Natalie Segura Velandia- Bachelor of Engineering
- head of machine learning at SiteSee
Natalie Segura Velandia
- Bachelor of Engineering
- head of machine learning at SiteSee
Lead research, develop and maintain machine learning algorithms to innovate TELCO industry
About
8
Publications
4,385
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
13
Citations
Introduction
Machine Learning and AI researcher, I want to develop tools based on software applications to help people with neuromuscular diseases. Currently, I'm working with semantic segmentation, instance segmentation and panoptic segmentation, to identify areas of interest with pixel wise accuracy.
Current institution
SiteSee
Current position
- head of machine learning
Additional affiliations
April 2018 - June 2020
SiteSee
Position
- Developer
April 2017 - February 2018
Education
July 2011 - April 2017
Publications
Publications (8)
![Figura 21 La adición del Intervalo de guarda. [43]](profile/Natalie-Segura-Velandia/publication/318281182/figure/fig7/AS:668886248734721@1536486317093/Figura-21-La-adicion-del-Intervalo-de-guarda-43_Q320.jpg)
![Figura 42 Conector serial D9 para comunicaciones RS-232. [59]](profile/Natalie-Segura-Velandia/publication/318281182/figure/fig8/AS:668886248738817@1536486317123/Figura-42-Conector-serial-D9-para-comunicaciones-RS-232-59_Q320.jpg)
![Figura 56 Diagrama esfuerzo-deformación [69]-Dureza Es la resistencia...](profile/Natalie-Segura-Velandia/publication/318281182/figure/fig3/AS:513574742052865@1499457168496/Figura-56-Diagrama-esfuerzo-deformacion-69-Dureza-Es-la-resistencia-que-ejerce-el_Q320.jpg)
This work shows the development and construction of an UGV unmanned ground vehicle, which is able to realize labors of vigilance and security inside aeronautical enviroments. Its main aim is to avoid typical threats as airplane’s sabotage, theft of aircraft's equipments or fuel, entrance of unauthorized personnel, etc. Starting by the following que...
This paper presents the development of a 3D virtual environment to validate the effectiveness of a Convolutional Neural Network (CNN) in a virtual application, controlling the movements of a manipulator or robotic arm through commands recognized by the network. The architecture of the CNN network was designed to recognize five (5) gestures by means...
This study presents a review of the computational methods implemented with the deep learning technique, highlighting the architecture of convolutional neural networks. Works that use these methods are addressed for image recognition and pattern recognition, each characterizing a specific task. With the technological and investigative momentum that...
This article presents a robotic integration system, based on machine vision and acquisition of the signals for the Human-Machine interaction in the delivery and reception of tools. By using the Microsoft Kinect v1.0 sensor, it is possible to spatially locate the manipulator using the RGB camera to which the conversion of color spaces and filters wi...
In this study it is present a review of artificial intelligence algorithms applied to robotic agents, emphasizing learning from Convolutional Neural Networks (CNN). For the construction of this review, a bibliographical research was carried out in the databases of scientific articles, research journals and technological advances where the most impo...
Abstract: This study presents the implementation of 3 convolutional neural network architectures for the recognition of hand gestures by means of electromyographic signals. The acquisition of signals is done by means of electrodes located in the forearm and the development platform specialized in biomedical signals MySignals HW V2.0 which will be a...
![Figure 4 Diagram with terrain profiles. [33]](profile/Natalie-Segura-Velandia/publication/353679430/figure/fig1/AS:1052948041854977@1628053784437/Diagram-with-terrain-profiles-33_Q320.jpg)
![Figure 5 Atmospheric Absorption. [33]](profile/Natalie-Segura-Velandia/publication/353679430/figure/fig2/AS:1052948041830401@1628053784466/Atmospheric-Absorption-33_Q320.jpg)
This work shows the development and construction of an unmanned ground vehicle
(UGV), which can realize labours of vigilance and security inside aeronautical
environments. Its main aim is to avoid typical threats as airplane’s sabotage, theft of
aircraft's equipment or fuel, the entrance of unauthorized personnel, etc. Starting with the
following q...
This work shows the development and construction of an unmanned ground vehicle
(UGV), which can realize labours of vigilance and security inside aeronautical
environments. Its main aim is to avoid typical threats as airplane’s sabotage, theft of
aircraft's equipment or fuel, the entrance of unauthorized personnel, etc. Starting with the
following q...
Questions
Questions (3)
I'm doing the reconstruction of 3d objects most of them are vertical, however, some of them are tilted I would like to know exactly how tilted they are.
I'm working on a project that has around 10 different classes, it's working fine. However, I still have a problem with a couple of classes that I don't have enough data on those ones. I would like to know if someone has been using something different that balance the weights for training those classes. and if someone knows how to apply continuous learning or has some ideas to fine-tune a model on badly performing classes, without degrading the performance of existing classes and needing to retraining on the entire data set.
I'm looking for a useful app that allow me label the data
