MUMBAI, India, Feb. 13 -- Intellectual Property India has published a patent application (202641007797 A) filed by Jawaharlal Nehru Technological University, Hyderabad, Telangana, on Jan. 27, for 'a wired-logic based partial product generator for modified booth multipliers.'
Inventor(s) include A Lakshmi; and P Chandrasekhar Reddy.
The application for the patent was published on Feb. 13, under issue no. 07/2026.
According to the abstract released by the Intellectual Property India: "A method for channel estimation and signal detection in Orthogonal Frequency-Division Multiplexing (OFDM) systems utilizing deep learning-based architectures is proposed and designed. The proposed approach advances from conventional OFDM receivers by eliminating the need for explicit channel state information (CSI) estimation. Instead, the system employs deep learning models trained to implicitly learn CSI and directly recover transmitted symbols in an end-to-end manner. Training data is generated through simulation of wireless channel conditions, including distortion and fading, based on predefined channel measurements. A deep learning model is trained using this data to enable robust symbol recovery under time varying channel conditions. Various deep learning model architectures are developed and evaluated against the Minimum Mean Square Error (MMSE) estimator."
Disclaimer: Curated by HT Syndication.
