Senior Front-End Developer
Front-End Software Engineer
This project aims, through machine learning techniques, at creation a model for road traffic accidents classifications. Dataset contains information on accidents across Leeds. Data includes location, number of people and vehicles involved, road surface, weather conditions and severity of any casualties.
Dataset source: https://data.gov.uk/dataset/road-traffic-accidents
This project aims, through machine learning techniques, at creation a model for image classifications, dowloaded by Flickr API. There have been several types of classifications, on a dataset containing images of category “bird” and “mammal”. The purpose is to train a model which classifies images as “animal-volatile” or “non-volatile”.
The different classifiers are compared with corresponding values of “accuracy_score” that measure the efficiency. In particular have been implemented and compared the following classifiers: 1-nn, 3-nn, 5-nn, Logistic Regression (one-vs-rest), Logistic Regression (multinomial), Gaussian and Multinomial Naive Bayes.
A Hybrid Recommendation System for car sales, developed using R-language and a graph-based database (Neo4J), which combines content-based and collaborative filtering approaches. Cross-validation technique (k-fold Cross-validation) was used to validate created model.
The current view of the big data have been enormously changed due to management of big quantities of data, moreover an efficient analysis of them is a difficult task. For these reasons our project, using distributed computing techniques same as MapReduce and MPI, to analyze social networks contents, searching inside keywords (hashtag) summarizing and highlighting, in a geographic map, places where these keywords are most used. This tool is a social network contents analyzer that predict and intuitively understand mobility phenomena, natural disasters, social events, social trends and opinions, thanks to a geographic representation of this contents.
