MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202641082455 A) filed by Indian Institute Of Technology Hyderabad on July 03, 2026, for Systems And Methods For Classifying Wireless Signals In Wideband Radio Frequency (rf) Environments.
Inventors include Sundaram Vanka; Sumohana Channappayya; Shaurya Singh; Aman Kumar; and Jay Vikrant.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: A wireless signal processing system and computer-implemented method for localization-aware wireless signal classification in wideband environments are disclosed. The system includes a receiver configured to acquire radio frequency (RF) signals and generate signal samples, a processing engine configured to process the signal samples into signal portions, a segmentation engine configured to generate signal segments, and a classification engine configured to classify the signal segments to determine signal characteristics including signal type, protocol, or modulation. The segmentation engine may introduce variations in segment boundaries including temporal truncation, boundary misalignment, inclusion of noise-only samples, or overlap with adjacent signal transmissions. The classification engine includes a complex-valued multiscale state space model having complex-valued recurrent hidden states configured to preserve amplitude and phase information while modeling temporal evolution of RF signals across multiple temporal scales. The classification engine is trained using signal segments generated by substantially the same segmentation process used during deployment to improve robustness under additive noise, multipath fading, and interference. (Fig. 4)
Disclaimer: Curated by HT Syndication.
