CNN-Based LOS/NLOS Identification in 3-D Massive MIMO Systems
In this letter, we propose to identify line-of-sight (LOS) and non-line-of-sight (NLOS) conditions based on a convolutional neural network (CNN) in urban 3-D massive MIMO systems. The proposed method includes two parts. In the first part, given that the paths spread differently in time domain, we co...
Gespeichert in:
Veröffentlicht in: | IEEE communications letters 2018-12, Vol.22 (12), p.2491-2494 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | In this letter, we propose to identify line-of-sight (LOS) and non-line-of-sight (NLOS) conditions based on a convolutional neural network (CNN) in urban 3-D massive MIMO systems. The proposed method includes two parts. In the first part, given that the paths spread differently in time domain, we combine the normalized tap energy distribution on each antenna utilizing sounding reference signals and construct the coordinated tap energy matrix. In the second part, we train a CNN to analyze the matrix and identify the LOS/NLOS conditions. A 3-D massive MIMO channel model is considered in our simulation. Results show that error rates of the worst performance using proposed identification algorithm are lower than 2.4%, and a remarkable improvement is achieved compared with schemes that exploit the space-time-frequency channel correlation features. |
---|---|
ISSN: | 1089-7798 1558-2558 |
DOI: | 10.1109/LCOMM.2018.2872522 |