Hello, I am
{Francisco Izquierdo}

Machine Learning & Software Engineer

I'm a 24-year-old professional based in Aveiro, specialized in AI and Back-End development. I thrive in diverse teams and love collaborating to build impactful solutions.

Take a Look at
Some of My Projects

CrowdFlow

2024 - Now

pythonpython
opencvopencv
azureazure
tensorflowtensorflow
flaskflask
dockerdocker

CrowdFlow is a data collection and analysis platform that uses AI and surveillance cameras to monitor clients movements inside commercial surfaces. I refined object detection and classification models, quantized AI models for deployment on edge devices, developed Rest API server, backend architecture and statistical processing modules. I also implemented cloud deployment and managed database integration, including connection handling and query optimization.

AIComputer VisionCrowd Analytics
Visit
Project screenshot

Hate Speech Recognition – DistilBert Fine-Tuning

2023 - 2024

pythonpython
huggingfacehuggingface
jupyterjupyter
kagglekaggle
pytorchpytorch
pandaspandas
scikit-learnscikit-learn

This project tackles the problem of hate speech and offensive language detection on social media platforms using a fine-tuned DistilBERT transformer model. The motivation stems from the growing challenge faced by online communities to moderate harmful content and ensure safe digital spaces. Manual moderation is not scalable—automated NLP tools can help identify and mitigate toxic behavior at scale.

Natural Language ProcessingHate Speech DetectionTransfer LearningText Classification
Visit
Project screenshot

oNode

2022 - 2023

javajava
linuxlinux
latexlatex

oNode is a prototype platform designed to distribute audio, video, and text content from a central content server to multiple clients. It supports various transport protocols, allowing experimentation and performance testing with different network delivery mechanisms. This setup simulates real-world multimedia distribution systems, focusing on flexibility, modularity, and protocol-level behavior.

Transport ProtocolsNetwork EngineeringClient-Server Architecture
Visit
Project screenshot

Face Fraud Detection

2022 - 2023

pythonpython
jupyterjupyter
kagglekaggle
tensorflowtensorflow
pandaspandas
scikit-learnscikit-learn
keraskeras

This project entails the development of a deep learning model utilizing advanced computer vision techniques to identify AI-generated faces. By employing robust image classification methodologies, the model is designed to effectively distinguish between authentic and synthetic facial images. This capability not only advances the accuracy and reliability of visual content analysis but also plays a crucial role in detecting manipulated media, which is increasingly important in maintaining the integrity of digital information.

Computer VisionImage ClassificationFacial RecognitionFraud Detection
Visit
Project screenshot

Development Stack

Programming Languages

Machine & Deep Learning

Data Science & Visualization

Cloud, DevOps & Infrastructure

Awards & Recognition

Startup Point logo

2nd Place

Award

Startup Point 2024

National Contest for Young Entrepreneurs logo

Capgemini Prize

Award

National Contest for Young Entrepreneurs 2024

Colégio de Albergaria Honor Student logo

Honor Student

Recognition

Colégio de Albergaria

Jobra Music Conservatory logo

Level 5 Saxophone

Recognition

Jobra Music Conservatory

Publications & White Papers

Springer Nature logo

Publication

EPIA2024 International Conference on Artificial Intelligence

Efficient Image Search and Retrieval System in Cloud Platforms

Altice Labs logo

White Paper

InnovAction Magazine

Artificial Intelligence in Efficient Image Search on MEO Cloud

Contact

Got a question, suggestion, or just want to say hi? Drop me an email atfranciaguia@hotmail.comor fill out the form — I’d love to hear from you!