showcases its superior performance compared to other related models, and makes a comparison with multiple click fraud datasets with varying sizes.
Journal ArticleDOI
Metric and Accuracy Ranked Feature Inclusion: Hybrids of Filter and Wrapper Feature Selection Approaches
G S Thejas,Rameshwar Garg,S. Sitharama Iyengar,N. R. Sunitha,Prajwal Badrinath,Shasank Chennupati +5 more
TL;DR: In this paper, two hybrid feature selection methods, metric ranked feature inclusion (MRIN) and accuracy ranked feature inclusion (ARIN), are proposed to reduce the computational overhead and improve the correctness of classifier.
Proceedings ArticleDOI
COMB: A Hybrid Method for Cross-validated Feature Selection
TL;DR: This work proposes hybrid FS methods using unsupervised classification, statistical scoring, and a wrapper method for feature selection that represents an advancement in supervised classification.