Skip to content
View Luismpso's full-sized avatar
🦖
🦖
  • Universidade do Minho
  • Braga
  • Instagram luismpso

Highlights

  • Pro

Block or report Luismpso

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Luismpso/README.md

header banner

Typing SVG

LinkedIn Kaggle Email Based in Portugal profile views


👨‍💻 About me

  • 🎓 Master's in Artificial Intelligence @ Universidade do Minho · (2025 – present)
  • 📡 Incoming Machine Learning Intern @ NOS · (Summer 2026) — geospatial mobile network intelligence
  • 📐 B.Sc. in Engineering Physics, Universidade do Minho — final grade 17/20 (ECTS A)
  • 🧭 Focused on high-level system architecture — designing, orchestrating and validating robust, scalable ML & GenAI pipelines over raw development
  • 🌍 Languages: Portuguese (native) · English (B1)
  • 📫 Reach me at Luimpsoo@gmail.com

🏆 Featured academic work

Project What makes it interesting Stack
🥇 AI-Generated Text Detection 1st place in all 3 submissions (out of 25 teams) — multi-class classifier for Google / Mistral / Meta / OpenAI text · Grade 19/20 Deep Learning PyTorch
🏛️ SmartStudyRoom — Multi-Agent System Distributed library management with SPADE/XMPP, FIPA-ACL & Contract Net negotiation, real-time dashboard · Grade 20/20 Multi-Agent Systems Python
📖 Study-Room Occupancy & Comfort Monitoring Low-cost distributed IoT system — 2× ESP32 nodes, YOLOv11 occupancy detection, web dashboard & Android app · Grade 19/20 ESP32 YOLOv11 IoT
🏎️ Autonomous FS Racing Agent RL agent (SAC/PPO) in a 2D simulator with FS-AI rules, procedural tracks & domain randomization Reinforcement Learning
🎯 Reinforcement Learning Portfolio 5 environments · 20+ algorithms (DP, MC, TD, SARSA, Q-Learning, REINFORCE, MCTS, DQN, AlphaZero) · 71 pytest tests Gymnasium PyTorch
🩻 ERCP Medical Image Classification Multi-class deep learning with equipment-bias removal via SAM3 and model ensembles Deep Learning PyTorch
🏅 Porto Traffic Flow Prediction 4th / 57 teams in a university Kaggle competition — full CRISP-DM pipeline · Grade 18.2/20 scikit-learn Pandas
🤖 FS Rules AI Assistant 100% offline RAG agent for Formula Student regulations, with accurate cited sources · Grade 18/20 Ollama Gemma 3 12B Flask
🗺️ Multimodal Route Optimization (Porto) Bi-criterion shortest path (time + CO₂) over a complex transport graph · Grade 18/20 Nature-Inspired Computing
🏢 Tech Retail Decision Support System Star-constellation Data Warehouse (PostgreSQL, CSV, MongoDB) with NLP sentiment analysis & Metabase dashboards PostgreSQL MongoDB NLP
🛢️ D3.js Data Stories Interactive visual narratives on energy transition (SVDC2) and the 2026 Hormuz crisis D3.js JavaScript
🎮 Millionaire — Prolog Edition Logic-driven game engine + GenAI "Phone a Friend" lifeline · Grade 17/20 Prolog LLM

💼 Experience

🐦 EMG Signal Acquisition Intern — BirdLab · Jun 2023 – Aug 2023

  • Built a real-time EMG acquisition & transmission pipeline on Arduino + STM32
  • Designed a 12th-order Butterworth band-pass filter (20–450 Hz) in C++ at a 1200 Hz sampling rate
  • Cut UART payload size by 75% with a custom float→16-bit encoding (stable 249,600 bps)

🎓 Event Logistics Lead — NEFUM (Physics Students' Union, U. Minho) · Jul 2022 – Jul 2024

  • Directed logistics for 2 major academic events (~120 attendees each)
  • Planned and ran lectures & workshops for Physics / Engineering Physics students

🛠️ Tech stack

Focus

AI & Machine Learning

Data Science & Analysis

Programming Languages

Web, DBs & DevOps

Hardware & Signals


📊 GitHub activity

GitHub stats GitHub streak

Top languages

Activity graph

Trophies


footer

Pinned Loading

  1. AP1 AP1 Public

    🤖 Multi-class detection of AI-generated vs. human text in English, covering Google, Mistral, Meta, and OpenAI models.

    Jupyter Notebook 3

  2. AP2 AP2 Public

    🩻 Deep Learning models for multi-class ERCP classification featuring equipment bias removal via SAM3 and ensembles.

    Jupyter Notebook 1

  3. pedroreis2468/IIA pedroreis2468/IIA Public

    🏎️ AI Assistant for Formula Student Rules using RAG and Local LLMs.

    HTML 2

  4. pedroreis2468/ASM pedroreis2468/ASM Public

    🏛️ Distributed multi-agent system for smart university library management using SPADE/XMPP, FIPA-ACL protocols, and Contract Net negotiation, with real-time dashboard.

    Python 2

  5. pedroreis2468/AR2 pedroreis2468/AR2 Public

    🏎️ Autonomous Formula Student racing agent using Reinforcement Learning (SAC/PPO) in a 2D simulator with FS-AI rules, procedural tracks, and domain randomization.

    Jupyter Notebook 1

  6. GuilhermeLobo225/DAA GuilhermeLobo225/DAA Public

    🚦 Road Traffic Flow Prediction in Porto using Machine Learning.

    Jupyter Notebook 3