# Coverage Hole Detection for mmWave Networks: An Unsupervised Learning Approach

arXiv: https://arxiv.org/abs/2108.07854 · HTML: https://mlsanity.com/paper/2108.07854/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 12 references that are in the map.
- First posted on arXiv 17 Aug 2021.

## Builds on (most cited first, 6 of 6)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications](https://mlsanity.com/paper/1902.06435/) (2019)
- [Channel Charting: Locating Users within the Radio Environment using Channel State Information](https://mlsanity.com/paper/1807.05247/) (2018)
- [Wireless Localization for mmWave Networks in Urban Environments](https://mlsanity.com/paper/1805.11208/) (2018)
- [Base Station and Passive Reflectors Placement for Urban mmWave Networks](https://mlsanity.com/paper/2011.01920/) (2020)
- [Location Privacy in Cognitive Radio Networks: A Survey](https://mlsanity.com/paper/1806.00750/) (2018)

## Built on by (most cited first, 2 of 2)

- [Data-Driven Radio Environment Map Estimation Using Graph Neural Networks](https://mlsanity.com/paper/2407.07713/) (2024)
- [On Out-of-sample Embedding in UMAP](https://mlsanity.com/paper/2606.04451/) (2026)

## Abstract (arXiv)

The utilization of millimeter-wave (mmWave) bands in 5G networks poses new challenges to network planning. Vulnerability to blockages at mmWave bands can cause coverage holes (CHs) in the radio environment, leading to radio link failure when a user enters these CHs. Detection of the CHs carries critical importance so that necessary remedies can be introduced to improve coverage. In this letter, we propose a novel approach to identify the CHs in an unsupervised fashion using a state-of-the-art manifold learning technique: uniform manifold approximation and projection. The key idea is to preserve the local-connectedness structure inherent in the collected unlabelled channel samples, such that the CHs from the service area are detectable. Our results on the DeepMIMO dataset scenario demonstrate that the proposed method can learn the structure within the data samples and provide visual holes in the low-dimensional embedding while preserving the CH boundaries. Once the CH boundary is determined in the low-dimensional embedding, channel-based localization techniques can be applied to these samples to obtain the geographical boundaries of the CHs.