Difference between revisions of "Software"
WikiSheriff (talk | contribs) |
WikiSheriff (talk | contribs) |
||
| Line 12: | Line 12: | ||
https://github.com/ClaudiaAlvarezAparicio/petra | https://github.com/ClaudiaAlvarezAparicio/petra | ||
| − | |||
Latest revision as of 10:40, 5 November 2020
Here we enumerate different software packages developed by our group:
Contents
PeTra (People Tracker)
PeTra is a tool which allows detecting and tracking people. The system is based on a CNN that uses an occupancy map constructed from the readings of a LIDAR sensor.
Dataset: https://www.frontiersin.org/articles/10.3389/fnbot.2017.00072/full PeTra: https://www.frontiersin.org/articles/10.3389/fnbot.2018.00085/full https://www.mdpi.com/2218-6581/8/3/75
https://github.com/ClaudiaAlvarezAparicio/petra
BRITTANY (Biometric RecognITion Through gAit aNalYsis)
Brittany is a tool which allows a Biometric recognition through gait analysis by using LIDAR sensors. The system is based on a classification neural network which allow identify 5 diferent users of the system or intruders in it.
https://github.com/ClaudiaAlvarezAparicio/brittany
SUFFER (SimUlation Framework for Education in Robotics)
Robot as a Service (RaaS) platform for simulating robots.
More information in Innovacionfrentealvirus
Jaco gym (Reinforcement Learning for Manipulators)
Pierre has been using Gazebo for trainning
https://github.com/PierreExeter/jaco-gym
DOROTHEA (DOcker-based fRamework fOr gaTHering nEtflow trAffic)
DOROTHEA is a Docker-based solution to build packet flow datasets. It uses a NetFlow sensor which collects the streams of packets that pass through a network interface. The tool simulates a complex and realistic computer network. It is easily configurable and scalable, for instance it is possible to set the number of computers that generate network traffic. A threshold can be set to define the number of packets used to create flows, thus emulating the real functionality of routers.
More information at https://seguridad.unileon.es/index.php/DOROTHEA
MoEv (Model Evaluator)
MoEv is a general-purpose tool that allows for building classification models from labeled datasets. Besides, MoEv allows for performing data cleaning and pre-processing operations. It has been successfully used in different research areas such us jamming attacks detection on real-time location systems, academic success prediction at educational institutions, or network attacks detection.
More information at https://seguridad.unileon.es/index.php/MoEv
