Giter Club home page Giter Club logo

Dario Della Mura's Projects

advanced-machine-learning-image-classification-models icon advanced-machine-learning-image-classification-models

Object Classification is one of the most significant tasks whose development is constantly growing in the field of deep learning research. The objective of this study is the development of neural architectures for the classification of images (of fruits and vegetables) contained within the Fruits-360 dataset. The methodological approach adopted to face the task in question has been the development of three models of convolutional neural networks obtained by applying three different techniques typical of deep learning: development of a convolutional neural network ex novo, Use of a pre-computed convolutional neural network using the transfer learning technique and use of a pre-defined convolutional neural network as a feature extraction tool.

classification-of-musical-genres-and-music-retrieval icon classification-of-musical-genres-and-music-retrieval

During the project for the DIGITAL SIGNAL IMAGE MANAGEMENT course I learned how to manage and process audio and image files. The aim of the project was the classification, through machine learning and deep learning models, of musical genres by extracting specific audio features from the "gtzan dataset" dataset files with which to train the models (SVM, Linear Regression, Decision tree , Random Forest, Neural Network). Mel spectograms were also extracted to train convolutional neural network models. In addition, the extracted audio features have been used to develop a model of music retrieval which given an audio track in input produces as output 5 audio tracks recommended meiante the use of cousine similarity.

covid-analysis---italy icon covid-analysis---italy

Covid Analysis in Italy: During the Data mangagement and visualization project, I learned to: collect data autonomously from multiple heterogeneous sources and store them (often in streaming) on appropriate databases (such as MongoDB and SQL); scrape online iterative graphs; perform statistical and graphic analysis of the collected data Link table with visualizations: https://public.tableau.com/views/ProgettoDMV_CovidHistory/Storia1?:language=it-IT&publish=yes&:display_count=n&:origin=viz_share_link

foundation-of-computer-science icon foundation-of-computer-science

Thanks to this university project I acquired the skills in python and SQL, specifically a deep knowledge: in the use of numpy libraries, pandas for the correct management, cleaning and analysis of datasets consisting of some interconnected tables, such as those usually available on Kaggle.com (CSV, TSV, JSON formats); in the design of a relational database according to the principles of standard normalization and deduction of the implicit structure of a database from its tables.

nlg-the-impact-of-data-quality-on-automatic-text-generation-from-rdf-data icon nlg-the-impact-of-data-quality-on-automatic-text-generation-from-rdf-data

The work presented was developed during the internship, as researchers in the field of Natural Language Generation, at the Insid&s Lab laboratory in Milan-Bicocca. The work carried out deals with the creation of a framework for the correct assessment of the impact of the quality of the input datasets on the quality of the text generated by the NLG models, specifically: Creation of the "Concept-Based" and "Entity-Based" versions of the WebNLG dataset; Evaluation of the quality of the datasets created; Training of LSTM and Transformer models using the OpenNMT tool; Natural language text generation by LSTM and Transformer models; Evaluation of the quality of the text generated by the NLG models; Final analysis.

prediction-of-high-cost-patients icon prediction-of-high-cost-patients

Predicting the likely future healthcare costs of individuals across different social groups is an important and stimulating computing challenge. To address the problem of controlling healthcare costs, we retrieved data from the MEPS dataset, which contains general and medical information about 2000 patients collected during 2003 in the United States. The proposed work was carried out by using the ML Knime tool.

sentiment-analysis-and-text-classification-of-drug-reviews icon sentiment-analysis-and-text-classification-of-drug-reviews

For the text Mining course I carried out a project related to the analysis and classification of the reviews of the "UCI ML Drug Review" dataset (link: https://archive.ics.uci.edu/ml/datasets/Drug+Review+Dataset+%28Drugs.com%29). I learned to apply techniques such as bag of words, TF-IDF and build sentiment analysis models through the Bert and Vader model.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.