The influence of the discrepancies in the observers' decisions on the process of identification of maceral groups using artificial neural networks

• Autorzy: Skiba M.

Identyfikatory

DOI

10.1016/j.jsm.2017.03.001

• Języki publikacji: EN

Abstrakty

EN

When analyzing the sorption properties of coal in the context of gas hazards in underground mining, focus should be placed on a number of aspects. These include the internal structure of coal, its structural properties, and its maceral composition. The share of particular macerals is most often determined manually, which e due to the huge diversity of petrographic features e can pose some difficulties even for experienced petrographers. Over the past few years, studies have been carried out into the use of artificial neural networks as a means to develop a methodology that would enable the identification of maceral groups based solely on the knowledge which the computer gains from sample macroscopic images and the information about their content provided by the observer. This paper investigates the effect that the selection of the training set, defined by particular teachers e petrographers, has on the effectiveness of selected neural classifiers. The research was carried out with the participation of three expert petrographers, who classified maceral groups in the macroscopic images of a lump sample of coal extracted from the Upper Silesian Coal Basin. Next, the feature space describing particular classes was defined using image analysis methods. The parameters defining that space were determined each time within a certain neighborhood of the studied points. Thus, the obtained sets were used to train neural networks (MLP) and to indicate the optimal network architecture for each expert. The research also included the identification of the influence that the change of the “teacher” e observer has on the identification process of the analyzed objects, as well as the automatic analysis of those measuring points which were classified differently by the observers e petrographers. The results presented concerning the objectivization of the quantitative analyses of coal indicate that modern methods of image analysis and artificial neural networks can contribute to the improvement of these measurements. However, it requires close cooperation between the designer of the neural network and the expert e petrographer.

Słowa kluczowe

EN

quantitative analysis of coal; maceral group; artificial neural network

PL

analiza ilościowa węgla; grupy maceralne; sztuczna sieć neuronowa

• Wydawca: Elsevier ; Główny Instytut Górnictwa
• Czasopismo: Journal of Sustainable Mining
• Rocznik: 2016
• Tom: Vol. 15, iss. 4
• Strony: 151--155
• Opis fizyczny: Bibliogr. 14 poz.

Twórcy

autor

Skiba M.

• The Strata Mechanics Research Institute of the Polish Academy of Sciences, Reymonta 27, 30-059 Cracow, Poland

Bibliografia

• Bishop, C. (1995). Neural networks for pattern recognition. Oxford: University Press.
• Bodziony, J. (1965). On certain indices characterizing the geometric structure of rocks. Bulletin de l’Academie Polonaise des Sciences, 8, 9.
• Bodziony, J., Gabzdyl, W., & Ratajczak, T. (1986). Evaluation of effect of a subjective factor on the results of stereological analysis of coal. Archives of Mining Sciences, 31, 689-702.
• Eberle, D., Hutchins, D., Das, S., Majumdar, A., & Paasche, H. (2015). Automated pattern recognition to support geological mapping and exploration target generation - a case study from southern Namibia. Journal of African Earth Sciences, 106, 60-74.
• Korbicz, J., Obuchowicz, A., & Uciński, D. (1994). Sztuczne sieci neuronowe. Podstawy i zastosowania [Artificial neural networks. Fundamentals and applications]. Warszawa: Akademicka Oficyna Wydawnicza PLJ.
• Marmo, R., Amodio, S., Tagliaferri, R., Ferreri, V., & Longo, G. (2005). Textural identification of carbonate rocks by image processing and neural network: Methodology proposal and examples. Computers & Geosciences, 31(5), 649-659.
• Marschallinger, R. (1997). Automatic mineral classification in the macroscopic scale. Computers & Geosciences, 23(1), 119-126.
• Młynarczuk, M., Godyń, K., & Skiba, M. (2015). Wykorzystanie sztucznych sieci neuronowych do klasyfikacji struktur odmienionych węgla kamiennego w strefach przyuskokowych [The application of artificial neural networks for the classification of altered structures of hard coal in near-fault zones]. Przegląd Górniczy, 11, 15-20.
• Młynarczuk, M., Górszczyk, A., & Ślipek, B. (2013). The application of pattern recognition in the automatic classification of microscopic rock images. Computers & Geosciences, 60, 126-133.
• Osowski, S. (2006). Sieci neuronowe do przetwarzania informacji [Neural networks for information processing]. Warszawa: Oficyna Wydawnicza Politechniki Warszawskiej.
• Ratajczak, T., Magiera, J., Skowroński, A., & Tumidajski, T. (1998). Ilościowa analiza mikroskopowa skał [The quantitative microscopic analysis of rocks]. Kraków: Wydawnictwo AGH.
• Skiba, M., & Młynarczuk, M. (2015a). Możliwości wykorzystania sztucznych sieci neuronowych w badaniach petrograficznych węgla kamiennego [The possibility of usage of artificial neural networks for the petrographic analysis of coal]. Ostrava 13.-15.10.2015. In 10th Czech and Polish Conference “Geology of coal basins” (pp. 131-137). Ostrava: Academy of Sciences of the Czech Republic. Institute of Geonics, Documenta Geonica 2015/1.
• Skiba, M., & Młynarczuk, M. (2015b). Możliwości wykorzystania sztucznych sieci neuronowych do identyfikacji macerałów grupy inertynitu [The possibility of using artificial neural networks to identification of inertinite macerals]. Prace Instytutu Mechaniki Górotworu PAN, 17(3-4), 91-97.
• Tadeusiewicz, R. (1993). Sieci neuronowe [Neural networks]. Warszawa: Akademicka Oficyna Wydawnicza.