# ConvLoRa: Convolutional Neural Network-Based Collision Demodulation for LoRa Uplinks in LEO-IoT

## TL;DR

This paper introduces ConvLoRa, a new method using neural networks to improve LoRa uplink reliability in satellite-based IoT networks by resolving signal collisions.

## Contribution

ConvLoRa is a novel collision demodulation method for LoRa signals in LEO-IoT using a convolutional neural network with synchronization-robust design and multi-task learning.

## Key findings

- ConvLoRa achieves lower bit error rate (BER) in collision scenarios compared to existing methods like CoRa and SIC-based receivers.
- Under two-signal collisions at SNR = −9 dB and SF = 8, ConvLoRa's BER is 21% of CoRa's and 28% of SIC-based methods.
- The method uses an up-chirp in the preamble and data augmentation to improve robustness to synchronization deviations.

## Abstract

Satellites supporting IoT connectivity may need to serve a large population of LoRa terminals, where collisions among packets using the same spreading factor (SF) can severely degrade uplink reliability. The ALOHA-based access used in LEO-IoT leads to frequent collisions under massive terminal access, which limits system capacity. Conventional signal separation methods that rely on the capture effect typically require a sufficiently large power difference between colliding signals. However, due to the channel characteristics of LEO links, this condition is often difficult to satisfy. We propose ConvLoRa, a collision demodulation method for co-SF LoRa uplink signals in LEO-IoT based on a fully convolutional neural network (FCN). To improve robustness to synchronization deviations, ConvLoRa uses an up-chirp in the preamble as a reference for feature matching, and employs data augmentation to emulate synchronization deviations during training. In addition, a multi-task design is adopted to estimate the payload length with minimal introduction of extra network parameters. Experiments show that ConvLoRa achieves lower demodulation bit error rate (BER) under collision conditions compared with baselines, including CoRa and SIC-based receivers. Under the condition of a two-signal collision with SNR = −9 dB and SF = 8, the BER of the proposed method is 21% that of CoRa and 28% that of the SIC-based method.