Abstract: The successful establishment of any wireless communication link between two entities relies on feedback signalling from both ends to indicate the channel quality as well as the status of previous transmissions. Physical Uplink Control Channel (PUCCH) is the key enabler of such feedback in the uplink direction for a 5G NR link. It is a dedicated channel on which a User Equipment (UE) can send control information to a Base station (gNB). Uplink Control Information (UCI) carried by the PUCCH may include (1) Hybrid Automatic Repeat Request (HARQ) acknowledgments for prior downlink transmissions (gNB to UE), (2) Scheduling Requests (SR) for the subsequent allocation of uplink transmission resources, and (3) Downlink Channel State Information (CSI) reports containing channel quality metrics that facilitate link adaptation, precoding, and downlink resource allocation.

Accurate decoding of this Uplink Control Information (UCI) on the PUCCH is very essential for enabling 5G wireless links. This talk presents an AI/ML - based receiver design for PUCCH Format 0. Format 0 signaling encodes the UCI content within the phase of a known base waveform and even supports multiplexing of up to 12 users within the same time-frequency resources. The proposed novel neural network classifier, which is termed as UCINet0, is capable of predicting when no user is transmitting on the PUCCH, as well as decoding the UCI content for any number of multiplexed users (up to 12). The test results with simulated, hardware-captured (lab) and field datasets (collected from Commercial UEs) show that the UCINet0 model outperforms conventional correlation-based decoders across all Signal-to-Noise Ratio (SNR) ranges and multiple fading scenarios.

Event Details
Title: UCINet0 - A modular Neural Receiver for 5G NR PUCCH Format 0
Date: August 14, 2026 at 3:00 PM
Venue: ESB244 / Google Meet (https://meet.google.com/qms-wkii-kzf)
Speaker: Mr. Jeeva Keshav S (EE22D404)
Guide: Dr. Radhakrishna Ganti
Type: PHD seminar

Updated: