Domenico's Projects
development in C of a concurrent server that implements a chat, users can exchange text messages / files by connecting to the server with a client program
Implementation of personalized convolutional network and show performance results on CIFAR-10. After network is trained, try an adversarial attack to it with the simple Fast Gradient Sign method, generating one (or more) adversarial examples starting from one (or more) CIFAR-10 test images. At the end display the original image, the adversarial noise and the final adversarial example.
Assignment from the Course of Parallel and Distributed Systems
Tools for running Cpp applications on Docker with docker-compose and local volume
A java project (client-server) which use NIO MULTIPLEXING,RMI, TCP and UDP.
Collection of oral questions and exam material
Android app for remote control of an IoT system
Hidden Markov Model with Gaussian emissions of the dataset which measure the energy consumption of appliances and lights, across a period of 4.5 months. Once trained the HMMs, perform Viterbi on a reasonably sized subsequence (e.g. 1 month of data), plot the timeseries data highlighting (e.g. with different colours) the hidden state assigned to each timepoint by the Viterbi algorithm. Then,sampling a sequence of at least 100 points from the trained HMMs and show it on a plot discussing similarities and differences w.r.t. the ground truth data.
This repository contains the source code of an image recognition system using deep learning techniques, with a focus on leveraging the Keras framework in Python. The primary objective of this project is to create a robust and accurate model capable of identifying objects or patterns
IoT System with html and Arduino code for plant monitoring using ThinkSpeak platform
the project consists in designing, implementing and documenting the SecureDataContainer <E> collection. SecureDataContainer <E> is a container of type E objects. Intuitively the collection is constituted as a species Data storage for data specification and sharing (represented in the simulation from type E objects). The collection guarantees a Data Security mechanism providing its own user identity management mechanism. Furthermore, it provides a mechanism for access control that allows the data owner to perform a selective restriction access to your data included in the collection. Some users can be set by the owner to access the data, while others cannot access it without authorization.
Select an image from 4 different themes, for these images, extract the SIFT descriptors using the visual feature detector embedded in SIFT to identify the points of interest. Aggregate all the identified descriptors in a dataset and run k-means to partition the descriptors in clusters. Then analyze the obtained clusters by confronting the descriptors assigned to each cluster with the thematic classes of the images from which they were extracted (confusion matrix ).
Personal Github Profile
HLT project
implementation of an Artificial Intelligence Neural Network from scratch using Python programming language with the use of k-fold cross validation, grid search and ensamble.
formulas for the approximate calculation of integrals by numerical integration
project for the programming exam
Some code with the usage of OpenMP multi-platform shared-memory parallel programming in C/C++
web platform for IoT - AI - Industry 4.0 which is based on 4 docker containers
Richard Benson appreciation page - Symfony 5