Browsing by Subject "pipelines"

Sort by: Order: Results:

Now showing items 1-2 of 2
  • Chumachenko, Kateryna; Männistö, Anssi; Iosifidis, Alexandros; Raitoharju, Jenni (IEEE, 2020)
    IEEE Access 8 (2020)
    In this paper, we demonstrate the benefits of using state-of-the-art machine learning methods in the analysis of historical photo archives. Specifically, we analyze prominent Finnish World War II photographers, who have captured high numbers of photographs in the publicly available Finnish Wartime Photograph Archive, which contains 160,000 photographs from Finnish Winter, Continuation, and Lapland Wars captures in 1939-1945. We were able to find some special characteristics for different photographers in terms of their typical photo content and framing (e.g., close-ups vs. overall shots, number of people). Furthermore, we managed to train a neural network that can successfully recognize the photographer from some of the photos, which shows that such photos are indeed characteristic for certain photographers. We further analyzed the similarities and differences between the photographers using the features extracted from the photographer classifier network. We make our annotations and analysis pipeline publicly available, in an effort to introduce this new research problem to the machine learning and computer vision communities and facilitate future research in historical and societal studies over the photo archives.
  • Kozyreva, Olga V.; Pilipenko, Vyacheslav A.; Marshalko, Elena E.; Sokolova, Elena Yu.; Dobrovolsky, Mikhail N. (MDPI AG, 2022)
    Applied sciences
    The influence of space factors on technological systems in the Arctic (power transmission lines, oil/gas pipelines) has become critically important. To examine in depth these effects, an archive of digital 1 min data from Soviet/Russian magnetic stations deployed along the Arctic coast was created, starting from 1983 to the present. All data from various sources were converted to daily files in standard IAGA-2002 format and supplemented with quick-look magnetograms. Some of these data are included already in the existing world magnetic field databases, but not all. Examples of disturbances known to excite intense geomagnetically induced currents in power transmission lines were presented: irregular Pi3 pulsations and magnetic perturbation events. The database was augmented with the global 3D model of the Earth’s conductivity structure. The given example showed how the combined usage of the geomagnetic field database and the conductivity model enables one to synthesize the geoelectric field response to geomagnetic variations, and to assess the distortions of the pipeline-soil potential. To determine regions most susceptible to geomagnetic hazard, a map with normalized telluric fields was created for a uniform sinusoidally varying magnetic disturbance. This map showed that the largest electrotelluric potentials and field are induced in regions with a high resistivity (e.g., Kola Peninsula and Ural Mountains). This database can be also a useful support for space missions in the magnetosphere. The database is publicly available on the anonymous FTP site.