ABSTRACT
Over the years, transportable instrumentation for cultural heritage (CH) in situ measurements has noticeably widespread, due to logistic, economical and safety reasons. Ion beam analysis, a powerful set of analytical techniques, of great importance for CH, is instead carried out by using fixed instrumentation. To overcome this limit, the Italian national Institute of Nuclear Physics (INFN), CERN (European Centre for Nuclear Research) and the Opificio delle Pietre Dure (OPD), started MACHINA, the "Movable Accelerator for CH In-situ Non-destructive Analysis: the new generation of accelerators for art” to build a transportable accelerator, compact, with strongly reduced weight, absorbed power and cost. MACHINA will be installed at the OPD and dedicated to CH. It will be moved to major conservation centres and museums, when needed. The INFN-CERN proposal, approved in December 2017, became operative in February 2018. 2018 was dedicated to the acquisition of material/instrumentations, to set up both a dummy accelerator (to test the vacuum system) and a vacuum chamber (to test the source). Due to COVID, in 2020 and 2021 the experimental work was slowed down, but we kept developing the control electronics/software and built the second-generation supporting structure. The HF-RFQ power supplies were integrated in October 2021. At the rise of 2022, after conditioning the cavities, we tested the system and in March 2022 we got the first extracted 2-MeV proton beam. In this paper, we present the structure of the MACHINA system, the approach followed and the main solutions adopted, with a special focus on the control system, and finally the first experimental results. © 2023, The Author(s).
ABSTRACT
COVID-19, an infectious coronavirus disease, triggered a pandemic that resulted in countless deaths. Since its inception, clinical institutions have used computed tomography as a supplemental screening method to reverse transcription-polymerase chain reaction. Deep learning approaches have shown promising results in addressing the problem;however, less computationally expensive techniques, such as those based on handcrafted descriptors and shallow classifiers, may be equally capable of detecting COVID-19 based on medical images of patients. This work proposes an initial investigation of several handcrafted descriptors well known in the computer vision literature already been exploited for similar tasks. The goal is to discriminate tomographic images belonging to three classes, COVID-19, pneumonia, and normal conditions, and present in a large public dataset. The results show that kNN and ensembles trained with texture descriptors achieve outstanding accuracy in this task, reaching accuracy and F-measure of 93.05% and 89.63%, respectively. Although it did not exceed state of the art, it achieved satisfactory performance with only 36 features, enabling the potential to achieve remarkable improvements from a computational complexity perspective. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.