IRDM: A Generative Diffusion Model for Indoor Radio Map Interpolation
Authors:
- 4 December 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-06
Abstract
This article proposes a novel methodology for interpolating path-loss radio maps, which are vital for comprehending signal distribution and hence planning indoor wireless networks. The approach employs generative diffusion models and proves to be highly effective in generating accurate radio maps with only a small number of measurements. The experimental outcomes demonstrate an average root-mean-square error of 4.23 dB using only 10 percent of the reference points, highlighting the ability of the generative diffusion model to achieve significant interpolation accuracy in radio map generation.Keywords
This publication has 18 references indexed in Scilit:
- A Survey on Generative Diffusion Models_supp1-3361474.pdf2024
- Pseudo Ray-Tracing: Deep Leaning Assisted Outdoor mm-Wave Path Loss PredictionIEEE Wireless Communications Letters, 2022
- Improving Positioning Accuracy Using WLAN Optimization for Location Based Services and Cognitive Radio Networks2022
- Image-Driven Spatial Interpolation With Deep Learning for Radio Map ConstructionIEEE Wireless Communications Letters, 2021
- FadeNet: Deep Learning-Based mm-Wave Large-Scale Channel Fading Prediction and its ApplicationsIEEE Access, 2020
- WiFi-Based Indoor Robot Positioning Using Deep Fuzzy ForestsIEEE Internet of Things Journal, 2020
- Model-Aided Deep Learning Method for Path Loss Prediction in Mobile Communication Systems at 2.6 GHzIEEE Access, 2020
- Wi-Fi Fingerprint Radio Map Creation by Using InterpolationProcedia Engineering, 2017
- Ray Tracing for Radio Propagation Modeling: Principles and ApplicationsIEEE Access, 2015
- A Ray Launching-Neural Network Approach for Radio Wave Propagation Analysis in Complex Indoor EnvironmentsIEEE Transactions on Antennas and Propagation, 2014