Ph.D. in Ingegneria Informatica E Dei Sistemi , 33rd cycle (2017-2020)
Ph.D. obtained in 2021
Dissertation:
Explaining black-box deep neural models' predictions, behaviors, and performances through the unsupervised mining of their inner knowledge (Abstract)
Tutors:
Tania Cerquitelli
Research presentation:
PosterProfile
Research topic
Opening the black-box decision-making process with prediction-local and model-global explanations
Research interests
Biography
During my PhD, I learned what research is and the value of knowing, speaking and facing with researchers from all over the world.
I learned the importance of the impacts that modern AI technologies can have on our society, thus I focused my studies on transparent and explainable machine learning processes.
The main research goal of my PhD thesis is to design innovative solutions to explain the reasons and the processes that brought to specific outcomes produced by a black-box data analytics algorithm (e.g., neural networks) and to explain whether or not the models under analysis remain reliable over time in presence of concept drift.
Also, I experienced teaching activities for degree courses related to Data Bases and Big Data analytics.
I participated to several research projects funded by private and public entities, collaborating with international companies, studying and developing new solutions for the Industry 4.0, co-authoring several research papers published in international conferences and, in every new project, I always look forward improving myself learning from collaborators and friends.
Awards and Honors
- BEST PAPER AWARD for the paper titled "iSTEP, An Integrated Self-Tunin g Engine for Predictive Maintenance in Industry 4.0" published in the 16th IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA 2018), held in Melbourne, Australia, 11-13 December 2018. (2019)
- BEST PAPER AWARD for the paper titled "Clustering-Based Assessment of Residential Consumers from Hourly-Metered Data" published in the "International Conference on Smart Energy Systems and Technologies", 10-12 September 2018, University of Sevilla, Sevilla, Spain (2019)
Teaching
Teachings
Master of Science
- Big data: architectures and data analytics. A.A. 2017/18, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
- Big data: architectures and data analytics. A.A. 2018/19, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
- Big data: architectures and data analytics. A.A. 2020/21, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
- Data science lab: process and methods. A.A. 2019/20, DATA SCIENCE AND ENGINEERING. Collaboratore del corso
- Data science lab: process and methods. A.A. 2020/21, DATA SCIENCE AND ENGINEERING. Collaboratore del corso
Bachelor of Science
- Introduction to databases. A.A. 2017/18, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
- Introduction to databases. A.A. 2018/19, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
Publications
Works published during the Ph.D. View all publications in Porto@Iris
- Ventura, Francesco (2021)
Explaining black-box deep neural models' predictions, behaviors, and performances through the unsupervised mining of their inner knowledge. relatore: CERQUITELLI, TANIA; , 33. XXXIII Ciclo, P.: 141
Doctoral Thesis - Cerquitelli, Tania; Ventura, Francesco; Apiletti, Daniele; Baralis, Elena; Macii, ... (2021)
Enhancing manufacturing intelligence through an unsupervised data-driven methodology for cyclic industrial processes. In: EXPERT SYSTEMS WITH APPLICATIONS. ISSN 0957-4174
Contributo su Rivista - Cerquitelli, T; Nikolakis, N; Bethaz, P; Panicucci, S; Ventura, F; Macii, E; Andolina, ... (2020)
Enabling predictive analytics for smart manufacturing through an IIoT platform. In: 4th IFAC Workshop on Advanced Maintenance Engineering, Services and Technologies - AMEST 2020, Cambridge (UK), 10 September 2020through 11 September 2020, pp. 179-184. ISSN 2405-8963
Contributo in Atti di Convegno (Proceeding) - Attanasio, Giuseppe; Giobergia, Flavio; Pasini, Andrea; Ventura, Francesco; Baralis, ... (2020)
DSLE: A Smart Platform for Designing Data Science Competitions. In: 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), Madrid (Spain), July 13-17, pp. 133-142. ISBN: 978-1-7281-7303-0
Contributo in Atti di Convegno (Proceeding) - Panicucci, S.; Nikolakis, N.; Cerquitelli, T.; Ventura, F.; Proto, S.; Macii, E.; ... (2020)
A cloud-to-edge approach to support predictive analytics in robotics industry. In: ELECTRONICS, vol. 9, pp. 492-513. ISSN 2079-9292
Contributo su Rivista - Ventura, Francesco; Cerquitelli, Tania (2019)
What's in the box? Explaining the black-box model through an evaluation of its interpretable features. pp. 1-5
Altro - Cerquitelli, Tania; Proto, Stefano; Ventura, Francesco; Apiletti, Daniele; Baralis, ... (2019)
Automating concept-drift detection by self-evaluating predictive model degradation. pp. 1-5
Altro - Proto, Stefano; DI CORSO, Evelina; Ventura, Francesco; Cerquitelli, Tania (2018)
Useful ToPIC: Self-tuning strategies to enhance Latent Dirichlet Allocation. In: BigData Congress 2018, San Francisco (USA), July 2-7, 2018, pp. 33-40. ISBN: 978-1-5386-7232-7
Contributo in Atti di Convegno (Proceeding) - Cerquitelli, T.; Di Corso, E.; Ventura, F.; Chiusano, S. (2017)
Prompting the data transformation activities for cluster analysis on collections of documents. In: 25th Italian Symposium on Advanced Database Systems, SEBD 2017, Squillace Lido, Catanzaro, Italy, June 25th-29th, 2017,, Squillace Lido, Catanzaro, Italy, June 25th-29th, 2017, pp. 1-8
Contributo in Atti di Convegno (Proceeding) - Di Corso, Evelina; Ventura, Francesco; Cerquitelli, Tania (2017)
All in a twitter: Self-tuning strategies for a deeper understanding of a crisis tweet collection. In: Big Data (Big Data), 2017 IEEE International Conference on, Boston (USA), 11-14 Dec. 2017, pp. 3722-3726. ISBN: 978-1-5386-2715-0
Contributo in Atti di Convegno (Proceeding)