2025 BrainChip Discussion, page-155

Unpublished conference/Abstract (Scientific congresses, symposiums and conference proceedings)

Enhanced Demodulator for 5G NTN using Spatio-Temporal Attention Convolutional Autoencoder and Akida Brainchip SNN

VARADARAJULU, Swetha; OLIVEIRA KUHFUSS DE MENDONÇA, Marcele; EAPPEN, Geoffrey et al.

2024 • The conference at which the Contributor proposes to present the Content, titled: 41st International Communications Satellite Systems Conference (ICSSC 2024)

Editorial reviewed

Permalink
https://hdl.handle.net/10993/63270

Files

Full Text

Channel_Estimation_Equalisation_CNN_SNN_Akida_ICSSC_Conf-18.pdf

Author postprint (730.1 kB)

Request a copy

All documents in ORBilu are protected by a user license.

Send to

RISBibTexAPAChicagoPermalinkXLinkedin

Details

Keywords :

CNN-STAN; Channel estimation; CNN2SNN; Akida Brainchip

Abstract :

[en] This paper presents a novel approach to overcoming challenges in 5G and 6G mobile satellite systems (MSS) in Low Earth Orbit (LEO), focusing on Non-Line-of-Sight (NLOS) issues in 5G Non-Terrestrial Networks (NTN) that connect directly with handheld devices. We utilize a Convolutional Neural Network (CNN) with a Spatio-Temporal Attention Network (STAN) au- toencoder, which is then converted into a Spiking Neural Network (SNN) using Brainchip Akida’s Meta TF Software Framework. This integration of neuromorphic processing aims to enhance energy efficiency, reduce computational demands, and increase data transmission rates, optimizing Channel State Information (CSI) in compliance with 3GPP standards. Our STAN-CNN- SNN architecture achieves a 85% reduction in computational requirements, leading to decrease in power consumption, and increase in data rates within the C-Band spectrum. Simulations with LEO satellite MSS parameters demonstrate significant advancements in communication systems. The numerical results demonstrates substantial computational reductions with minimal capacity trade-offs.

Research center :

Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM - Signal Processing & Communications

Disciplines :

Computer science

Author, co-author :

VARADARAJULU, Swetha ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom

OLIVEIRA KUHFUSS DE MENDONÇA, Marcele ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom

EAPPEN, Geoffrey ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust > SigCom > Team Symeon CHATZINOTAS

QUEROL, Jorge ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom

CHATZINOTAS, Symeon ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom

External co-authors :

no

Language :

English

Title :

Enhanced Demodulator for 5G NTN using Spatio-Temporal Attention Convolutional Autoencoder and Akida Brainchip SNN

Publication date :

24 September 2024

Number of pages :

1-6

Event name :

The conference at which the Contributor proposes to present the Content, titled: 41st International Communications Satellite Systems Conference (ICSSC 2024)

Event place :

Seattle, United States

Event date :

24-27 September, 2024

By request :

Yes

Peer reviewed :

Editorial reviewed

Focus Area :

Security, Reliability and Trust

FnR Project :

Tan

Name of the research project :

U-AGR-8297 - ESA-TANNDEM - QUEROL Jorge

Available on ORBilu :

since 18 December 2024

A: