A hybrid feature selection method for production condition recognition in froth flotation with noisy labels

Abstract Production condition recognition plays a major role in the froth flotation process control, and its accuracy has great influence on the performance of froth flotation. In order to improve the performance, lots of features are extracted from froth images; however, not all of these features are useful. There are some redundant and irrelevant features among them, which may increase the computational cost and the difficulty of training classifier, or even reduce the recognition accuracy. In order to resolve this issue, a feature selection method named mRMR-BSTA is proposed in this paper to find the best feature subset with most useful and less redundant features. This proposed method is comprised of two phases: the filter phase based on minimal-redundancy-maximal-relevance (mRMR) criterion and the wrapper phase based on binary state transition algorithm (BSTA), and it is applied to the production condition recognition in gold-antimony froth flotation. Least squares support vector machine (LSSVM) is applied to recognition and used as a black box to evaluate the quality of selected features in wrapper phase. Especially, for removing the noisy data with wrong labels caused by the subjectivity of workers, a preprocessing approach based on fuzzy C-means (FCM) is proposed in this paper. Finally, the most efficient feature subset in froth flotation is selected, including hue, mean of blue, relative red component, coarseness, and high frequency energy. The production condition is classified into eight classes with high accuracy successfully, and the effectiveness of the proposed method for production condition recognition in froth flotation is validated.

[1]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[2]  Chen Wang,et al.  Information Technology and Quantitative Management ( ITQM 2017 ) D-FCM : Density based fuzzy c-means cl stering algorithm with applicat on in medical image segmentatio , 2017 .

[3]  Xing Yan,et al.  Mid-term electricity market clearing price forecasting: A hybrid LSSVM and ARMAX approach , 2013 .

[4]  Marimuthu Palaniswami,et al.  Fuzzy c-Means Algorithms for Very Large Data , 2012, IEEE Transactions on Fuzzy Systems.

[5]  Kewei Cheng,et al.  Feature Selection , 2016, ACM Comput. Surv..

[6]  Samira Abbasgholizadeh Rahimi,et al.  Medical diagnosis of Rheumatoid Arthritis using data driven PSO-FCM with scarce datasets , 2017, Neurocomputing.

[7]  Xiao Chen,et al.  Multi-model soft measurement method of the froth layer thickness based on visual features , 2016 .

[8]  Changming Sun,et al.  Cell Segmentation Based on FOPSO Combined With Shape Information Improved Intuitionistic FCM , 2019, IEEE Journal of Biomedical and Health Informatics.

[9]  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.

[10]  Xiaojun Zhou,et al.  A Two-stage State Transition Algorithm for Constrained Engineering Optimization Problems , 2018 .

[11]  Minqiang Xu,et al.  A fault diagnosis scheme for planetary gearboxes using modified multi-scale symbolic dynamic entropy and mRMR feature selection , 2017 .

[12]  Keke Gai,et al.  An Empirical Study on Preprocessing High-Dimensional Class-Imbalanced Data for Classification , 2015, 2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium on Cyberspace Safety and Security, and 2015 IEEE 12th International Conference on Embedded Software and Systems.

[13]  Ahmad Taher Azar,et al.  Supervised hybrid feature selection based on PSO and rough sets for medical diagnosis , 2014, Comput. Methods Programs Biomed..

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

[15]  Xiaojun Zhou,et al.  A Statistical Study on Parameter Selection of Operators in Continuous State Transition Algorithm , 2018, IEEE Transactions on Cybernetics.

[16]  Xiaojun Zhou,et al.  Discrete state transition algorithm for unconstrained integer optimization problems , 2012, Neurocomputing.

[17]  Xiaojun Zhou,et al.  State Transition Algorithm , 2012, ArXiv.

[18]  Chong-Ho Choi,et al.  Input Feature Selection by Mutual Information Based on Parzen Window , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Weihua Gui,et al.  Recognition of the operational statuses of reagent addition using dynamic bubble size distribution in copper flotation process , 2013 .

[20]  Xiaojun Zhou,et al.  Optimal design of water distribution networks by a discrete state transition algorithm , 2013, ArXiv.

[21]  Kuo-Chen Chou,et al.  Prediction of Protein Domain with mRMR Feature Selection and Analysis , 2012, PloS one.

[22]  Jinping Liu,et al.  Color co-occurrence matrix based froth image texture extraction for mineral flotation , 2013 .

[23]  Chen Song,et al.  Process working condition recognition based on the fusion of morphological and pixel set features of froth for froth flotation , 2018, Minerals Engineering.

[24]  Xiaojun Zhou,et al.  A Novel Cognitively Inspired State Transition Algorithm for Solving the Linear Bi-Level Programming Problem , 2018, Cognitive Computation.

[25]  Xiaojun Zhou,et al.  A novel modularity-based discrete state transition algorithm for community detection in networks , 2019, Neurocomputing.

[26]  Ling He,et al.  An Improved FCM Clustering Method for Interval Data , 2010, RSKT.

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

[28]  Weihua Gui,et al.  Recognition of flooding and sinking conditions in flotation process using soft measurement of froth surface level and QTA , 2017 .

[29]  Weihua Gui,et al.  The Method of Reagent Control Based on Time Series Distribution of Bubble Size in a Gold‐Antimony Flotation Process , 2018 .

[30]  Xiaojun Zhou,et al.  Feature selection in froth flotation for production condition recognition , 2018 .

[31]  J. Roger,et al.  Application of LS-SVM to non-linear phenomena in NIR spectroscopy: development of a robust and portable sensor for acidity prediction in grapes , 2004 .

[32]  Xiaojun Zhou,et al.  A dynamic state transition algorithm with application to sensor network localization , 2015, Neurocomputing.

[33]  Yang Chun-hu,et al.  A discrete state transition algorithm for traveling salesman problem , 2013 .

[34]  Xiaojun Zhou,et al.  A Hybrid Feature Selection Method Based on Binary State Transition Algorithm and ReliefF , 2019, IEEE Journal of Biomedical and Health Informatics.

[35]  Xiaojun Zhou,et al.  Set-Point Tracking and Multi-Objective Optimization-Based PID Control for the Goethite Process , 2018, IEEE Access.

[36]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.