Research
My undergraduate thesis and the final projects from my master’s in Artificial Intelligence at UNI. Each one with its full report as a PDF.
Thesis
Undergraduate thesis · Systems EngineeringUniversidad Nacional José María Arguedas · 2023
Effectiveness of a Deep Learning classification model for COVID-19 detection
My thesis for the Systems Engineer degree. A modified DenseNet201 that detects COVID-19 in chest X-rays at 98% effectiveness, using 18.1M parameters and 3.2 GFLOPs.
Master’s final projects
Reinforcement LearningCycle II · 2026-1
Support-ticket routing with deep reinforcement learning: when generalization matters more than depth
Ticket dispatch framed as a Markov decision process and solved with everything from tabular Q-learning to A2C, on a simulator calibrated against 177,940 real incidents. The shallow model won.
Real-Time Embedded SystemsCycle II · 2026-1
Real-time embedded speed enforcement with computer vision
An embedded system that watches a real street in Ayacucho from an IP camera, measures the speed of every vehicle, and files an automatic infraction report when someone crosses the limit.
Deep LearningCycle II · 2026-1
RICUY: a driver-assistance system for the urban roads of Lima and Andahuaylas
A real-time driver-assistance system built to see the mototaxi, a vehicle that appears in no major computer-vision dataset. Instance segmentation, multi-object tracking and monocular distance estimation, running on a 4 GB GPU.
Big DataCycle II · 2026-1
Distributed detection of transactional anomalies in SAP Business One for mining audit
A Big Data architecture for finding financial and operational anomalies across roughly 30 GB of real ERP history from a Peruvian mining company. Project proposal.
Programming for Machine LearningCycle I · 2025-2
Data analysis through public APIs: statistical visualization and result export
Pulling SpaceX's public launch API to look for patterns in mission success, booster reuse, and how the company's operations changed shape over two decades.
Foundations of Artificial IntelligenceCycle I · 2025-2
A hybrid search agent: ant colony algorithms and Dijkstra for rescue in maze-like environments
An agent for search-and-rescue in unknown, maze-like terrain. Ant algorithms handle the exploration; once the victim is found, Dijkstra plans the route out.