Temat: PCA (Principal Component Analysis)

Skocz do pozycji: 1.

Tytuł:: Projekt autonomicznego robota inspekcyjnego
Project of autonomous inspection robot
Autorzy:: Majek, K.
Pełka, M.
Będkowski, J.
Cader, M.
Masłowski, A.
Tematy:: robot inspekcyjny
laserowy system pomiarowy 3D
PCA (Principal Component Analysis)
inspection robot
laser measurement 3D system; Pokaż więcej
Wydawca:: Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów
Powiązania:: https://bibliotekanauki.pl/articles/276604.pdf Link otwiera się w nowym oknie
Opis:: W artykule przedstawiono projekt autonomicznego robota inspekcyjnego. Ze względu na fakt, że komercyjne rozwiązania nie oferują satysfakcjonującej funkcjonalności w stosunkowo niskiej cenie zdecydowano się zaprojektować autonomicznego robota inspekcyjnego na bazie komercyjnej platformy wyposażonej w autorskie rozwiązanie laserowego systemu pomiarowego 3D. Projekt lasera 3D wykonano z wykorzystaniem technik szybkiego prototypowania metodą druku 3D. Autonomiczny robot mobilny nawigowany jest na podstawie systemu IMU (Inertial Measurement Unit) ze zintegrowanym GPS (Global Positioning System). Opracowane rozwiązanie dostarcza użytkownikowi danych w postaci map lokalnych 3D wraz z częściową analizą semantyczną (obliczanie wektorów normalnych dla chmury punktów metodą PCA Principal Component Analysis) w trybie on-line. Przeprowadzono eksperymenty weryfikujące poprawność działania systemu. W rezultacie powstało nowoczesne stanowisko badawcze, które może być wykorzystane do kolejnych badań z wykorzystaniem mobilnych systemów inspekcyjnych.
In the article the project of autonomous inspection robot is shown. Instead of commercial applications, proposed approach with relatively lower prize offer satisfactory functionality. Proposed approach is based on State of the Art mobile platform equipped with developed 3D laser measurement system 3D. Laser 3D is developed based on Fused Deposition Modeling FDM technology. Autonomous mobile robot is using IMU (Inertial Measurement Unit) wit GPS (Global Positioning System) to navigate in outdoor environment. The approach offers 3D cloud of points augmented by normal vectors looking form user point of view. Normal vectors are computed using PCA (Principal Component Analysis) method in on-line fashion. The proof of concept was demonstrated based on the experiment in the real environment. As a result the modern research platform is developed, which can be used for further inspection systems' analysis.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 2.

Tytuł:: Application of GGE biplot graphs in multi-environment trials on selection of forest trees
Autorzy:: Ukalski, Krzysztof
Klisz, Marcin
Wydawca:: The Forest Sciences and Committee on Forestry Sciences and Wood Technology of the Polish Academy of Sciences; Instytut Badawczy Lesnictwa (Forest Research Institute), Sekocin Stary, Poland
Opis:: In the studies on selection and population genetics of forest trees that include the analysis of genotype × environment interaction (GE), the use of biplot graphs is relatively rare. This article describes the models and analytic methods useful in the biplot graphs, which enable the analyses of mega-environments, selection of the testing environment, as well as the evaluation of genotype stability. The main method presented in the paper is the GGE biplot method (G – genotype effect, GE –genotype × environment interaction effect). At the same time, other methods have also been referred to, such as, SVD (singular value decomposition), PCA (principal component analysis), linear-bilinear SREG model (sites regression), linear-bilinear GREG model (genotypes regression) and AMMI (additive main effects multiplicative interaction). The potential of biplot method is presented based on the data on growth height of 20 European beech genotypes (Fagus sylvatica L.), generated from real data concerning selection trials and carried out in 5 different environments. The combined ANOVA was performed using fixed-effects, as well as mixed-effects models, and significant interaction GE was shown. The GGE biplot graphs were constructed using PCA. The first principal component (GGE1) explained 54%, and the second (GGE2) explained more than 23% of the total variation. The similarity between environments was evaluated by means of the AEC method, which allowed us to determine one mega-environment that comprised of 4 environments. None of the tested environments represented the ideal one for trial on genotype selection. The GGE biplot graphs enabled: (a) the detection of a stable genotype in terms of tree height (high and low), (b) the genotype evaluation by ranking with respect to the height and genotype stability, (c) determination of an ideal genotype, (d) the comparison of genotypes in 2 chosen environments.
Przemysław Szmit
Dostawca treści:: Repozytorium Centrum Otwartej Nauki

Artykuł

na półce

Skocz do pozycji: 3.

Artykuł

na półce

Skocz do pozycji: 4.

Tytuł:: Klasteryzacja względem krzywych
Clustering in curve linear system
Autorzy:: Supronowicz, Rafał
Opis:: A primary goal of the thesis is an introduction of (k,omega)-means algorithm and its implementation. It is a clustering type of algorithm, the modification of k-means. In addition of a distance between a cluster mean and objects, it takes in account the distance between objects and a function, which describes the group. PCA, linear regression and other necessary definitions were introduced in the document. Both k-means and (k,omega)-means were presented. The implementation is a R package written in C++, using Rcpp and RcppArmadillo libraries. A set of experiments were executed. A list of conclusions, potential problems, fixes and upgrades was made for both algorithm and implementation.
Praca ma na celu przedstawienie algorytmu (k,omega)-means, oraz jego implementacje. Jest to algorytm klasteryzacji bazujący na k-średnich, który decyzję o przynależności obiektów do klastra opiero nie tylko o odległość punktu od centrum, ale także o odległość od funkcji opisującej grupę. W pracy przedstawiono analizę składowych głównych, regresję liniową, oraz pojęcia, którymi operuje metoda. Przybliżono także algorytmy k-means, (k,omega)-means, oraz jego implementację w postaci wtyczki R. Program został napisany w C++ przy użyciu bibliotek Rcpp i RcppArmadillo. Przeprowadzono serię eksperymentów, oraz zebrano wnioski i propozycje usprawnień zarówno o programie jak i samym algorytmie.
Dostawca treści:: Repozytorium Uniwersytetu Jagiellońskiego

Inne

na półce

Skocz do pozycji: 5.

Tytuł:: Factors of the development of organic farming in Poland at the voivodship level
Autorzy:: Nowak, Ewa
Jadczyszyn, Jan
Tematy:: organic farming
Rural Development Program
Principal component analysis – PCA
voivodships
Polska; Pokaż więcej
Wydawca:: Instytut Uprawy Nawożenia i Gleboznawstwa – Państwowy Instytut Badawczy
Powiązania:: https://bibliotekanauki.pl/articles/2148092.pdf Link otwiera się w nowym oknie
Opis:: The purpose of the research based on the data from the Report on the state of organic farming in Poland in 2015–2016 and environmental conditions, was to determine the impact of natural and economic factors and subsidies from EU programs on the level of organic production and to better understand the diver-sity of the spatial structure of organic farming within the system of provinces (voivodships). Nineteen structural, socio-economic and financial features, and 3 environmental features that charac-terize the quality of agricultural production and forms of nature protection for 16 voivodships, were used as assessment criteria.Principal component analysis allowed the basic factors of diver-sification to be discovered of the set of voivodships contained in the hidden structure defined by the features adopted for analysis. Homogeneous groups – organic farming types by voivodships were distinguished using the k-means method.The comparative analysis allowed the connections between the structure of organic farming and its place in voivodships to be highlighted in connection with support for organic farming, the number of producers of organic agricultural products, production of feed on arable land, production of cereals and vegetables. The location of organic farms is related to the occurrence of Natura 2000 areas. The first type includes two voivodships, Zachodnio-pomorskie and Warmińsko-Mazurskie – with the highest level of development of organic farming. In the second type, the fol-lowing voivodships were concentrated: Lubelskie, Łódzkie, Ma-zowieckie, Podlaskie and Świętokrzyskie, with a high level of or-ganic farming, where farms smaller in area, that focus on fruit and vegetable production are the predominant type. In the third type, the following voivodships were located in the region of western Poland: Pomorskie and Wielkopolskie with a medium level of organic farming and very diverse in characteristics, including the largest and smaller organic farms with a low level of fruit and vegetable production. The fourth type includes the Małopolskie and Podkarpackie voivodships with a very small farm area and a small number of producers. In the fifth type with the least developed organic farming with a small number of producers and low fruit and vegetable production, three voivodships focused on the average farm area: Śląskie, Opolskie and Kujawsko-Pomorskie.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 6.

Tytuł:: Assessment of the influence of soil properties on 137Cs accumulation in Of horizon in forest soils
Autorzy:: Ziembik, Z.
Dołhańczuk-Śródka, A.
Wacławek, M.
Tematy:: 137Cs
forest soil
physicochemical parameters
cluster analysis (CA)
principal component analysis (PCA); Pokaż więcej
Wydawca:: Instytut Chemii i Techniki Jądrowej
Powiązania:: https://bibliotekanauki.pl/articles/148398.pdf Link otwiera się w nowym oknie
Opis:: The work focuses on assessment of soil physicochemical parameters influence on 137Cs accumulation in Of soil horizon. Besides organic matter content and pH, the parameters related to sorption properties and mobile ions concentration were considered. The data were transformed using Box-Cox formula. To find mutual relationships between variables cluster analysis (CA) and principal components analysis (PCA) were used. It was found that the transformed physicochemical parameters in Of horizon are more or less related with each other but no linear or nearly linear relationships between 137Cs activity and physicochemical parameters were found.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 7.

Tytuł:: Biometric watermarking for security enhancement in digital images
Autorzy:: Wójtowicz, W.
Tematy:: images security
watermarking technique
discrete wavelet transform (DWT)
biometrics
principal component analysis (PCA); Pokaż więcej
Wydawca:: Fundacja na Rzecz Młodych Naukowców
Powiązania:: https://bibliotekanauki.pl/articles/115437.pdf Link otwiera się w nowym oknie
Opis:: In this paper some preliminary investigation on combination of watermarking technique with biometric data to increase security of digital images in case of medical images is proposed. Performance of watermarking algorithm, based on discrete wavelet transform (DWT) decomposition, that incorporates biometric watermark is elaborated. The frequency domain were chosen as it is proven, that this domain provides better robustness against attacks and leads to less perceptibility of an embedded watermark. To assure confidentiality of patient data their hand geometry features are embedded instead of patient’s name. Proposed system is evaluated by measuring the similarity between embedded and extracted biometric codes.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 8.

Tytuł:: Differences between technological and textural parameters of meat from farmed and wildlife red deer (Cervus elaphus) determined by PCA method
Różnice pomiędzy parametrami technologicznymi i teksturalnymi mięsa jeleni (Cervus elaphus) hodowlanych i dziko żyjących określone metodą składowych głównych
Autorzy:: Kral, M.
Snirc, M.
Tremlova, B.
Tematy:: farmed deer
wildlife animal
red deer
Cervus elaphus
meat
difference
technological parameter
texture parameter
determination
PCA method zob.principal component analysis
principal component analysis; Pokaż więcej
Wydawca:: Polskie Towarzystwo Technologów Żywności
Powiązania:: https://bibliotekanauki.pl/articles/825883.pdf Link otwiera się w nowym oknie
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 9.

Tytuł:: Forecast of prices and volatility on the day ahead market
Autorzy:: Ganczarek-Gamrot, Alicja
Tematy:: principal component analysis (PCA)
SARIMA model
DCC model
Value-at- -Risk
portfolio; Pokaż więcej
Wydawca:: Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu
Powiązania:: https://bibliotekanauki.pl/articles/425278.pdf Link otwiera się w nowym oknie
Opis:: The subject of this paper is the forecast of prices and volatility on the Day Ahead Market (DAM). The analysis was made for two portfolios of four contracts from 30.03.2009 to 28.10.2011 for two fixings on DAM. Four out of 24 contracts noted on DAM were chosen by PCA. Prices were forecast by the SARIMA models incorporating autocorrelation and seasonality. Value-at-Risk calculated through the DCC model was used to forecast volatility. These models describe well the prices and volatility on the DAM and may be used for forecasting purposes. Prices on fixing 2 are characterized by higher volatility than prices on fixing 1.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Skocz do pozycji: 10.

Tytuł:: Source apportionment of the PM10 fraction of particulate matter collected in Kraków, Poland
Autorzy:: Samek, L.
Tematy:: air pollution
energy dispersive X-ray fluorescence (EDXRF)
elemental concentration
particulate matter
statistical analyses
PCA - principal component factor analysis
MLRA - multilinear regression analysis; Pokaż więcej
Wydawca:: Instytut Chemii i Techniki Jądrowej
Powiązania:: https://bibliotekanauki.pl/articles/146888.pdf Link otwiera się w nowym oknie
Opis:: Samples of PM10 fraction of air particulates were collected during the winter of 2010 at two different sites in the City of Kraków, Poland. One site was located nearby a steel mill (Nowa Huta district) and the second one was situated at a distance of 10 km from the first site (Krowodrza district). The measured mass concentrations of PM10 fraction were in the range of 33 to 358 μg/m3. They exceeded the permissible daily limit value of 50 μg/m3. The Voivodship Inspectorate for Environmental Protection in Kraków was in charge of collecting samples as well as determining mass concentrations. Assessment of elemental concentrations and statistical analyses were performed at the University of Science and Technology in Kraków. Mean concentrations of Ti, Cu, Br and Pb were almost the same at both sites, while those of K, Ca and Zn were two times higher at Nowa Huta than at Krowodrza. Cr, Mn and Fe mass concentrations were also higher at Nowa Huta site; the values were a factor of three higher for Cr and Mn and factor of four for Fe. Factor analysis (FA) and multilinear regression analysis (MLRA) were used to determine source contributions to ambient PM10. The measurements were based on PM10 composition data which included elemental concentrations. Local combustion, industry and other, not identified sources, such as secondary aerosols, were the factors that highly contributed to the pollution of PM10 during winter time. For the site at Nowa Huta 53.1% of pollution was attributable to combustion and traffic, 28.5% was due to industry and wood combustion, and 18.3% were not identified. For the Krowodrza site, industry and wood combustion contributed 46.1%, combustion and traffic 50.4% and other, not identified sources 3.5% of the total PM10. Examination of meteorological data suggested that the concentration of potassium was inversely proportional to ambient air temperature at both sites. A wood combustion was identified as possible source of potassium in PM10.
Dostawca treści:: Biblioteka Nauki

Artykuł

na półce

Informacja

Wyszukujesz frazę "PCA (Principal Component Analysis)" wg kryterium: Temat