| 29-03-2023 |
Algoritmos predictivos en la estimación de vida útil de infraestructura horizontal
Estudio de tesis de magíster requiere contar con un catastro actualizado del estado de los pavimentos de veredas en el sector del caso de estudio. Esto, identificando el tipo de pavimento (baldosa, hormigón, adoquines, adocretos, etc.), estado (bueno, regular, malo), superficie de pavimentos dañadas (m2), identificación del origen de daño (vida útil, raíces de árboles, accesos vehiculares, paso de vehículos por lugares no autorizados, etc.). También problemas en soleras (de hormigón o de piedra), tapas de cámaras, sumideros, alcorques de árboles, canaletas con rejillas para evacuación de aguas lluvias en veredas continuas, etc.). Esta IPRE servirá para identificar los sectores afectados, analizar mediante la aplicación de algoritmos de Inteligencia Artificial los tipos de daños capturados para así poder generar una predicción acerca de la vida útil de los pavimentos de vereda, para finalmente generar un background para la toma efectiva de decisiones de intervención.
Prerequisitos:
no tiene.
Tiene un método de evaluación Nota 1-7, con 10 créditos y tiene 1/1 vacantes disponibles |
Mentor(es): Ver en la plataforma |
| 19-12-2022 |
Motor de extracción de información desde documentos
Actualmente, nuestro grupo de investigación está en el desarrollo e implementación de un motor de extracción de información desde documentos no-estructurados, llamado REmatch (ver una demo acá http://www.rematch.cl). Esta investigación consta en el trabajo de implementación en REmatch. Esta investigación puede ser tanto en las componentes de software del sistema como también en la implementación interna del sistema.
Prerequisitos:
no tiene.
Tiene un método de evaluación Nota 1-7, con 10 créditos y tiene 2/4 vacantes disponibles |
Mentor(es): Ver en la plataforma |
| 17-10-2023 |
Numerical methods for ultrasound in biomedical engineering
Focused ultrasound can be used in a clinical context to non-invasively treat different types of cancer. The idea is to guide acoustic energy to a focal region in the human body and generate an ablation process. The challenge is to focus the energy in the tumor without overheating healthy tissue, organs, or bone. This project is part of a research line that designs numerical methods to simulate the propagation of acoustic waves in the human body. This requires the design of efficient algorithms and programming fast algorithms in Python.
Prerequisites:
None.
Evaluation method: Nota 1-7, with 0/2 available vacants |
Mentor(s): Open in the plataform |
| 29-03-2023 |
Prerequisites:
None.
Evaluation method: Nota 1-7, with 1/1 available vacants |
Mentor(s): Open in the plataform |
| 19-12-2022 |
Prerequisites:
None.
Evaluation method: Nota 1-7, with 2/4 available vacants |
Mentor(s): Open in the plataform |
| 19-12-2022 |
Prerequisites:
None.
Evaluation method: Nota 1-7, with 0/4 available vacants |
Mentor(s): Open in the plataform |
| 07-12-2022 |
Prerequisites:
None.
Evaluation method: Nota 1-7, with 0/1 available vacants |
Mentor(s): Open in the plataform |
| 06-01-2022 |
Liquid Democracy: Modelling, Analysis, and Computational Implementation
Liquid democracy is a new paradigm of democratic decision-making, based on the idea that voters can delegate their votes transitively to people they consider most qualified for the particular election that is being held. The study of liquid democracy from an algorithmic and computational point of view, which is a branch of the area of "computational social choice", has recently started through a couple of very influential articles; for example, https://ojs.aaai.org/index.php/AAAI/article/view/11468. Despite how interesting these works are, we believe that they have not yet managed to capture all the complexities that these types of dynamics have in reality. The idea is to develop extensions of this model that better fit the requirements of current political science, and from that to analyze its mathematical and computational properties. The work will be interdisciplinary with components of mathematics, computing, and political science.
Prerequisites:
IIC1253
Evaluation method: Nota 1-7, with 0/1 available vacants |
Mentor(s): Open in the plataform |
| 21-01-2021 |
Reasoning over knowledge graphs using vector embeddings
Knowledge graphs are one of the hottest topics in artificial intelligence today as they allow increasing the reasoning capabilities of neural networks. Extracting information from these graphs is complex, but this year new techniques have been presented to do it efficiently through machine learning techniques using vector embeddings. We want to study algorithmically robust and optimal ways to carry out this process based on the state of the art of data structures and algorithms.
Prerequisites:
IIC2133
Evaluation method: Nota 1-7, with 0/1 available vacants |
Mentor(s): Open in the plataform |