Data Science Tech Lead @Turing
Systems Engineer @ UFMG
-
The mutation repository: projects implemented on the Evolutionary Computing course using Jupyter Notebooks and Python. Genetic Algorithms (GA) are applied to solve The N-queens problem, the Knapsack problem, and the Weasel Program. Application of Differential Evolution (DE) and Participle Optimization Swarm (PSO) methods to optimize non-convex multimodal functions.
-
Dynamic Systems Modeling: using parametric and non-parametric methods for modeling the transfer function on a linear dynamic system. Undergrad projects for the Dynamic Systems Modeling at UFMG.
-
Choosing the best way: finding the best solution for 250 instances of a multi-objective Sales Man Problem (TSP) using Simulated Annealing (SA) neighborhood structures. The problem solutions were analyzed and selected using decision theory methods: Analytic Hierarchy Process (AHP), ELECTRE I, and PROMETHEE II. Undergrad project for the Decision Theory course.
-
Optimizing drunkness and bar bills: the Knapsack problem was applied to safely optimize the money spent and the Blood Alcohol Concentration (BAC). Undergrad project for Operation Research course.
-
AceleraDev Data Science: Career Acceleration Program in Data Science by former Codenation, now known as Trybe.
-
Pika Pika! Pikachu! (but in augmented reality): rendering a 3D Pikachu on an augmented reality marker. Coded step-by-step in Jupyter notebook using Python, OpenCV, and OpenGL.
-
Finding stars: Pattern recognition course final project, predicting Pulsar Stars using SMOTE for data balancing, and SVM for classification.
-
Image compression: Python notebook implementing an algorithm for image compression and decompression using frequency analysis and Huffman coding.
-
Data Structures and Algorithms: computer science fundamentals. Graphs, external sorting, programming paradigms, etc., implementations in C.