Animal Crossing WiFi CSI

<p>This dataset is shared as part of the paper&nbsp;<em>Detection and classification of animal crossings on roads using IoT based WiFi sensing</em>, submitted to the IEEE LATINCOM 2023 conference. It is distributed under the Creative Commons license Attribution-NonCommercial-ShareAlike 4.0 International&nbsp;(CC BY-NC-SA 4.0).</p> <p>An expanded version of this dataset is available at <a href="https://ieee-dataport.org/documents/channel-state-information-data-animal-crossings-rural-roads" target="_blank" rel="noopener">IEEE Dataport</a>.</p> <h2>General description</h2> <p>Each sample from the dataset contains 500 frames of WiFi Channel State Information data, captured during a 5-second window (100 Hz sampling rate). Each frame contains the amplitude information from the 52 Wi-Fi subcarriers that transmit a data. This amounts to 26,000 features per sample.</p> <p>The non-zero amplitude values are converted to decibels, while null values are set to zero after the decibel function application to prevent negative infinite values. Subsequently, a running mean filter is applied to each frame to mitigate noise and outlier interference, ensuring a more stable representation of the signal.&nbsp; Additionally, we disregard zero-valued amplitudes, as these result from errors in the original signal capture process, leading to subcarriers without meaningful amplitude. Thus, zero values are not included in the running mean computation.</p> <p>We collected the CSI data using ESP32 boards, which were placed at a height of 70 cm and 12 meters apart from each other. To avoid bias towards a single environment, we collected data in four different locations, including paved and unpaved rural roads, a pasture and a gravel road.&nbsp;</p> <p>The parquet files can be easily read and manipulated with python libraries such as pandas.</p> <p>&nbsp;</p> <h2>Data labels</h2> <p>As it is intended to allow replication of the work presented, we uploaded the same separated test and training datasets used for the machine learning model. The data labels represent the following classes:</p> <p>0 - Background noise</p> <p>1 - Person</p> <p>2 - Car</p> <p>3 - Dog</p> <p>4 - Cow</p>