Ghiordy Ferney Contreras Contreras

ORCID: 0000-0002-8945-2737
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Sensor Technology and Measurement Systems
  • Particle Detector Development and Performance
  • Autonomous Vehicle Technology and Safety
  • Photoacoustic and Ultrasonic Imaging
  • Image Retrieval and Classification Techniques
  • Business, Innovation, and Economy
  • Anomaly Detection Techniques and Applications
  • Advanced Clustering Algorithms Research
  • Arduino and IoT Applications
  • Multidisciplinary Science and Engineering Research
  • IoT-based Smart Home Systems
  • Sparse and Compressive Sensing Techniques
  • Greenhouse Technology and Climate Control
  • Data Management and Algorithms
  • Optical Imaging and Spectroscopy Techniques
  • High-Energy Particle Collisions Research
  • Particle physics theoretical and experimental studies
  • Artificial Intelligence in Healthcare
  • Knowledge Societies in the 21st Century

Instituto Politécnico Nacional
2010-2022

Center for Research and Advanced Studies of the National Polytechnic Institute
2022

Industrial University of Santander
2021

Francisco de Paula Santander University
2019

This work shows a novel application based on techniques of Computer Vision and Machine Learning to identify k clusters into data set with overlapping issue. Used in area unsupervised clustering, where separation between groups is tricky. Through pair-to-pair distance calculations upon original data, gotten Distances Matrix as representative information data. matrix contains visual information, then using morphological operators extract relevant features for individual identification set....

10.1109/stsiva.2019.8730239 article EN 2019-04-01

Abstract This work takes thermodynamic modelling through computer science for incubation process at domestic birds, that has presented energy consumption significantly high than used in processes. Thus, a data analysis was applied upon variables of temperature and relative humidity heating zones, trying to know how much supplied by source used, as well as, voltage current are measured the same moment acquired. Then, done using artificial neural networks models with samples obtained from...

10.1088/1742-6596/1386/1/012070 article EN Journal of Physics Conference Series 2019-11-01

Objetivo: Presentar un método de aprendizaje profundo denominado Denoising Unet for Medical Image, DUnet-MI, enfocado en la corrección diferentes niveles ruido imágenes médicas las modalidades Rayos X, Tomografía Computarizada y Resonancia Magnética. Metodología: Se aborda una solución para reducir Gaussiano sal pimienta, que se suele agregar a imagen médica por el proceso obtención, transmisión y/o recepción. DUnet-MI es adaptación del modelo con variaciones capas, filtros e hiperparámetros...

10.17081/invinno.12.2.6786 article ES cc-by Investigación e Innovación en Ingenierías 2024-07-22

Contexto: Hoy en día, el uso de grandes cantidades datos adquiridos desde diversos dispositivos y equipos electrónicos, ópticos u otra tecnología medición, generan un problema análisis momento extraer la información interés las muestras adquiridas. En ellos, agrupar correctamente los es necesario para obtener relevante precisa evidenciar fenómeno físico que se desea abordar. Metodología: El trabajo presenta evolución una metodología cinco etapas desarrollo técnica agrupamiento datos, a...

10.14483/22487638.17246 article ES cc-by-sa Tecnura 2022-04-01

The purpose of this research work is to develop a system correct the noise present in images, using computer vision and automatic learning tools, specifically, focused on processing images used by assisted driving systems, which presence represents loss information, directly affecting efficiency such systems.To achieve above, methodological process analysis, design, evaluation was followed, thus obtaining neural network model capable responding proposed task, verified performing tests...

10.1109/ica-acca56767.2022.10006275 article EN 2022 IEEE International Conference on Automation/XXV Congress of the Chilean Association of Automatic Control (ICA-ACCA) 2022-10-24

Spectral imaging offers useful additional information to improve or expand applications such as biomedical images, identification of cultures, and surveillance. These take advantage features involved in a spectral scene captured using, for instance, the Coded Aperture Snapshot Imagers (CASSI), that naturally embodies compressing sensing principles, whose potential is diminished because practice, matrix loses ideal characteristics. This paper uses deep learning based method order correct...

10.1109/stsiva53688.2021.9592024 article EN 2021-09-15
Coming Soon ...