Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: palynological data

Sortuj według:

Ogranicz wyniki do:

First 230Th/U date of middle Pleistocene peat bog in Siberia (key section Krivosheino, Western Siberia)

Maksimov F. E. F. E., Laukhin S. A., Arslanov K. A., Kuznetsov V. Y., Shilova G. N.

Geochronometria

2012

Vol. 39, no. 4

241-251

A ¹⁴C date older than 53900 yrs BP was obtained for the uppermost part of the buried peat bog in Krivosheino section (Middle Pleistocene of Western Siberia). These sediments also yielded ²³⁰Th/U dates of 195 _-9.1 ka using the leachate alone (L/L) and 204 ⁺¹⁷ _-13 ka using total sample dissolution (TSD) models. Peculiarities of 230Th/U dating are discussed. Palynological investigation of the buried peat bog together with underlying and overlaying sediments, and comparison with palynologi-cal data from Baikal and Elgygytgyn lakes revealed that the peat layer in Krivosheino section was formed at the end of Shirta Interglacial (Marine Isotopic-Oxygenous stages MIS-7), when climate conditions at all studied sites were more severe compared to the modern ones.

{GA}-Based Feed-Forward Neural Network For Image Classification: Application For the Grains of Pollen

Khorissi N., Mellit A., Guessoum A., Mesaouer A.

Journal of Applied Computer Science

2009

Vol. 17, nr 2

83-96

Palynological data are used in wide range application, the pattern recognition of pollen grains is very important in the determination of the original floral honey, and the prediction of the allergy, which touches lot of people. Due to the high computing time needed for classification of the pollen grains and complex architecture of the neural networks, the genetic algorithm is used in order to find the optimal architecture of the Multilayer perceptron (number of hidden layers and the number of neurons within each hidden layer). In this paper, a methodology for pollen grain classification based on the using of the MLP optimized by genetic algorithm (GA) called MLP-GA is described. A database of pollen images has been used in this work. Firstly, for each image we have calculated some morphological and geometric features. Subsequently, the MLP-GA network has been used for classification of the image pollen. The best classification performance is achieved by using an experimental data base of grains pollen. The classification rate is 90% which is very promising, and by comparing the hybrid MLP-GA with others ANN architectures, we can note that the MLP-GA is faster (the convergence time is 500 iterations).