class Matteo:
  def __init__(self): 
    self.name = 'Matteo'
    self.surname = 'Merlo'
    self.education = ['Politecnico di Torino']
    self.experience = ['Icarus Polito Team', 'Links Foundation']
    self.achievements = ['Best Paper Award at ECML PKDD 2023']
    self.interests = ['Space Exploration', 'Climate change', 'Automotive', 'Computer Vision', 'Finance']
    self.hobbies = ['Chess', 'Reading scientific papers', 'Gym', 'Hiking']- π₯ Multitask Semantic Segmentation from satellite imagery for burned area and severity estimation: A Multitask Learning in Semantic Segmentation approach is employed for targeting both wildfire delineation and burn severity estimation.
- π°οΈ CEMS Wildfire Dataset: A large dataset (500+ images) of past wildfire from Copernicus EMS using Sentinel-2 images.
- π© Skymap path planner: UAV flight route planner though the clouds using pathfinding algorithm.
- π€οΈ Path finding in a Weighted Environment: Try and testing different pathfinding algorithms in weighted environments.
- π Real-Time Domain Adaptation in Semantic Segmentation: A class-based styling approach for Real-Time Domain Adaptation in Semantic Segmentation applied within the realm of autonomous driving solutions.
- π Smart Home Vigilance System: an indoor vigilance system that is capable of recognizing the presence of a human intrusion through video-audio recordings.
- π³ Default of Credit Card Clients Dataset Analisys: in depth mathematical analysis of Random Forest, SVM and Logistic Regression;
- π₯ Twitter-Sentiment-Analisys: Sentiment analysis of a dataset of tweets through machine learning techniques.
- π Simulation Epidemics on Graphs: SIR simulation of the evolution with the parameter of 2009 pandemic in Sweden with the goal of learning the network structure characteristics and disease-dynamics.
- π Machine Learning for IOT: Homeworks from the course "Machine Learning for IOT", multi-step forecasting and Edge-Cloud Collaborative Inference.
- π Network dynamics and learning homework: Homeworks from the course "Network Dynamics and Learning", averaging dynamics through network and epidemic simulation model.
- π Distributed architectures for big data processing and analytics: Homeworks from the course "Distributed architectures for big data processing and analytics", pyspark and hadoop exercises.
- π Datascience Lab: process and methods: Laboratories from the course "Datascience Lab: process and methods";
|  |  | 


