Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

Wyszukujesz frazę "Multidimensional Discriminant Analysis" wg kryterium: Temat


Wyświetlanie 1-2 z 2
Tytuł:
Metoda 4M – nowe zastosowanie spektroskopii mössbauerowskiej w klasyfikacji zrównoważonych chondrytów zwyczajnych
4M method – the new application of Mössbauer spectroscopy for classification of equilibrated ordinary chondrites
Autorzy:
Woźniak, Marek
Karwowski, Łukasz
Gałązka-Friedman, Jolanta
Duda, Przemysław
Jakubowska, Martyna
Bogusz, Patrycja
Powiązania:
https://bibliotekanauki.pl/articles/1033156.pdf
Data publikacji:
2020
Wydawca:
Polskie Towarzystwo Meteorytowe
Tematy:
4M method
Cluster Analysis
Mahalanobis distance
Multidimensional Discriminant Analysis
Mössbauer spectroscopy
Principal Components Analysis
meteorites
meteorites classification
ordinary chondrites
Opis:
The 4M method aims to determine the type of equilibrated ordinary chondrite only on the basis of the Mössbauer spectrum of the investigated meteorite. Mössbauer spectrum of non-weathered ordinary chondrite is comprised of four sub-spectra: two doublets and two sextets. One of the doublets consists of a signal from iron present in olivine and the other consists of a signal from iron present in pyroxene. Sextets on the other hand, contain signals from magnetically ordered iron. One sextet is related to the metallic phase (kamacite, taenite), whereas the second is related to troilite. A third of doublets, which emerges in weathered ordinary chondrites, is related to products of the oxidation of iron present in metallic phase. The spectral areas of olivine, pyroxenes, metallic phase and troilite, which were obtained from Mössbauer spectrum are proportional to the number of iron atoms present in relevant mineral phases. Some Mössbauer groups were inspired by this fact to construct different methods to determine the type (H, L, or LL) of investigated meteorites (Gałązka-Friedman et al. 2019, Hyp. Inter. 241(1)). However, these methods, based on subjective criteria, were only qualitative. Our group elaborated a quantitative method, which is based on objective criteria. We called it the "4M method" (where M are derived from meteorites, Mössbauer spectroscopy, multidimensional discriminant analysis (MDA), Mahalanobis distance) (Woźniak et al. 2019). This method was using only the Mössbauer experimental data, to which it applied advanced statistical methods. The base, which was created from Mössbauer data, consisted of three clusters H, L, LL. These clusters were constructed with sets of 4-dimensional vectors. The vectors are comprised of spectral areas of Mössbauer spectrum: ol (value proportional to iron present in olivine), pyr (value proportional to iron present in pyroxene), met (value proportional to iron present in metallic phase), tr (value proportional to iron present in troilite). To determine the type of investigated ordinary chondrite, its ol, pyr, met and tr values with average values of variables obtained for clusters H, L and LL need to be compared. The comparison can be performed with the use of MDA and Mahalanobis distance. Once Mahalanobis distance of the investigated meteoriteis is known, the level of similarity to three types of ordinary chondrites can be calculated. Examples of such calculations were performed for seven ordinary chondrites: Goronyo, Carancas, New Concord, NWA 7733, Leoncin, Sołtmany and Pułtusk. They were made with the use of the new base composed of 62 non-weathered ordinary chondrites. All results obtained with the 4M method yielded results consistent with traditional mineralogical methods.
Źródło:
Acta Societatis Metheoriticae Polonorum; 2020, 11; 125-140
2080-5497
Pojawia się w:
Acta Societatis Metheoriticae Polonorum
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A new method for identifying outlying subsets of data
Autorzy:
Zalewska, M.
Grzanka, A.
Niemiro, W.
Samoliński, B.
Powiązania:
https://bibliotekanauki.pl/articles/970610.pdf
Data publikacji:
2008
Wydawca:
Polska Akademia Nauk. Instytut Badań Systemowych PAN
Tematy:
misclassification error
discriminant analysis
multidimensional homogeneity test
medical data
Opis:
In various branches of science, e.g. medicine, economics, sociology, it is necessary to identify or detect outlying subsets of data. Suppose that the set of data is partitioned into many relatively small subsets and we have some reason to suspect that one or several of these subsets may be atypical or aberrant. We propose applying a new measure of separability, based on the ideas borrowed from the discriminant analysis. In our paper we define two versions of this measure, both using a jacknife, leave-one-out, estimator of classification error. If a suspected subset is significantly well separated from the main bulk of data, then we regard it as outlying. The usefulness of our algorithm is illustrated on a set of medical data collected in a large survey "Epidemiology of Allergic Diseases in Poland" (ECAP). We also tested our method on artificial data sets and on the classical IRIS data set. For a comparison, we report the results of a homogeneity test of Bartoszyński, Pearl and Lawrence, applied to the same data sets.
Źródło:
Control and Cybernetics; 2008, 37, 3; 693-709
0324-8569
Pojawia się w:
Control and Cybernetics
Dostawca treści:
Biblioteka Nauki
Artykuł
    Wyświetlanie 1-2 z 2

    Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies