There is a newer version of this record available.

Dataset Open Access

Sigfox and LoRaWAN Datasets for Fingerprint Localization in Large Urban and Rural Areas

Aernouts, Michiel; Berkvens, Rafael; Van Vlaenderen, Koen; Weyn, Maarten


Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Aernouts, Michiel</dc:creator>
  <dc:creator>Berkvens, Rafael</dc:creator>
  <dc:creator>Van Vlaenderen, Koen</dc:creator>
  <dc:creator>Weyn, Maarten</dc:creator>
  <dc:date>2019-07-19</dc:date>
  <dc:description>INTRODUCTION

The goal of these LPWAN datasets is to provide the global research community with a benchmark tool to evaluate fingerprint localization algorithms in large outdoor environments with various properties. An identical collection methodology was used for all datasets: during a period of three months, numerous devices containing a GPS receiver periodically obtained new location data, which was sent to a local data server via a Sigfox or LoRaWAN message. Together with network information such as the receiving time of the message, base station IDs' of all receiving base stations and the Received Signal Strength Indicator (RSSI) per base station, this location data was stored in one of the three LPWAN datasets: 


	
	lorawan_dataset_antwerp.csv
	
	
	130 430 LoRaWAN messages, obtained in the city center of Antwerp
	
	
	sigfox_dataset_antwerp.csv
	
	
	14 378 Sigfox messages, obtained in the city center of Antwerp
	
	
	sigfox_dataset_rural.csv
	
	
	25 638 Sigfox messages, obtained in a rural area between Antwerp and Ghent
	


As the rural and urban Sigfox datasets were recorded in adjacent areas, many base stations that are located at the border of these areas can be found in both datasets. However, they do not necessarily share the same identifier: e.g. ‘BS 1’ in the urban Sigfox dataset could be the same base station as ‘BS 36’ in the rural Sigfox dataset. If the user intends to combine both Sigfox datasets, the mapping of the ID's of these base stations can be found in the file:


	
	sigfox_bs_mapping.csv
	


The collection methodology of the datasets, and the first results of a basic fingerprinting implementation are documented in the following journal paper:
 http://www.mdpi.com/2306-5729/3/2/13

UPDATES IN VERSION 1.2

In this version of the LPWAN dataset, only the LoRaWAN set has been updated. The Sigfox datasets remain identical to version 1.0 and 1.1. The main updates in the LoRaWAN set are the following:


	
	New data: the LoRaWAN messages in the new set are collected 1 year after the previous dataset version. To be consistent with the previous versions, the new LoRaWAN set is uploaded in the same .CSV format as before. This upload can still be found in this repository as ‘lorawan_dataset_antwerp.csv’.
	
	
	More gateways:  Compared to the previous dataset, 4 gateways were added to the LoRaWAN network. The RSSI of these gateways are shown in columns ‘BS 69’, ‘BS 70’,‘BS 71’ and ‘BS 72’. All other ‘BS’ columns are in the same order as in previous dataset versions.
	
	
	More metadata: In the previous LoRaWAN dataset, metadata was limited to 3 receiving gateways per message. In the new dataset version, metadata from all receiving gateways is included in every message. Moreover, some gateways provide a timestamp with nanosecond precision, which can be used to evaluate Time Difference of Arrival localization methods with LoRaWAN.
	
	
	2 file formats: As more metadata becomes available, we find it important to share the dataset in a clearer overview.  This also allows researchers to evaluate the performance of LoRaWAN in an urban environment. Therefore, we publish the new LoRaWAN dataset as a .CSV file as described above, but also as a .JSON file (lorawan_antwerp_2019_dataset.json.txt, the .txt file type had to be appended, otherwise the file could not be uploaded to Zenodo) An example of one message in this JSON format can be seen below:

	
		
		JSON format description:

		
			
			HDOP: Horizontal Dilution of Precision
			
			
			dev_addr: LoRaWAN device address
			
			
			dev_eui: LoRaWAN device EUI
			
			
			sf: Spreading factor
			
			
			channel: TX channel (EU region)
			
			
			payload: application payload
			
			
			adr: Adaptive Data Rate (1 = enabled, 0= disabled)
			
			
			counter: device uplink message counter
			
			
			latitude: Groundtruth TX location latitude
			
			
			longitude: Groundtruth TX location longitude
			
			
			airtime: signal airtime (seconds)
			
			
			gateways:

			
				
				rssi: Received Signal Strength
				
				
				esp: Estimated Signal Power
				
				
				snr: Signal-to-Noise Ratio
				
				
				ts_type: Timestamp type. If this says "GPS_RADIO", a nanosecond precise timestamp is available
				
				
				time: time of arrival at the gateway
				
				
				id: gateway ID
				
			
			
		
		
		
		JSON example

		{
  "hdop": 0.7,
  "dev_addr": "07000EFE",
  "payload": "008d000392d54c4284d18c403333333f04682aa9410500e8fd4106cabdbc420f00db0d470ce32ac93f0d582be93f0bfa3f8d3f",
  "adr": 1,
  "latitude": 51.20856475830078,
  "counter": 31952,
  "longitude": 4.400575637817383,
  "airtime": 0.112896,
  "gateways": [
    {
      "rssi": -115,
      "esp": -115.832695,
      "snr": 6.75,
      "rx_time": {
        "ts_type": "None",
        "time": "2019-01-04T08:59:53.079+01:00"
      },
      "id": "08060716"
    },
    {
      "rssi": -116,
      "esp": -125.51497,
      "snr": -9.0,
      "rx_time": {
        "ts_type": "GPS_RADIO",
        "time": "2019-01-04T08:59:53.962029179+01:00"
      },
      "id": "FF0178DF"
    }
  ],
  "dev_eui": "3432333853376B18",
  "sf": 7,
  "channel": 8
}

		 
		
	
	


 </dc:description>
  <dc:identifier>https://zenodo.org/record/3342253</dc:identifier>
  <dc:identifier>10.5281/zenodo.3342253</dc:identifier>
  <dc:identifier>oai:zenodo.org:3342253</dc:identifier>
  <dc:language>eng</dc:language>
  <dc:relation>doi:10.5281/zenodo.1193562</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>https://creativecommons.org/licenses/by/4.0/legalcode</dc:rights>
  <dc:subject>Internet of Things</dc:subject>
  <dc:subject>LPWAN</dc:subject>
  <dc:subject>Sigfox</dc:subject>
  <dc:subject>LoRaWAN</dc:subject>
  <dc:subject>Localization</dc:subject>
  <dc:subject>Fingerprinting</dc:subject>
  <dc:title>Sigfox and LoRaWAN Datasets for Fingerprint Localization in Large Urban and Rural Areas</dc:title>
  <dc:type>info:eu-repo/semantics/other</dc:type>
  <dc:type>dataset</dc:type>
</oai_dc:dc>
1,657
1,203
views
downloads
All versions This version
Views 1,657728
Downloads 1,203280
Data volume 52.0 GB13.3 GB
Unique views 1,332647
Unique downloads 649138

Share

Cite as