Michele De Filippo's repositories
mcda-nn
The approach involves the usage of Multi-Criteria Decision Analyses, including Weighted Sum Model (WSM), Weighted Product Model (WPM) and Topsis to produce ranking of decisions on incomplete structured datasets. Subsequently, Multi-variate Regression, Deep Neural Network (DNN) and a Multi-layer Perceptron (MLP) are trained to predict such rankings.
ml-fitbit
A thorough analysis of opensource Fitbit data is performed. The key findings are highlighted and discussed. The analysis provided herein is performed using 940 data points collected from 33 distinct users. Machine Learning Models are used to solve a regression problem using Multiple Linear Regression, Random Forest and Extreme Gradient Booster
time-series-forecast-sarimax-prophet
This repo introduces a simple script for time series forecast based on SARIMAX and Facebook Prophet Models applied onto some energy dataset
plate-bending
Bending of multi cross-section thin/thick plate under composite transverse pressures and boundary conditions modeled using Finite Element Method
breast-cancer-classifier
Keras classifier for breast cancer data
FinBERT
A Pretrained BERT Model for Financial Communications. https://arxiv.org/abs/2006.08097
googlemaps-scraper
Google Maps reviews scraping
open-images-parser
Download bounding boxes and segmentation annotations from Google's Open Images dataset and parse them into a simple csv format
recommenders
Best Practices on Recommendation Systems
TF2DeepFloorplan
A Tensorflow2 implementation of Deep Floor Plan Recognition using a Multi-task Network with Room-boundary-Guided Attention paper
WorldModels
An implementation of the ideas from this paper https://arxiv.org/pdf/1803.10122.pdf
xiaohongshu-2
利用Appium实现抓取小红书App