MultiModal Dataset for Machine Learning Applied to Telecommunications

Abstract

Gathering channel data to test telecommunication systems is an essential step to guarantee the quality of the product. However, it can be a slow process and demand a considerable amount of effort and investment since it is costly to make field measurements of mmWaves. Having a ready dataset at disposal make things way faster and cheaper, allowing a developer to focus on more specific tasks. This paper presents an entire multimodal dataset with different kinds of information like channel communication, urban traffic and obstacles position, got from two realistic computer simulations made in two different city models: Beijing and Rosslyn. It also includes detailed information on how each data is stored.

Generating MIMO Channels For 6G Virtual Worlds Using Ray-tracing Simulations

“…The input to this network are features Θ t,1 extracted from a LIDAR simulator for two plots. The other two plots are obtained with a distinct NN architecture, which uses multimodal (MM) data (LIDAR, position, and images) as inputs [7]. Each of these two architectures were used with two distinct versions of the s008 dataset: one with the new and correct orientation (CO), while the other antenna arrays had a fixed orientation (FO) regardless any vehicle rotation.…”

“…For instance, P = 1 was adopted in [6], which assumed the raw data from a LI-DAR sensor was converted to features Θ t,1 . In [7], P = 3 distinct feature modalities were adopted: Θ t,1 with positions from a GNSS (GPS) receiver, Θ t,2 with resampled images from RGB cameras and Θ t,3 with features from LIDAR [8].…”