Intellectual Property India Publishes Patent Application for 'Multivariate Time Series Forecasting System Using Hybrid Deep Learning Models With Cyclical Feature Engineering' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122118 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'multivariate time series forecasting system using hybrid deep learning models with cyclical feature engineering.'

Inventor(s) include Dr. Vijayasherly V; Prakhar Vishwas; Shreyansh Saurav; and Srajal Agarwal.

The application for the patent was published on Jan. 2, under issue no. 01/2026.

According to the abstract released by the Intellectual Property India: "The present disclosure provides a multivariate time series forecasting system including a data preprocessing module configured to receive multivariate climate datasets and perform normalization operations, a cyclical feature engineering module configured to generate cyclical temporal features by applying sine and cosine transformations to encode temporal patterns, a hybrid deep learning architecture including Long Short-Term Memory network, Gated Recurrent Unit network, and one-dimensional Convolutional Neural Network configured to process sequential input data and learn temporal dependencies, a multi-output prediction module configured to simultaneously forecast multiple climate variables, and a model training module configured to train the hybrid architecture using preprocessed data with cyclical features. The system processes climate datasets through a systematic workflow (FIG. 1) where raw data flows through preprocessing, feature engineering, model training, validation, and prediction stages to generate temperature and pressure forecasts."

Disclaimer: Curated by HT Syndication.