Abstract
Accurate classification and recognition of coal flotation froth is one of the key technologies for intelligent coal separation. At present, the coal flotation process relies on artificial recognition of froth features for adjusting the reagent dosage, which cannot realize the optimal control of the quality of the clean coal product and the cost of the reagents. Therefore, in this paper, it is proposed a method of froth image clustering with feature semi-supervision through selection and label information. It is mainly divided into two stages: offline clustering and online recognition. The offline stage is to preprocess the froth image under various reagent conditions, extract the morphology, colour and texture features, and select the multi-dimensional optimal froth image features. A small number of marked samples are introduced to optimize the Gaussian mixture model. The selected optimal features are integrated into the optimized Gaussian mixture model to construct a froth image clusterer with multi-dimensional optimal features and class labels. In the online stage, the real-time froth image features are input clusterer and compared with the cluster feature samples to identify the current reagents conditions, which is used as feedback information to guide the abnormal reagent conditions during the production process. The effect of the amount of supervision information and the quality of feature on clustering results is analyzed and compared through experiments. The application results show that this method can provide key technical support for the accurate control of the dosage of reagents and the quality of clean coal product in the coal flotation production process, reduce the cost of reagents and the number of production accidents, improve the economic benefits, and promote the development of coal flotation intelligence to a higher level.
Similar content being viewed by others
References
Wu C, Yang X, Xu D et al (2002) Study of a coal slurry flotation optimizing control system based on ash on-line measurement. High Technol Lett 13:85–90
Shi J, Zhu Z (2014) Study and application of flotation automatic dosing device. Coal Prep Technol 3:68–71
Xu C, Gui W, Yang C et al (2012) Flotation process fault detection using output PDF of bubble size distribution. Miner Eng 26:5–12
Backes A, Bruno O (2010) Shape classification using complex network and Multi-scale Fractal Dimension. Pattern Recognit Lett 31:44–51
Hosseini M, Shirazi H, Massinaei M et al (2015) Modeling the relationship between froth bubble size and flotation performance using image analysis and neural networks. Chem Eng Commun 202:911–919
Bonifazi G, Massacci P, Meloni A (2000) Prediction of complex sulfide flotation performances by a combined 3D fractal and colour analysis of the froths. Miner Eng 13:737–746
Bonifazi G, Massacci P, Meloni A (2002) A 3D froth surface rendering and analysis technique to characterize flotation processes. Int J Miner Process 64:153–161
Haralick R, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC 3:610–621
Ren H, Yang C, Zhou X et al (2011) Froth image feature weighted SVM based working condition recognition for flotation process. Chinese J Zhejiang Univ 45:2115–2119
Sun C, Wee W (1983) Neighboring gray level dependence matrix for texture classification. Comput Vis Graph Image Process 23:341–352
Zhao L, Peng T, Zhao L et al (2015) Fault condition recognition based on multi-scale texture features and embedding prior knowledge k-means for antimony flotation process. IFAC-Papers OnLine 28:864–870
Liu W, Lu M et al (2003) Extraction of textural feature and recognition of coal flotation froth. Chinese J Chem Indus 54:830–835
Peng X, Peng T, Zhao L et al (2016) Working condition recognition based on an improved NGLDM and interval data-based classifier for the antimony roughing process. Miner Eng 86:1–9
Xu D, Chen X, Xie Y et al (2015) Complex networks-based texture extraction and classification method for mineral flotation froth images. Miner Eng 83:105–116
Liu J (2013) Statistical modeling of froth images and its applications in the monitoring of the mineral flotation process. Ph.D. dissertation, Central South Univ, Hunan, China
Cheng C (2010) Classification of mineral flotation selected froth based on color and texture feature. M.S. thesis, Central South Univ, Hunan, China
Liu M, Tang Z, Wang X et al (2015) Performance recognition of antimony flotation based on multi-information fusion and extension theory. J Cent South Univ 46:4512–4520
Raghavan H, Madani O, Jones R (2005) Interactive feature selection. In: 19th Interna-tional Joint Conference on Artificial Intelligence (IJCAI), pp 841–846
Geraldo N, Ricardo M, Eduardo R et al (2015) Interactive textual feature selection for consensus clustering. Patt Recog Lett 52:25–31
Hu Y, Evangelos E, James B (2011) Interactive feature selection for document clustering. In: Proceedings of the 2011 ACM Symposium on Applied Computing (SAC’11), pp 1143–1150
Hu Y, Evangelos E, James B (2014) Interactive document clustering with feature supervision through reweighting. Intell Data Anal 18(4):561–581
Gui W, Yang C, Xu D et al (2013) Machine-vision-based online measuring and controlling technologies for mineral flotation-a review. Acta Autom Sin 39:1879–1888
Wang Z (2010) Research on the classification method of remote sensing images based on texture and spectral information fusion. M.S. thesis, Xidian Univ, Xian, China
Peng H, Long F, Ding C (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27:1226–1238
Bae J, Helldin T, Riveiro M et al (2020) Interactive clustering: a comprehensive review. ACM Comput Surv 53(1):1–39
Babaee M, Bahmanyar R, Rigoll G et al (2014) Interactive clustering forSARimage understanding. In: Proceedings of the 10th European Conference on Synthetic Aperture Radar (EUSAR’14), pp 1–4
Kern M, Lex A, Gehlenborg N et al (2017) Interactive visual exploration and refinement of cluster assignments. BMC Bioinform 18(1):406
Lai H, Visani M, Boucher A et al (2014) A new interactive semi-supervised clustering model for large image database indexing. Pattern Recogn Lett 37:94–106
Long T, Linsen L (2009) MultiClusterTree: interactive visual exploration of hierarchical clusters in multidimensional multivariate data. Comput Graph Forum 28:23–830
Choo J, Lee C, Reddy C, Park H (2013) UTOPIAN: user-driven topic modeling based on interactive nonnegative matrix factorization. IEEE Trans Vis Comput Graph 19(12):1992–2001
Xiong C, Johnson D, Corso J (2017) Active clustering with model-based uncertainty reduction. IEEE Trans Pattern Anal Mach Intell 39(1):5–17
Zhou C, Frankowski D, Ludford P et al (2004) Discovering personal gazetteers: An interactive clustering approach. In: Proceedings of the 12th Annual ACM International Workshop on Geographic Information Systems (GIS’04), pp 266–273
Andrienko G, Andrienko N (2010) Interactive cluster analysis of diverse types of spatiotemporal data. ACM SIGKDD Explor Newslett 11(2):19–28
Sato Y, Iwayama M (2009) Interactive constrained clustering for patent document set. In: Proceedings of the 2nd International Workshop on Patent Information Retrieval (PaIR’09), pp 17–20
Okabe M, Yamada S (2011) An interactive tool for human active learning in constrained clustering. J Emerg Technol Web Intell 3(1):20–27
Müller E, Assent I, Krieger R et al (2008) Morpheus: Interactive exploration of subspace clustering. In: Proceeding of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 1089–1092
Berthold M, Wiswedel B, Patterson D (2002) Neighborgram clustering Interactive exploration of cluster neighborhoods. In: Proceedings of the 2002 IEEE International Conference on Data Mining, pp 581–584
Mukhopadhyay A, Maulik U, Bandyopadhyay S (2013) An interactive approach to multiobjective clustering of gene expression patterns. IEEE Trans Biomed Eng 60(1):35–41
Lee H, Kihm J, Choo J et al (2012) iVisClustering: an interactive visual document clustering via topic modeling. Comput Graph Forum 31(3pt3):1155–1164
Xu P, Cao N, Qu H et al (2016) Interactive visual co-cluster analysis of bipartite graphs. In: Proceedings of the 2016 IEEE Pacific Visualization Symposium (PacificVis’16), pp 32–39
Gruźdź A, Ihnatowicz A et al (2006) Interactive gene clustering—a case study of breast cancer microarray data. Inf Syst Front 8(1):21–27
Celler B, Le P, Argha A et al (2020) GMM-HMM-based blood pressure estimation using time-domain features. IEEE Trans Instrum Meas 69(6):3631–3641
Gorbach T, Lundquist A, Luna X et al (2020) A hierarchical Bayesian mixture model approach for analysis of resting-state functional brain connectivity: an alternative to thresholding. Brain Connectivity 10(5):1–53
Leng Y, Xu X, Qi G (2013) Combining active learning and semi-supervised learning to construct SVM classifier. Knowl-Based Syst 44:121–131
Gong C, Tao D, Maybank S et al (2016) Multi-modal curriculum learning for semi-supervised image classification. IEEE Trans Image Process 25:3249–3260
Qin Y, Ding S, Wang L et al (2019) Research progress on semi-supervised clustering. Cognit Comput 11:599–621
Luo S, Zheng B, Ye X (2009) Image segment based on the self-adaptive threshold EM and GMM algorithm. Acta Photo Sini 38(6):1581–1585
DeGroot M, Schervish M (2002) Probability and statistics. J Roy Stat Soc. Ser A (Statistics in Society) 151(3):385–418
Dukkipati A, Ghoshdastidar D, Krishnan J (2016) Mixture modeling with compact support distributions for unsupervised learning. In: The International Joint Conference on Neural Networks (IJCNN), pp 2706-2713
Liu S, Hu J, Hao S et al (2016) Improved EM method for internet traffic classification. In: The 8th International Conference on Knowledge and Smart Technology (KST), pp 13–17
Zarie M, Jahedsaravani A, Massinaei M (2020) Flotation froth image classification using convolutional neural networks. Miner Eng 155:106443
Wang Y, Sun B, Zhang R et al (2018) Sulfur flotation performance recognition based on hierarchical classification of local dynamic and static froth features. IEEE Access 6:14019–14029
Fu Y, Aldrich C (2018) Using convolutional neural networks to develop state-of-the-art flotation froth image sensors. IFAC-Papers OnLine 51(21):152–157
Acknowledgements
This work is supported in part by the Youth Fund of the Science and Technology Plan Research Project of Shanxi Province, China, under Grant 201801D221358.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cao, W., Wang, R., Fan, M. et al. Froth image clustering with feature semi-supervision through selection and label information. Int. J. Mach. Learn. & Cyber. 12, 2499–2516 (2021). https://doi.org/10.1007/s13042-021-01333-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-021-01333-5