MUMBAI, India, Jan. 23 -- Intellectual Property India has published a patent application (202531133715 A) filed by Kalinga Institute Of Industrial Technology, Bhubaneswar, Orissa, on Dec. 30, 2025, for 'hyperparameter tuning system for machine learning depression prediction.'
Inventor(s) include Panda, Amiya Ranjan; Roy, Sattwik; Mishra, Manoj Kumar; Sahoo, Soumyashree; and Mohapatra, Subhranshu.
The application for the patent was published on Jan. 23, under issue no. 04/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a computing system including a processor and memory configured to perform hyperparameter tuning of machine learning classifiers for depression prediction, wherein the computing system implements multiple automated search techniques including grid search, random search, and Bayesian optimization for hyperparameter optimization, performs cross-validation to prevent overfitting during the hyperparameter tuning process, and evaluates model performance by comparing optimization results across the multiple automated search techniques. The machine learning classifiers include K-Nearest Neighbors classifier, Support Vector Classifier, Logistic Regression classifier, and AdaBoost classifier. The hyperparameter tuning defines search spaces for hyperparameters including n_neighbors and metric parameters for K-Nearest Neighbors, C and kernel parameters for Support Vector Classifier, regularization strength and penalty parameters for Logistic Regression, and n_estimators and learning_rate parameters for AdaBoost. The cross-validation includes k-fold cross-validation with multiple data splits for robust performance assessment."
Disclaimer: Curated by HT Syndication.
