lhystronger/csi-dataset

Real-world datasets for indoor localization

CSI-dataset

Here are the channel state information (CSI) dataset which could be utilized for indoor localization. We collect them in two real world environments:

Area One: It is a 13.5×11m2 computer laboratory with tables, chairs and obstacles, which can be considered as a NLOS scenario. And there are 317 sampling locations.

Area Two: It is a 7×10m2 meeting room and almost empty, which can be considered as a LOS scenario. And there are 176 sampling locations.

We also upload the layout of two scenarios. And the file "coordinate 715" means position coordinate is [7, 15] as well as other files.

Area Three and Four are the new collection datasat for the conference room and the miniLab, respectively.

Update

2023.11.24, I uploaded the imaginary part data of CSI in the lab and meeting room, you can find them in the corresponding folder.

Reference

If you use this work for your research, you may want to cite

@article{zhu2021bls,
  title={{BLS-Location: A Wireless Fingerprint Localization Algorithm Based on Broad Learning}},
  author={Zhu, Xiaoqiang and Qiu, Tie and Qu, Wenyu and Zhou, Xiaobo and Atiquzzaman, Mohammed and Wu, Dapeng},
  journal={IEEE Transactions on Mobile Computing},
  volume={22},
  number={1},
  pages={115--128},
  year={2023}
}

@article{zhu2022intelligent,
  title={Intelligent Fingerprint-Based Localization Scheme Using CSI Images for Internet of Things},
  author={Zhu, Xiaoqiang and Qu, Wenyu and Zhou, Xiaobo and Zhao, Laiping and Ning, Zhaolong and Qiu, Tie},
  journal={IEEE Transactions on Network Science and Engineering},
  volume={9},
  number={4},
  pages={2378--2391},
  year={2022},
  publisher={IEEE}
}