1.
|
A Carbon Tracking Model for Federated Learning: Impact of Quantization and Sparsification
/ Barbieri, Luca (Milan, Polytech.) ; Savazzi, Stefano ; Kianoush, Sanaz ; Nicoli, Monica (Milan, Polytech.) ; Serio, Luigi (CERN)
Federated Learning (FL) methods adopt efficient communication technologies to distribute machine learning tasks across edge devices, reducing the overhead in terms of data storage and computational complexity compared to centralized solutions. Rather than moving large data volumes from producers (sensors, machines) to energy-hungry data centers, raising environmental concerns due to resource demands, FL provides an alternative solution to mitigate the energy demands of several learning tasks while enabling new Artificial Intelligence of Things (AIoT) applications. [...]
arXiv:2310.08087.-
2023-11-06 - 6 p.
- Published in : 10.1109/CAMAD59638.2023.10478391
Fulltext: PDF;
In : IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD 2023), Edinburgh, Scotland, 6-8 Nov 2023, pp.213-218
|
|
2.
|
|
|
A Secure and Trustworthy Network Architecture for Federated Learning Healthcare Applications
/ Boiano, Antonio (Milan, Polytech.) ; Di Gennaro, Marco (Milan, Polytech.) ; Barbieri, Luca (Milan, Polytech.) ; Carminati, Michele (Milan, Polytech.) ; Nicoli, Monica (Milan, Polytech.) ; Redondi, Alessandro (Milan, Polytech.) ; Savazzi, Stefano (IFN, Rome) ; Aillet, Albert Sund (CERN) ; Santos, Diogo Reis (CERN) ; Serio, Luigi (CERN)
Federated Learning (FL) has emerged as a promising approach for privacy-preserving machine learning, particularly in sensitive domains such as healthcare. [...]
arXiv:2404.11698.
-
6 p.
Fulltext
|
|
3.
|
Decentralized Federated Learning for Healthcare Networks: A Case Study on Tumor Segmentation
/ Camajori Tedeschini, Bernardo (Milan, Polytech.) ; Savazzi, Stefano (ISTP, Milan) ; Stoklasa, Roman (CERN) ; Barbieri, Luca (Milan, Polytech.) ; Stathopoulos, Ioannis (CERN) ; Nicoli, Monica (Milan, Polytech.) ; Serio, Luigi (CERN)
Smart healthcare relies on artificial intelligence (AI) functions for learning and analysis of patient data. Since large and diverse datasets for training of Machine Learning (ML) models can rarely be found in individual medical centers, classical centralized AI requires moving privacy-sensitive data from medical institutions to data centers that process the fused information. [...]
2022 - 16 p.
- Published in : IEEE Access 10 (2022) 8693-8708
Fulltext: PDF;
|
|
4.
|
Assessment of few-hits machine learning classification algorithms for low-energy physics in liquid argon detectors
/ Moretti, Roberto (INFN, Milan Bicocca ; Milan Bicocca U.) ; Rossi, Marco (CERN ; Milan U. ; INFN, Milan) ; Biassoni, Matteo (INFN, Milan Bicocca) ; Giachero, Andrea (INFN, Milan Bicocca ; Milan Bicocca U.) ; Grossi, Michele (CERN) ; Guffanti, Daniele (INFN, Milan Bicocca ; Milan Bicocca U.) ; Labranca, Danilo (INFN, Milan Bicocca ; Milan Bicocca U.) ; Terranova, Francesco (INFN, Milan Bicocca ; Milan Bicocca U.) ; Vallecorsa, Sofia (CERN)
The physics potential of massive liquid argon TPCs in the low-energy regime is still to be fully reaped because few-hits events encode information that can hardly be exploited by conventional classification algorithms. Machine learning (ML) techniques give their best in these types of classification problems. [...]
arXiv:2305.09744.-
2024-08-13 - 12 p.
- Published in : Eur. Phys. J. Plus 139 (2024) 723
Fulltext: 2305.09744 - PDF; document - PDF;
|
|
5.
|
A dual-detector extended range rem-counter
/ Ferrarini, M (Politecn Milan, Dipartimento Energia, Via Ponzio 34-3, I-20133 Milan, Italy. ; Politecn Milan, Dipartimento Energia, I-20133 Milan, Italy. ; Fdn CNAO, I-27100 Pavia, Italy.) ; Caresana, M (Politecn Milan, Dipartimento Energia, I-20133 Milan, Italy.) ; Silari, M (CERN) ; Agosteo, S (Politecn Milan, Dipartimento Energia, I-20133 Milan, Italy. ; Ist Nazl Fis Nucl, Sez Milano, I-20133 Milan, Italy.)
The design and characterization of a dual-detector spherical rem counter is discussed in this paper. The rem counter is based on a polythene sphere with lead and cadmium insets, designed to host at its centre either an active (He-3 SP9 proportional counter) or a passive (CR39 + B-10 radiator) thermal neutron detector. [...]
2010
- Published in : Radiat. Meas. 45 (2010) 1217-1219
|
|
6.
|
|
|
Accelerators for hadrontherapy: From Lawrence cyclotrons to linacs
/ Braccini, S (Univ Bern, Albert Einstein Ctr Fundamental Phys, High Energy Phys Lab, Sidlerstr 5, CH-3012 Bern, Switzerland. ; TERA Fdn, Novara, Italy.) ; Andres, S Verdu (TERA Fdn, Novara, Italy. ; Ctr Mixto CSIC UVEG, Inst Fis Corpuscular IFIC, Valencia 46071, Spain.) ; Garlasche, M (TERA Fdn, Novara, Italy.) ; Weiss, M (TERA Fdn, Novara, Italy.) ; Crescenti, M (TERA Fdn, Novara, Italy.) ; Pearce, P (TERA Fdn, Novara, Italy.) ; Rosso, E (TERA Fdn, Novara, Italy.) ; Wegner, R (TERA Fdn, Novara, Italy. ; CERN) ; Magrin, G (TERA Fdn, Novara, Italy.) ; Pitta, G (TERA Fdn, Novara, Italy.) et al.
Hadrontherapy with protons and carbon ions is a fast developing methodology in radiation oncology. The accelerators used and planned for this purpose are reviewed starting from the cyclotrons used in the thirties. [...]
2010
- Published in : Nucl. Instrum. Methods Phys. Res., A 620 (2010) 563-577
|
|
7.
|
Experience on Series Production of the HL-LHC Superferric High Order Corrector Magnets
/ Statera, M (Milan U.) ; Prioli, M (Milan U.) ; Broggi, F (Milan U.) ; De Matteis, E (Milan U.) ; Imeri, L (Milan U.) ; Leone, A (Milan U.) ; Mariotto, S (Milan U. ; INFN, Milan) ; Paccalini, A (Milan U.) ; Pasini, A (Milan U.) ; Pedrini, D (Milan U.) et al.
INFN has developed at the LASA lab (Milano, Italy) the High Order (HO) corrector magnets for the High Luminosity-LHC (HL-LHC) project, which will equip the new interaction regions. All the HO correctors, from skew quadrupole to dodecapole, are based on a novel superferric design, never used so far in high energy colliders, which allows a relatively simple, modular, and easy way to construct a magnet. [...]
2023 - 7 p.
- Published in : IEEE Trans. Appl. Supercond. 33 (2023) 1-7
|
|
8.
|
|
9.
|
The HL-LHC High Order Correctors Series Production and Powering Tests Status
/ Statera, M (Milan U.) ; Broggi, F (Milan U.) ; Matteis, E De (Milan U.) ; Imeri, L (Milan U.) ; Leone, A (Milan U.) ; Mariotto, S (Milan U. ; INFN, Milan) ; Paccalini, A (Milan U.) ; Pasini, A (Milan U.) ; Pedrini, D (Milan U.) ; Prioli, M (Milan U.) et al.
INFN is developing at the LASA lab (Milano, Italy) the High Order (HO) corrector magnets for the High Luminosity-LHC (HL-LHC) project, which will equip the new interaction regions. All the HO correctors, from skew quadrupole to dodecapole, are based on a novel superferric design, never used so far in high energy colliders, which allows a relatively simple, modular, and easy way to construct a magnet. [...]
2022 - 5 p.
- Published in : IEEE Trans. Appl. Supercond. 32 (2022) 4004405
In : 27th International Conference on Magnet Technology (MT-27), Fukuoka, Japan, 15 - 19 Nov 2021, pp.4004405
|
|
10.
|
Machine learning-based events classification in heterostructured scintillators
/ Lowis, C (CERN ; RWTH Aachen U.) ; Pagano, F (CERN ; Milan Bicocca U.) ; Kratochwil, N (CERN) ; Pizzichemi, M (Milan Bicocca U.) ; Langen, K J (RWTH Aachen U.) ; Ziemons, K (Applied Sci. U., Aachen) ; Hillemanns, E Auffray (CERN)
Time-of-flight positron emission tomography (TOF PET) faces the challenge of improving time resolution while maintaining high detector efficiency. Heterostructured scintillators, which consist of multiple layers of different scintillating materials with complementary properties, have emerged as a promising solution. [...]
2023 - 1 p.
- Published in : 10.1109/NSSMICRTSD49126.2023.10338326
In : 2023 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and Room Temperature Semiconductor Detector (RTSD) Conference (2023 IEEE NSS MIC RTSD), Vancouver, Canada, 4 - 11 Nov 2023
|
|