LoRa Modulation for Split Learning

TL;DR

This paper presents a novel communication scheme combining LoRa modulation with split learning, utilizing an expressive neural network with adaptive activation functions for efficient data transmission over challenging channels.

Contribution

It introduces a task-oriented communication design using LoRa and a new neural network architecture with adaptive activation functions for split learning.

Findings

Achieves high accuracy in low SNR conditions

Effective in scenarios without channel state information

Demonstrates robustness over AWGN and Rayleigh fading channels

Abstract

In this paper we introduce a task-oriented communication design for split learning (SL) over a communication channel. Our approach involves the Expressive Neural Network (ENN), a novel neural network featuring adaptive activation functions (AAF) based on the Discrete Cosine Transform (DCT). This architecture does not only provide better learning capabilities, but also facilitates data transmission using the Long Range (LoRa) modulation. The frequency nature of LoRa is adequate for the communication side of the problem, while allowing to construct the AAFs at the receiver. Additionally, we propose orthogonal chirp division multiplexing (OCDM) for multiple access and a modified modulation aimed at preserving communication bandwidth. Our experimental results demonstrate the effectiveness of this scheme, achieving high accuracy in challenging scenarios, including low signal to noise Ratio (SNR) and absence of channel state information (CSI) for both additive white Gaussian noise (AWGN) and Rayleigh fading channels.