An Improved Hybrid Feature Selection Algorithm for Electric Charge Recovery Risk

In order to extract more information that affects customer arrears behavior, the feature extraction method is used to extend the low-dimensional features to the high-dimensional features for the warning problem of user arrears risk model of electric charge recovery (ECR). However, there are many irrelevant or redundant features in data, which affect prediction accuracy. In order to reduce the dimension of the feature and improve the prediction result, an improved hybrid feature selection algorithm is proposed, integrating nonlinear inertia weight binary particle swarm optimization with shrinking encircling and exploration mechanism (NBPSOSEE) with sequential backward selection (SBS), namely, NBPSOSEE-SBS, for selecting the optimal feature subset. NBPSOSEE-SBS can not only effectively reduce the redundant or irrelevant features from the feature subset selected by NBPSOSEE but also improve the accuracy of classification. The experimental results show that the proposed NBPSOSEE-SBS can effectively reduce a large number of redundant features and stably improve the prediction results in the case of low execution time, compared with one state-of-the-art optimization algorithm, and seven well-known wrapper-based feature selection approaches for the risk prediction of ECR for power customers.

[1]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[3]  Y. Alinejad-Beromi,et al.  Optimal PMU placement for power system observability using binary particle swarm optimization and considering measurement redundancy , 2011, Expert Syst. Appl..

[4]  Rommel N. Carvalho,et al.  Predicting Recovery of Credit Operations on a Brazilian Bank , 2016, 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA).

[5]  Russell C. Eberhart,et al.  A discrete binary version of the particle swarm algorithm , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[6]  João Miguel da Costa Sousa,et al.  Modified binary PSO for feature selection using SVM applied to mortality prediction of septic patients , 2013, Appl. Soft Comput..

[7]  Gokul S. Krishnan,et al.  A novel GA-ELM model for patient-specific mortality prediction over large-scale lab event data , 2019, Appl. Soft Comput..

[8]  Yonghong Xie,et al.  Arrears prediction for electricity customer through Wgan-Gp , 2017, 2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC).

[9]  Seyed Mohammad Mirjalili,et al.  Whale optimization approaches for wrapper feature selection , 2018, Appl. Soft Comput..

[10]  Qasem Al-Tashi,et al.  Feature Selection Method Based on Grey Wolf Optimization for Coronary Artery Disease Classification , 2018, Advances in Intelligent Systems and Computing.

[11]  Kusum Deep,et al.  A Modified Binary Particle Swarm Optimization for Knapsack Problems , 2012, Appl. Math. Comput..

[12]  Yaojin Lin,et al.  Feature selection based on quality of information , 2017, Neurocomputing.

[13]  Mesut Gündüz,et al.  JayaX: Jaya algorithm with xor operator for binary optimization , 2019, Appl. Soft Comput..

[14]  Yuansheng Huang,et al.  Research of evaluating credit-risk in power enterprise based on SVM and VIKOR method , 2008, 2008 IEEE International Conference on Industrial Engineering and Engineering Management.

[15]  Jing-min Wang,et al.  Application of Data Mining in Arrear Risks Prediction of Power Customer , 2008, 2008 International Symposium on Knowledge Acquisition and Modeling.

[16]  Qing Wang,et al.  A filter-based bare-bone particle swarm optimization algorithm for unsupervised feature selection , 2019, Applied Intelligence.

[17]  Li-Yeh Chuang,et al.  Chaotic Binary Particle Swarm Optimization for Feature Selection using Logistic Map , 2008 .

[18]  Suren Chen,et al.  Enhancing resilience of interdependent traffic-electric power system , 2019, Reliab. Eng. Syst. Saf..

[19]  Hossam M. Zawbaa,et al.  Feature selection approach based on whale optimization algorithm , 2017, 2017 Ninth International Conference on Advanced Computational Intelligence (ICACI).

[20]  Stjepan Oreski,et al.  Genetic algorithm-based heuristic for feature selection in credit risk assessment , 2014, Expert Syst. Appl..

[21]  Li-Yeh Chuang,et al.  Boolean binary particle swarm optimization for feature selection , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[22]  Andries P. Engelbrecht,et al.  Set based particle swarm optimization for the feature selection problem , 2019, Eng. Appl. Artif. Intell..

[23]  Bjoern H. Menze,et al.  A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data , 2009, BMC Bioinformatics.

[24]  Strother H. Walker,et al.  Estimation of the probability of an event as a function of several independent variables. , 1967, Biometrika.

[25]  Stephen C. Adams,et al.  A survey of feature selection methods for Gaussian mixture models and hidden Markov models , 2019, Artificial Intelligence Review.

[26]  Mengjie Zhang,et al.  A New Representation in PSO for Discretisation-Based Feature Selection , 2017 .

[27]  Andries Petrus Engelbrecht,et al.  Binary artificial bee colony optimization , 2011, 2011 IEEE Symposium on Swarm Intelligence.

[28]  Jinghua Liu,et al.  Feature selection for multi-label learning with missing labels , 2019, Applied Intelligence.

[29]  Mohamed Elhoseny,et al.  Feature selection based on artificial bee colony and gradient boosting decision tree , 2019, Appl. Soft Comput..

[30]  Meng Lu,et al.  Embedded feature selection accounting for unknown data heterogeneity , 2019, Expert Syst. Appl..

[31]  Kuang Hong,et al.  Credit evaluation for mobile customers using artificial immune algorithms , 2008, 2008 7th World Congress on Intelligent Control and Automation.

[32]  Qing Wu,et al.  A Feature Selection Method Based on Hybrid Improved Binary Quantum Particle Swarm Optimization , 2019, IEEE Access.

[33]  Licheng Jiao,et al.  Evolving deep convolutional neural networks by quantum behaved particle swarm optimization with binary encoding for image classification , 2019, Neurocomputing.

[34]  Shengsheng Wang,et al.  Feature selection with improved binary artificial bee colony algorithm for microarray data , 2019 .

[35]  Yang Hong.  Predication of Default Probability of Clients’ Electricity Charges Arrears Based on Logistic Regression Model , 2007 .

[36]  Ali Broumandnia,et al.  Image steganalysis using improved particle swarm optimization based feature selection , 2018, Applied Intelligence.

[37]  Wei Wang,et al.  Prediction of default probability of clients' electricity charge arrears , 2008, 2008 IEEE International Conference on Service Operations and Logistics, and Informatics.

[38]  Li-Yeh Chuang,et al.  Gene selection and classification using Taguchi chaotic binary particle swarm optimization , 2011, Expert Syst. Appl..

[39]  Mohamed A. Tawhid,et al.  Feature selection based on rough set approach, wrapper approach, and binary whale optimization algorithm , 2020, Int. J. Mach. Learn. Cybern..

[40]  Juan Luis Fernández-Martínez,et al.  A Brief Historical Review of Particle Swarm Optimization (PSO) , 2012 .

[41]  Wang Tao,et al.  Study on Tariff Risk Early Warning of Electric Power Users Based on PSO-SVM Algorithm , 2018, 2018 International Conference on Big Data and Artificial Intelligence (BDAI).

[42]  Siddhartha Bhattacharyya,et al.  S-shaped Binary Whale Optimization Algorithm for Feature Selection , 2019 .

[43]  Zhile Yang,et al.  A Novel Binary Jaya Optimization for Economic/Emission Unit Commitment , 2018, 2018 IEEE Congress on Evolutionary Computation (CEC).

[44]  Andries Petrus Engelbrecht,et al.  A parameter-free particle swarm optimization algorithm using performance classifiers , 2019, Inf. Sci..

[45]  Alper Ekrem Murat,et al.  A discrete particle swarm optimization method for feature selection in binary classification problems , 2010, Eur. J. Oper. Res..

[46]  Geng Lin,et al.  A hybrid binary particle swarm optimization with tabu search for the set-union knapsack problem , 2019, Expert Syst. Appl..

[47]  Xiaodong Li,et al.  An Analysis of the Inertia Weight Parameter for Binary Particle Swarm Optimization , 2016, IEEE Transactions on Evolutionary Computation.

[48]  Manu Vardhan,et al.  A New Hybrid Feature Subset Selection Framework Based on Binary Genetic Algorithm and Information Theory , 2019, Int. J. Comput. Intell. Appl..

[49]  Kun Guo,et al.  Design and Implementation of Electric Charge Arrears Prediction System , 2015, 2015 12th Web Information System and Application Conference (WISA).

[50]  Dilip Kumar Pratihar,et al.  Phenomenological model-based study on electron beam welding process, and input-output modeling using neural networks trained by back-propagation algorithm, genetic algorithms, particle swarm optimization algorithm and bat algorithm , 2017, Applied Intelligence.

[51]  Li-Yeh Chuang,et al.  Chaotic maps based on binary particle swarm optimization for feature selection , 2011, Appl. Soft Comput..

[52]  Heiko Paulheim,et al.  Local and global feature selection for multilabel classification with binary relevance , 2017, Artificial Intelligence Review.

[53]  Chih-Cheng Hung,et al.  A Multi-objective hybrid filter-wrapper evolutionary approach for feature selection , 2018, Memetic Comput..

[54]  Hao Chen,et al.  A Heuristic Feature Selection Approach for Text Categorization by Using Chaos Optimization and Genetic Algorithm , 2013 .

[55]  Gan Zheng,et al.  Distributed Foresighted Energy Management in Smart-Grid-Powered Cellular Networks , 2019, IEEE Transactions on Vehicular Technology.

[56]  Yudong Zhang,et al.  Binary PSO with mutation operator for feature selection using decision tree applied to spam detection , 2014, Knowl. Based Syst..

[57]  Maurice Clerc,et al.  The particle swarm - explosion, stability, and convergence in a multidimensional complex space , 2002, IEEE Trans. Evol. Comput..

[58]  Nihat Yilmaz,et al.  A hybrid breast cancer detection system via neural network and feature selection based on SBS, SFS and PCA , 2012, Neural Computing and Applications.

[59]  Pei-Chann Chang,et al.  A novel complex network community detection approach using discrete particle swarm optimization with particle diversity and mutation , 2019, Appl. Soft Comput..

[60]  D. Cox.  The Regression Analysis of Binary Sequences , 1958 .

[61]  Aboul Ella Hassanien,et al.  Binary grey wolf optimization approaches for feature selection , 2016, Neurocomputing.

[62]  Taha Mokfi,et al.  Evaluation and selection of clustering methods using a hybrid group MCDM , 2019, Expert Syst. Appl..

[63]  Canbing Li,et al.  Research and application of subtilized customer clustering algorithm in power marketing , 2017, 2017 IEEE Conference on Energy Internet and Energy System Integration (EI2).

[64]  Zhen Yang,et al.  Application of EOS-ELM With Binary Jaya-Based Feature Selection to Real-Time Transient Stability Assessment Using PMU Data , 2017, IEEE Access.

[65]  Carlos A. Coello Coello,et al.  Handling multiple objectives with particle swarm optimization , 2004, IEEE Transactions on Evolutionary Computation.