Abstract
ABSTRACTThe rock near-infrared spectrum contains information of its composition and structure. The interpretation of rock near-infrared spectrum is one of the important approaches in the qualitative and quantitative analyses of the alteration minerals in rock. The rock near-infrared spectra are classified using optimized fuzzy C-means clustering algorithm, and the main mineral composition is obtained for different rock samples through the analysis of cluster centers. The minimum Spectral Correlation Coefficient is used as the objective function to classify the simulation data. In this study, the classification method was first tested for parameter setting using simulation data, which was the mixture of several standard mineral spectra quantified in terms of reflectivity in the near-infrared band. Classification accuracies under different fuzzy index values are compared. When the fuzzy index value is 1.5, the classification accuracy of the simulation samples is 83%. The initial values of different cluster centers were shown to affect the classification result. In the practical application, the initial values of cluster centers need to be rationally chosen based on the knowledge of mineral spectroscopy. This method is applied in the clustering analysis of the rock near-infrared spectra, which were also quantified in terms of reflectivity in the near-infrared band. These actual rock near-infrared spectra were measured by a spectrometer, while the classification results were compared with X-ray diffraction analysis to show the effectiveness of our algorithm. Our study has shown that, with the optimized fuzzy C-means clustering algorithm, the interpretation of rock near-infrared spectra can help us obtain information of the mineral composition and structure more effectively in terms of accuracy and speed. This method is suitable for the rapid processing of massive rock near-infrared spectra and may become an important technology in geological survey and geological prospecting.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
