Foto del docente

Danilo Montesi

Professore ordinario

Dipartimento di Informatica - Scienza e Ingegneria

Settore scientifico disciplinare: INF/01 INFORMATICA

Didattica

Argomenti di tesi proposti dal docente.

Below a partial list of thesis and internships. Please talk to me during office hours for more details. Here are some instructions for writing essays, internships and thesis  (work in progress).

Available thesis (and internships)

1. Biomedical/socio-clinical data analysis

  • Data mining of clinical data for the prediction of serious unexpected events

  • Clinical predictions using heterogeneous data of patients (text, codes, parameters)

  • PubMed full-text dataset crawling and scraping

2. Temporal Information Retrieval and Mining

  • Tree index for access and search of time intervals in text

  • Evaluation of Temporal Word Embeddings in web archives for text classification

3. Text Mining

  • Text classification in the International Classification of Diseases (ICD-9, ICD-10) for Emergency Department diagnosis

  • Domain-specific word embeddings for ICD (semi)automatic coding of discharge texts

4. Cloud/social networks/digital forensics

  • Data exploration tool for investigating social networks of crime-involved subjects

  • Text, pictures and sensors digital footprints analysis

5. Copyright and watermarking

  • Text authorship attribution by learning characterizing features of writing styles from big datasets

  • Text watermarking and digital rights management for copyright protection

  • Fake news tracking using watermarking to certify the source reliability

6. Competition in Digital markets

  • competition among service/app providers in the digital markets

  • data portability/open access as technical solution to foster competition

  • online search engine ranking and competition alteration 

  • artificial intelligence and competition

7. Similarity distances for plagiarism detection in

  • source code

  • text 

  • user experience (human-computer interaction + graphical aspects)

8. Interpretability and Explainability in AI using

  •  neural networks
  • machine learning