A Primer On Large Intelligent Surface for Wireless Sensing in an Industrial Setting

Abstract: One of the beyond-5G developments that is often highlighted is the integration of wireless communication and radio sensing. This paper addresses the potential of communication-sensing integration of Large Intelligent Surfaces (LIS) in an exemplary Industry 4.0 scenario.Besides the potential for high throughput and efficient multiplexing ofwireless links, an LIS can offer a high-resolution rendering of the propagation environment. This is because, in an indoor setting, it can be placed in proximity to the sensed phenomena, while the high resolutionis offered by densely spaced tiny antennas deployed over a large area. By treating an LIS as a radio image of the environment, we develop sensing techniques that leverage the usage of computer vision combined with machine learning. We test these methods for a scenario where we need to detect whether an industrial robot deviates from a predefined route.The results show that the LIS-based sensing offers high precision and has a high application potential in indoor industrial environments.

Here it is included the source code for the paper as well as the dataset used for obtaining the results.

Dataset images should be named as: #classindex_imageindex.png.

The order of execution of the scripts is the following:

1. Use the config.py to set up the origin dataset directory, directory for using later the scripts and final result directory. Choose also the class names. 

2. Execute build_dataset.py to generate the folder structure needed.

3. Execute extract_features.py to perform the VGG19 feature extraction for transfer learning.

4. Use train.py to train and evaluate the results.

Link to the paper: https://link.springer.com/content/pdf/10.1007/978-3-030-73423-7.pdf#page=134

If you consider using this code or part of it, please cite: 

@inproceedings{rubio2021primer,
  title={A Primer on Large Intelligent Surface (LIS) for Wireless Sensing in an Industrial Setting},
  author={Rubio, Cristian Jes{\'u}s Vaca and Espinosa, Pablo Ramirez and Williams, Robin Jess and Kansanen, Kimmo and Tan, Zheng-Hua and De Carvalho, Elisabeth and Popovski, Petar},
  booktitle={EAI CROWNCOM 2020-15th EAI International Conference on Cognitive Radio Oriented Wireless Networks},
  year={2021}
}