MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202511107832 A) filed by Dr. Rishika Shah, Dubai, U.A.E., on Nov. 6, 2025, for 'python implemented method for validating artificial neural network based outdoor thermal comfort predictions in urban street canyons.'
Inventor(s) include Dr. Rishika Shah.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The present invention discloses a Python-implemented system and method for validating ANN-based outdoor thermal comfort predictions in urban street canyons. A modular architecture comprises Data Ingestion (201), Schema & QC (202), Feature Reconciliation (203), ANN Inference Bridge (204), Validation Engine (205), Stratified Diagnostics (206), Drift & Stability Monitor (207), Uncertainty Estimation (208), Calibration Module (209), and Reporting & Provenance (210), interconnected via an outputs bus (211) and optionally a Sensor Interface Hub (212). The method orchestrates ingest (221), QC (222), reconcile (223), infer (224) using an ANN with input, hidden, and output layers (241-243), compute metrics (225) including RMSE (261), MAE (262), R (263), and Index of Agreement (264) with bootstrap intervals, diagnose strata (226), calibrate (227) via governed post-mapping, and report (228) with provenance. The invention enables reproducible, uncertainty-aware validation, drift detection, and portable calibration for trustworthy deployment of thermal-comfort indices across seasons, sites, and sensor configurations, with audit-ready HTML/PDF reports and JSON summaries."
Disclaimer: Curated by HT Syndication.
