Froth image clustering with feature semi-supervision through selection and label information

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.

[1]  A. Jahedsaravani,et al.  Flotation froth image classification using convolutional neural networks , 2020 .

[2]  Shengnan Hao,et al.  Improved EM method for internet traffic classification , 2016, 2016 8th International Conference on Knowledge and Smart Technology (KST).

[3]  André Ricardo Backes,et al.  Shape classification using complex network and Multi-scale Fractal Dimension , 2010, Pattern Recognit. Lett..

[4]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[5]  Yanru Wang,et al.  Research Progress on Semi-Supervised Clustering , 2019, Cognitive Computation.

[6]  Weihua Gui,et al.  Flotation process fault detection using output PDF of bubble size distribution , 2012 .

[7]  Chris Aldrich,et al.  Using Convolutional Neural Networks to Develop State-of-the-Art Flotation Froth Image Sensors , 2018 .

[8]  Branko G. Celler,et al.  GMM-HMM-Based Blood Pressure Estimation Using Time-Domain Features , 2020, IEEE Transactions on Instrumentation and Measurement.

[9]  Gennady L. Andrienko,et al.  Interactive cluster analysis of diverse types of spatiotemporal data , 2010, SKDD.

[10]  Ira Assent,et al.  Morpheus: interactive exploration of subspace clustering , 2008, KDD.

[11]  James Blustein,et al.  Interactive document clustering with feature supervision through reweighting , 2014, Intell. Data Anal..

[12]  Lars Linsen,et al.  MultiClusterTree: Interactive Visual Exploration of Hierarchical Clusters in Multidimensional Multivariate Data , 2009, Comput. Graph. Forum.

[13]  Gui Wei-hua,et al.  Machine-vision-based Online Measuring and Controlling Technologies for Mineral Flotation--A Review , 2013 .

[14]  Ricardo M. Marcacini,et al.  Interactive textual feature selection for consensus clustering , 2015, Pattern Recognit. Lett..

[15]  William G. Wee,et al.  Neighboring gray level dependence matrix for texture classification , 1982, Comput. Graph. Image Process..

[16]  Giuseppe Bonifazi,et al.  A 3D froth surface rendering and analysis technique to characterize flotation processes , 2002 .

[17]  Weihua Gui,et al.  Working condition recognition based on an improved NGLDM and interval data-based classifier for the antimony roughing process , 2016 .

[18]  Lars Nyberg,et al.  A Hierarchical Bayesian Mixture Model Approach for Analysis of Resting-State Functional Brain Connectivity: An Alternative to Thresholding , 2020, Brain Connect..

[19]  Yan Leng,et al.  Combining active learning and semi-supervised learning to construct SVM classifier , 2013, Knowl. Based Syst..

[20]  Walter L. Smith.  Probability and Statistics , 1959, Nature.

[21]  Göran Falkman,et al.  Interactive Clustering , 2020, ACM Comput. Surv..

[22]  John T. Stasko,et al.  Interactive visual co-cluster analysis of bipartite graphs , 2016, 2016 IEEE Pacific Visualization Symposium (PacificVis).

[23]  Dominik Slezak,et al.  Interactive Gene Clustering—A Case Study of Breast Cancer Microarray Data , 2006, Inf. Syst. Frontiers.

[24]  M. Massinaei,et al.  Modeling the Relationship between Froth Bubble Size and Flotation Performance Using Image Analysis and Neural Networks , 2015 .

[25]  Giuseppe Bonifazi,et al.  Prediction of complex sulfide flotation performances by a combined 3D fractal and colour analysis of the froths , 2000 .

[26]  Michael R. Berthold,et al.  Neighborgram clustering. Interactive exploration of cluster neighborhoods , 2002, 2002 IEEE International Conference on Data Mining, 2002. Proceedings..

[27]  Yalin Wang,et al.  Sulfur Flotation Performance Recognition Based on Hierarchical Classification of Local Dynamic and Static Froth Features , 2018, IEEE Access.

[28]  Ambedkar Dukkipati,et al.  Mixture modeling with compact support distributions for unsupervised learning , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[29]  James Blustein,et al.  Interactive feature selection for document clustering , 2011, SAC.

[30]  YE Xin-quan.  Image Segment Based on the Self-adaptive Threshold EM and GMM Algorithm , 2009 .

[31]  John T. Stasko,et al.  iVisClustering: An Interactive Visual Document Clustering via Topic Modeling , 2012, Comput. Graph. Forum.

[32]  Wei Liu,et al.  Multi-Modal Curriculum Learning for Semi-Supervised Image Classification , 2016, IEEE Transactions on Image Processing.

[33]  Yusuke Sato,et al.  Interactive constrained clustering for patent document set , 2009, PaIR@CIKM.

[34]  Alexander Lex,et al.  Interactive visual exploration and refinement of cluster assignments , 2017, BMC Bioinformatics.

[35]  Muriel Visani,et al.  A new interactive semi-supervised clustering model for large image database indexing , 2014, Pattern Recognit. Lett..

[36]  Jaegul Choo,et al.  UTOPIAN: User-Driven Topic Modeling Based on Interactive Nonnegative Matrix Factorization , 2013, IEEE Transactions on Visualization and Computer Graphics.

[37]  Shashi Shekhar,et al.  Discovering personal gazetteers: an interactive clustering approach , 2004, GIS '04.

[38]  Ujjwal Maulik,et al.  An Interactive Approach to Multiobjective Clustering of Gene Expression Patterns , 2013, IEEE Transactions on Biomedical Engineering.

[39]  Yan Feng.  Froth image feature weighted SVM based working condition recognition for flotation process , 2011 .

[40]  Seiji Yamada,et al.  An Interactive Tool for Human Active Learning in Constrained Clustering , 2011 .

[41]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  Tao Peng,et al.  Fault Condition Recognition Based on Multi-scale Texture Features and Embedding Prior Knowledge K-means for Antimony Flotation Process , 2015 .

[43]  Hema Raghavan,et al.  InterActive Feature Selection , 2005, IJCAI.

[44]  Chen Xiao,et al.  Complex networks-based texture extraction and classification method for mineral flotation froth images , 2015 .

[45]  Jason J. Corso,et al.  Active Clustering with Model-Based Uncertainty Reduction , 2014, IEEE transactions on pattern analysis and machine intelligence.