Enrico Ferrari

Dr. Enrico Ferrari

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 June 2023 in Computers
Verified
Journal Article
Open access
PDF file
EFEnrico Ferrari
Enrico Ferrari
Damiano VerdaDamiano Verda
Damiano Verda
NPNicolò Pinna
Nicolò Pinna
MMMARCO MUSELLI
MARCO MUSELLI
Optimizing water distribution both from an energy-saving perspective and from a quality of service perspective is a challenging task since it involves a complex system with many nodes, many hidden variables and many operational constraints. For this reason, water distribution systems need to handle a delicate trade-off between the effectiveness and computational time of the solution. In this paper, we propose a new computationally efficient method, named rule-based control, to optimize water distribution networks without the need for a rigorous formulation of the optimization problem. As a matter of fact, since it is based on a machine learning approach, the proposed method employs only a set of historical data, where the configuration can be labeled according to a quality criterion. Since it is a data-driven approach, it could be applied to any complex network where historical labeled data are available. In particular, rule-based control exploits a rule-based classification method that allows us to retrieve the rules leading to good or bad performances of the system, even without any information about its physical laws. The evaluation of the results on some simulated scenarios shows that the proposed approach is able to reduce energy consumption while ensuring a good quality of the service. The proposed approach is currently used in the water distribution system of the Milan (Italy) water main.

1 November 2021 in Microprocessors and Microsystems
Verified
Journal Article
Open access
JAJ.A. Agirre
J.A. Agirre
LEL. Etxeberria
L. Etxeberria
RBR. Barbosa
R. Barbosa
SBS. Basagiannis
S. Basagiannis
GGG. Giantamidis
G. Giantamidis
BSBehrooz Sangchoolie
Behrooz Sangchoolie


22 June 2022 in Computing
Verified
Journal Article
Open access
PDF file
Ali DaherAli Daher
Ali Daher
EFEnrico Ferrari
Enrico Ferrari
MMMARCO MUSELLI
MARCO MUSELLI
Hussein ChibleHussein Chible
Hussein Chible
Daniele D. CavigliaDaniele D. Caviglia
Daniele D. Caviglia
Machine learning techniques aim to mimic the human ability to automatically learn how to perform tasks through training examples. They have proven capable of tasks such as prediction, learning and adaptation based on experience and can be used in virtually any scientific application, ranging from biomedical, robotic, to business decision applications, and others. However, the lack of domain knowledge for a particular application can make feature extraction ineffective or even unattainable. Furthermore, even in the presence of pre-processed datasets, the iterative process of optimizing Machine Learning parameters, which do not translate from one domain to another, maybe difficult for inexperienced practitioners. To address these issues, we present in this paper a Vectorized Automated ML Pre-processIng and post-pRocEssing framework, approximately named (VAMPIRE), which implements feature extraction algorithms capable of converting large time-series recordings into datasets. Also, it introduces a new concept, the Activation Engine, which is attached to the output of a Multi Layer Perceptron and extracts the optimal threshold to apply binary classification. Moreover, a tree-based algorithm is used to achieve multi-class classification using the Activation Engine. Furthermore, the internet of things gives rise to new applications such as remote sensing and communications, so consequently applying Machine Learning to improve operation accuracy, latency, and reliability is beneficial in such systems. Therefore, all classifications in this paper were performed on the edge in order to reach high accuracy with limited resources. Moreover, forecasts were applied on three unrelated biomedical datasets, and on two other pre-processed urban and activity detection datasets. Features were extracted when required, and training and testing were performed on the Raspberry Pi remotely, where high accuracy and inference speed were achieved in every experiment. Additionally, the board remained competitive in terms of power consumption when compared with a laptop which was optimized using a Graphical Processing Unit.