TransPathNet: A Novel Two-Stage Framework for Indoor Radio Map Prediction

2025-01-27 · Xin Li, Ran Liu, Saihua Xu, Sirajudeen Gulam Razul, Chau Yuen

Accurate indoor pathloss prediction is crucial for optimizing wireless communication in indoor settings, where diverse materials and complex electromagnetic interactions pose significant modeling challenges. This paper introduces TransPathNet, a novel two-stage deep learning framework that leverages transformer-based feature extraction and multiscale convolutional attention decoding to generate high-precision indoor radio pathloss maps. TransPathNet demonstrates state-of-the-art performance in the ICASSP 2025 Indoor Pathloss Radio Map Prediction Challenge, achieving an overall Root Mean Squared Error (RMSE) of 10.397 dB on the challenge full test set and 9.73 dB on the challenge Kaggle test set, showing excellent generalization capabilities across different indoor geometries, frequencies, and antenna patterns. Our project page, including the associated code, is available at https://lixin.ai/TransPathNet/.

📄 PDF Abstract BibTeX arXiv:2501.16023

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

The First Indoor Pathloss Radio Map Prediction Challenge

2025-01-23 · Stefanos Bakirtzis, Çağkan Yapar, Kehai Qiu, Ian Wassell 외

To encourage further research and to facilitate fair comparisons in the development of deep learning-based radio propagation models, in the less explored case of directional radio signal emissions in indoor propagation e…

Prediction

IPP-Net: A Generalizable Deep Neural Network Model for Indoor Pathloss Radio Map Prediction

2025-01-11 · Bin Feng, Meng Zheng, Wei Liang, Lei Zhang

In this paper, we propose a generalizable deep neural network model for indoor pathloss radio map prediction (termed as IPP-Net). IPP-Net is based on a UNet architecture and learned from both large-scale ray tracing simu…

Prediction

Machine-Learning-Based Classification of Radio Frequency Building Loss

2026-04-27 · Jiayi Tan, Neelabhro Roy, James Gross, Rohit Chandra 외 arxiv

Accurate modeling of outdoor-to-indoor (O2I) and indoor-to-indoor (I2I) signal loss is important for improving indoor wireless network performance in dense urban areas. Traditional on-site measurements are expensive, tim…

Practical Simplified Indoor Multiwall Path-Loss Model

2020-09-24 · Taewon Kang, Jiwon Seo

Over the past few decades, attempts had been made to build a suitable channel prediction model to optimize radio transmission systems. It is particularly essential to predict the path loss due to the blockage of the sign…

model

Vision Transformers for Efficient Indoor Pathloss Radio Map Prediction

2024-12-12 · Rafayel Mkrtchyan, Edvard Ghukasyan, Khoren Petrosyan, Hrant Khachatrian 외

Indoor pathloss prediction is a fundamental task in wireless network planning, yet it remains challenging due to environmental complexity and data scarcity. In this work, we propose a deep learning-based approach utilizi…

Data Augmentation Feature Engineering