Matteo Mendula's repositories
FitStic_noSQL
Fitstic noSQL database course
COVID19-twitter-depression
Analysis of labeling strategies aimed at identifying depression phenomena among users’ tweets.
LSTM_Seq2Seq_TERMINET_SCHN
LSTM and BiLSTM Seq2Seq forcasting in TERMINET_SCHN project
ScaledHome_Control_System
This repository shows the architecture developed during my internship period at University of Central Florida
express-vercel
Deploy express js to vercel.
DeepStream-Yolo
NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models
EAFL
Energy-Aware Federated Learning
Energon_Prometheus_exporter
Prometheus exporter for NVIDIA Jetson monitoring
GRM
Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation
Harvest
Harvest: a novel energy monitoring middleware for Distributed Learning
jetson_stats
📊 Simple package for monitoring and control your NVIDIA Jetson [Orin, Xavier, Nano, TX] series
lstm-attention-based-stress-detection
Attention-based bidirectional LSTM for Classification Task (ICASSP)
node-express-course
An introduction to Node.js and Express.js servers
Online3DViewer
A solution to visualize and explore 3D models in your browser.
powertop
The Linux PowerTOP tool -- please post patches to the mailing list instead of using github pull requests
prova-socket-server
prova-socket-server
splittableFasterCRRNN_BQ
Bottleneck quantization for FasterRCNN object detection and encoder quantization (TRT)
TensorflowJS-face-detection
Simple example of face detection using blazeface
Timelapselab
TimelapseLab project
trustfed_NASA_data
This repository presents a blockchain-based framework, TrustFed, for Cross-Device Federated Learning systems to detect the model poisoning attacks, enable fair training settings, and maintain the participating devices' reputation. TrustFed provides fairness by detecting and removing the attackers from the training distributions. It uses blockchain smart contracts to maintain participating devices' reputations to compel the participants in bringing active and honest model contributions. We implemented the TrustFed using a python-simulated FL framework, blockchain smart contracts, and statistical outlier detection techniques.
Ubicomp2023
Ubicomp2023 experiments
Video-Call-App-NodeJS
A conference call implementation using WebRTC, Socket.io and Node.js