Difference between revisions of "Datasets"

From robotica.unileon.es
Jump to: navigation, search
Line 3: Line 3:
 
__FORCETOC__
 
__FORCETOC__
  
[[File:Logo_feder.png|thumb|x60px]][[File:MICINN_Gob_Web_AEI.jpg|thumb|x60px]]
+
[[File:Logo_feder.png|thumb|200px]][[File:MICINN_Gob_Web_AEI.jpg|thumb|200px]]
  
 
== Available datasets ==
 
== Available datasets ==

Revision as of 09:38, 9 March 2022

This site summarizes different datasets gathered by the Robotics Group during their researches.


Logo feder.png
MICINN Gob Web AEI.jpg

Available datasets

Currently the following datasets are available:

(RRID:SCR_015756) Benchmark dataset for analysis of cyber-attacks to an indoor real time localization system for autonomous robots

This dataset can be used to analyze cyber-attacks to an indoor real time localization system for autonomous robots. Data have been gathered in an indoor mock-up apartmentlocated at the Robotics Lab of the University of León (Spain). An autonomous robot, called Karen, with an on-board Real Time Location System (RTLS) was used to gather the data.

Go to dataset

(RRID:SCR_015757) Benchmark dataset for training/testing of Machine Learning Models to detect cyber-attacks to an indoor real time localization system for autonomous robots

This dataset can be used to train and test Machine Learning Models to detect cyber-attacks to an indoor real time localization system for autonomous robots. Data have been gathered in an indoor mock-up apartmentlocated at the Robotics Lab of the University of León (Spain). An autonomous robot, called Orbi-One, with an on-board Real Time Location System (RTLS) was used to gather the data.

Go to dataset

(RRID:SCR_015743) Benchmark dataset for evaluation of range-based people tracker classifiers in mobile robots

This dataset can be used to evaluate the performance of different approaches for detecting and tracking people by using lidar sensors. Information contained at the dataset is specially suitable to be used as training data for neural network-based classifiers.

Go to dataset

NetFlow data for fitting malicious traffic detection models

We have gathered 2 datasets for malicious traffic detection, specifically port-scanning attacks. Both D1 and D2, contain approximately 50% benign flow data and 50% malicious flow data. Benign flow data, corresponding to legitimate network traffic, has been labeled as `0'. Malicious flow data, corresponding to port-scanning attacks, has been labeled as `1'. Both datasets are freely available online under an open-access license.

D1, doi:10.5281/zenodo.4106730

D2, doi:10.5281/zenodo.4106738

Acknowledgement

This material is based upon work supported by the "Proyecto RTI2018-100683-B-I00, financiado por: FEDER/Ministerio de Ciencia e Innovación – Agencia Estatal de Investigación"

Logo feder.png MICINN Gob Web AEI.jpg