Abstract
Aiming at the problem of the absence of effective coal–rock recognition methods during top coal caving, we propose a new multi-class feature selection approach to detecting full coal falling/30% rock mixture falling/50% rock mixture falling/full rock falling recognition during caving. The method is based on vibration and acoustic sensors fixed under the tail beam of the hydraulic as well as signal processing techniques. Distinctive vibration and acoustic signals generate during caving that depend on the state of coal–rock mixed. Via a contribution threshold \(\lambda_{0}\) and classification accuracy P, the optimal combination of feature attributes can be automatically and sequentially decided by using the multi-class F-score (MF-Score) feature reduction approach proposed in this paper. The main idea of the MF-Score is to construct the within-class scatter matrix with a membership function based on the aggregation degree within the sample. The support vector machine classifier has been employed to test the proposed algorithm and identified the state of the coal–rock mixed. The contribution threshold is readjusted according to the calculated feature selection criterion J(k) and user requirement, and then a feedback loop is developed to keep the dynamic of the samples. Experimental results show the good generality and effectiveness of this new approach.
Similar content being viewed by others
References
Cheng GM, Huang K, Yan FZh et al (2003) Methane control for mechanised longwall top-coal caving faces in high gas content mines. Min Technol 112(3):141–148
Liu W, He K, Gao Q, Liu CY (2014) Application of EMD-based SVD and SVM to coal–gangue interface detection. J Appl Math 2014:1–6
Liu W, Yan YH, Wang RL (2011) Application of Hilbert–Huang transform and SVM to coal gangue interface detection. J Comput 6(6):1262–1269
Wang BP, Wang ZC, Wang YJ (2012) Application of Hilbert marginal spectrum to coal–rock interface recognition. Adv Mater Res 569:70–73
Wang BP, Wang ZC, Li YX (2011) Application of wavelet packet energy spectrum in coal–rock interface recognition. Key Eng Mater 474–476:1103–1106
Li YM, Liu EM, Xue GH, Wu M (2014) Coal–rock interface identification method based on dimensionless parameters and support vector machine. Appl Mech Mater 716–717:843–847
Xu JK, Wang ZC, Zhang WZh (2013) Coal–rock interface recognition based on MFCC and neural network. Int J Signal Process Image Process Pattern Recogn 6(4):191–200
Sun JY (2007) Iterative RELIEF for feature weighting: algorithms, theories, and applications. IEEE Trans Pattern Anal Mach Intell 29(6):1035–1051
Li Y, Simon CK, Sankar KP (2006) Combining feature reduction and case selection in building CBR classifiers. IEEE Trans Knowl Data Eng 18(3):415–429
Liu YH (2009) Feature extraction and dimensionality reduction for mass spectrometry data. Comput Biol Med 39:818–823
Mwangi B, Tian TS, Soares JC (2014) A review of feature reduction techniques in neuroimaging. Neuroinformatics 12(2):229–244
Zhao GD, Wu Y, Chen FQ, Zhang JM (2015) Effective feature selection using feature vector graph for classification. Neurocomputing 151:376–389
Jolliffe IT (1986) Principal component analysis. Spriger, New York
Belhumeur PN, Hespanha JP, Kriegman DJ (1997) Eigenfaces versus fisherfaces: recognition using class specific linear projection. IEEE Trans Pattern Anal Mach Intell 19(7):711–720
Greenberg BG, Wells HB (1963) Linear discriminant analysis in perinatal mortality. Am J Public Health Nations Health 53:594–602
Cox T, Cox M (1994) Multidimensional scaling. Chapman & Hall, London
Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(22):2323–2326
Goldberg Y, Ritov Y (2012) Theoretical analysis of LLE based on its weighting step. J Comput Graph Stat 21(2):380–393
Tenenbaum JB, Silva V, Langford JC (2000) A global geometric framework for nonlinear dimensionality reduction. Science 290(22):2319–2323
Schölkopf B, Smola A, Muller K (1998) Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput 10:1299–1319
Mika S, Ratsch G, Weston J, Schölkopf B, Muller KR (1999) Fisher discriminant analysis with kernels. IEEE Neural Netw Signal Process 9:41–48
Park CH, Park H (2005) Nonlinear discriminant analysis using kernel functions and the generalized singular value decomposition. SIAM J Matrix Anal Appl 27(1):87–102
Golub TR, Slonimetc DK et al (1999) Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science 286(15):531–537
Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46:389–422
Chen YW, Lin CJ (2006) Combining SVMs with various feature selection strategies. In: Guyon I, Nikravesh M, Gunn S, Zadeh LA (eds) Feature extraction, Springer, Berlin, Heidelberg, pp 315–324
Kemal P, Salih G (2009) A new feature selection method on classification of medical datasets: kernel F-score feature selection. Expert Syst Appl 36:10367–10373
Salih G, Kemal P, Yosunkaya S (2010) Multi-class f-score feature selection approach to classification of obstructive sleep apnea syndrome. Expert Syst Appl 37:998–1004
Tsujinishi D, Abe S (2003) Fuzzy least squares support vector machines for multiclass problems. Neural Netw 16(5):785–792
Huang HP, Liu YH (2002) Fuzzy support vector machines for pattern recognition and data mining. Int J Fuzzy Syst 4(3):826–835
Abe S (2015) Fuzzy support vector machines for multilabel classification. Pattern Recogn 48:2110–2117
An WJ, Liang MJ (2013) Fuzzy support vector machine based on within-class scatter for classification problems with outliers or noises. Neurocomputing 110:101–110
Mowrey GL (1988) A new approach to coal interface detection: the in-seam seismic technique. IEEE Trans Ind Appl 24(4):660–665
Gaci S (2014) The use of wavelet-based denoising techniques to enhance the first-arrival picking on seismic traces. IEEE Trans Geosci Remote Sens 52(8):4558–4563
Song LY, Chen P, Wang HQ (2014) Automatic decision method of optimum symptom parameters and frequency bands for intelligent machinery diagnosis: application to condition diagnosis of centrifugal pump system. ADV Mech Eng 2014:1–13
Picone JW (1993) Signal modeling techniques in speech recognition. Proc IEEE 81(9):1215–1247
Zhai GF, Chen JB, Li Ch, Wang GT (2015) Pattern recognition approach to identify loose particle material based on modified MFCC and HMMs. Neural Comput 155:135–145
Massar ML, Fickus M, Bryan E, Petkie DT (2011) Fast computation of spectral centroids. Adv Comput Math 35(1):83–97
Aliouane L, Ouadfeul SA (2014) Heterogeneities analysis using the generalized fractal dimensions and the continuous wavelet transform. Application to the KTB boreholes. Arab J Geosci 7(8):2959–2967
Li Y et al (2010) Thirty cases analysis of MATLAB neural network. BUAA Press, Beijing
Acknowledgements
The authors gratefully thank anonymous reviewers for their valuable comments to improve the paper quality. This work was supported by Project of Natural Science Foundation of Shandong Province, China under Grant No. ZR2015EM042.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Song, Q., Jiang, H., Zhao, X. et al. An automatic decision approach to coal–rock recognition in top coal caving based on MF-Score. Pattern Anal Applic 20, 1307–1315 (2017). https://doi.org/10.1007/s10044-017-0618-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-017-0618-7