Alberto Formaggio's repositories
Where-Am-I
Application developed for the University course "Embedded Systems Programming". The app retrieves the location of the device in real time and shows it to the user. Furthermore, the app shows the path of the user in the last 5 minutes.
Adapter-Pattern-Software-Engineering
Re-adaptation of the List, Map, Set, Collection classes in Java Micro Edition environment by using the Adapter pattern
Client-Server-Chat-With-RSA-Encryption
A chat application simulating a connection client-server. The messages sent from one instance of the program to the other are encrypted and decrypted by using an RSA-Based handshake protocol.
data-mining-hw
This repository contains the homeworks used for the Data Mining course (NDBI023) at Charles University. We manually implemented k-Nearest Neighbor and the Naive Bayes Classifier.
fine_tuning_classification_prediction_GNN
Empirical Research over the possible advantages of pretraining a Graph Neural Network for Classification by using Link Prediction. We used GCN, GAT and GraphSAGE with minibatch generation. Done for the Learning From Networks course taught by professor Fabio Vandin at the University of Padova
Hough-Transform-From-Scratch
This GitHub repository provides a comprehensive guide and implementation of the Hough Transform for line detection in Python using OpenCV. It covers step-by-step instructions for implementing the algorithm from scratch, including edge detection, parameter space transformation, and line extraction.
NLP-Homeworks
This folder will contain some homeworks proposed by the professor Jan Hajic at Charles University for the course Statistical Methods for Natural Language Processing I, II (NPFL067, NPFL068)
speech_recognition
This repository will contain the project used for the course Algorithms for Speech Recogntion - NPFL079 held at Charles University
vision-transformer
A simple replication of the architecture implemented by the creators of the Vision Transformer paper. The project has been developed in pytorch for learning purposes.
Voice-Activity-Detector
An algorithm for Voice Activity Detection (VAD) that determines which packets have vocal content and, hence, need to be sent, and which instead can be supressed as they are not meaningful for the communication
Assignment_1_Intelligent_Robotics
Assignment 1 of the Intelligent Robotics course held by Emanuele Menegatti at the University of Padova. In this assignment, LiDAR scans must be used to find the coordinates of circular objects inside a room, thus discarding walls
Assignment_2_Intelligent_Robotics
Assignment 2 of the Intelligent Robotics course held by Emanuele Menegatti at the University of Padova. The goal is to make Tiago move between 2 rooms and use its robotic arm to pick objects on a table and releasing them on cylindric tables
Ensemble-Of-Segmentation
Source code used in the research paper "An empirical study on ensemble of segmentation approaches"
first-contributions
🚀✨ Help beginners to contribute to open source projects
Grayscale-to-RGB
Matlab code used to convert a 16-channels gray image to RGB for training a CNN
ml-assignments
This repository will contain the assignments done for the Machine Learning taught by Fabio Vandin at the University of Padova
npfl114
Materials for the Deep Learning -- ÚFAL course NPFL114
sentiment_analysis_climate
A study of the sentiment of people regarding Climate Change using data mining techniques over Twitter data
skills-github-pages
My clone repository
stat-indep-tests
This repository explores the Chi-square and Fisher's tests. Besides a manual implementation (and comparison with the scipy library), it will also be discussed the theoretical aspects of these 2 approaches
streamlit
Trial to use streamlit for inference with my models
turtle-head-detection
An object detection approach for the identification of turtles' heads.
WeatherClassification
Image classification pipeline relying on Deep Learning models dealing with training over multiple datasets with unbalanced labels and classes. In addition, also classification using histogram data was done for better generalization over different datasets.