MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202521128940 A) filed by Symbiosis International, Pune, Maharashtra, on Dec. 18, 2025, for 'system and method for predicting air quality index using long short-term memory neural networks.'
Inventor(s) include Dr. Sandeep Kumar; Aman Rahangdale; Shweta Kushwaha; and Meet Kansal.
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: "A computer-implemented system for predicting Air Quality Index using Long Short-Term Memory neural networks is disclosed. The system comprises a processor and memory storing executable instructions. A data acquisition module collects historical environmental data including pollutant concentration levels and meteorological parameters from monitoring stations via a network. A data processing module preprocesses the data by handling missing values, normalizing features, and formatting temporal sequences. A feature extraction module engineers temporal features including lag variables, moving averages, and temporal patterns. A model building module trains a recurrent neural network comprising Long Short-Term Memory layers with dropout regularization and early stopping to capture sequential dependencies. A validation module evaluates model performance using Root Mean Square Error and Mean Absolute Error metrics. A prediction module generates forecasted Air Quality Index values and visualization outputs. The system achieves improved prediction accuracy over traditional statistical forecasting through hierarchical temporal feature learning."
Disclaimer: Curated by HT Syndication.
