10.21227/ARTT-CX44
Yi Zhang
Yi
Zhang
The University of Texas at Austin
Akash Doshi
Akash
Doshi
The University of Texas at Austin
Rob Liston
Rob
Liston
Cisco Systems Inc.
Wai-tian Tan
Wai-tian
Tan
Cisco Systems Inc.
Xiaoqing Zhu
Xiaoqing
Zhu
Cisco Systems Inc.
Jeffrey Andrews
Jeffrey
Andrews
The University of Texas at Austin
Robert Heath
Robert
Heath
The University of Texas at Austin
DeepWiPHY: Synthetic and real-world IEEE 802.11ax OFDM symbol dataset
IEEE DataPort
2020
Artificial Intelligence
Machine Learning
Communications
Digital signal processing
IEEE 802.11 ax; channel estimation; synthetic data; real-world data
2020-04-11
Open Access Dataset
Creative Commons Attribution
This dataset is associated with the paper entitled "DeepWiPHY: Deep Learning-Based IEEE 802.11ax Receiver". It has synthetic and real-word IEEE 802.11ax OFDM symbols. The synthetic dataset has around 110 million OFDM symbols and the real-world dataset has more than 14 million OFDM symbols. Our comprehensive synthetic dataset has specifically considered typical indoor channel models and RF impairments. The real-world dataset was collected under a wide range of signal-to-noise ratio (SNR) levels and at various locations in a large office. To create this real-world dataset, we built a passive sniffing-based data collection testbed with a commercial AP, a Samsung mobile phone and two USRPs.