MUMBAI, India, June 26 -- Intellectual Property India has published a patent application (202641072807 A) filed by Cvr College Of Engineering on June 12, 2026, for Regularized Statistical Framework For Intelligent Feature Selection For Early Breast Cancer Diagnosis Using Optimized K-Nearest Neighbor Classification.
Inventor includes Vadapally Praveen Kumar.
The application for the patent was published on June 19, 2026, under issue no. 25/2026.
Abstract: The proposed method uses an intelligent learning system which employs optimized K-nearest neighbor (KNN) classification and regularized statistical feature selection (RSFS) techniques for breast cancer diagnosis. This system includes steps like data preprocessing, balancing of classes through synthetic minority oversampling technique (SMOTE), outliers identification with inter-quartile range (IQR), and application of innovative RSFS through L2 regularization and Chi-squared statistic- based approach. KNN classification algorithm is employed for predicting whether a tumor is benign or malignant using selected diagnostic variables. Some of the advantages offered by the system include improved prediction capability, reduced overfitting, removal of redundant features, and provision of assistance to clinicians in their selective decisions mechanisms.
Disclaimer: Curated by HT Syndication.
