Particle swarm optimization for bandwidth determination and feature selection of kernel density estimation based classifiers in diagnosis of breast cancer

Graphical abstractDisplay Omitted HighlightsA PSO-KDE model is proposed to diagnosis of breast cancer.PSO is used to determine bandwidth and select feature subset in KDE based classifier.PSO-KDE solves the multiple criteria problem using two single objective functions.The aim is to minimize the number of features and the classification error. Machine learning techniques can be used in diagnosis of breast cancer to help pathologists and physicians for decision making process. Kernel density estimation is a popular non-parametric method which can be applied for the estimation of data in many diverse applications. Selection of bandwidth and feature subset in kernel density estimator significantly influences the classification performance. In this paper, a PSO-KDE model is proposed that hybridize the particle swarm optimization (PSO) and non-parametric kernel density estimation (KDE) based classifier to diagnosis of breast cancer. In the proposed model, particle swarm optimization is used to simultaneously determine the kernel bandwidth and select the feature subset in the kernel density estimation based classifier. Classification performance and the number of selected features are the criteria used to design the objective function of PSO-KDE. The performance of the PSO-KDE is examined on Wisconsin Breast Cancer Dataset (WBCD) and Wisconsin Diagnosis Breast Cancer Database (WDBC) using classification accuracy, sensitivity and specificity. Experimental results demonstrate that the proposed model has better average performance than GA-KDE model in diagnosis of breast cancer.

[1]  Salman Mohagheghi,et al.  Particle Swarm Optimization: Basic Concepts, Variants and Applications in Power Systems , 2008, IEEE Transactions on Evolutionary Computation.

[2]  Nasser Ghasem-Aghaee,et al.  Text feature selection using ant colony optimization , 2009, Expert Syst. Appl..

[3]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[4]  Debao Chen,et al.  An improved cooperative particle swarm optimization and its application , 2011, Neural Computing and Applications.

[5]  Pasi Luukka,et al.  Similarity classifier with generalized mean applied to medical data , 2006, Comput. Biol. Medicine.

[6]  P. Yaghmaei,et al.  Immunohistochemical Assessment of p53 Protein and its Correlation with Clinicopathological Characteristics in Breast Cancer Patients , 2014 .

[7]  O L Mangasarian,et al.  Indeterminate fine‐needle aspiration of the breast , 1997, Cancer.

[8]  V. Sadasivam,et al.  An integrated PSO for parameter determination and feature selection of ELM and its application in classification of power system disturbances , 2015, Appl. Soft Comput..

[9]  B. Silverman.  Density estimation for statistics and data analysis , 1986 .

[10]  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..

[11]  Mengjie Zhang,et al.  A multi-objective particle swarm optimisation for filter-based feature selection in classification problems , 2012, Connect. Sci..

[12]  Dursun Delen,et al.  Predicting breast cancer survivability: a comparison of three data mining methods , 2005, Artif. Intell. Medicine.

[13]  Dean J. Krusienski,et al.  Nonparametric density estimation based independent component analysis via particle swarm optimization , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[14]  Yılmaz Kaya.  A new intelligent classifier for breast cancer diagnosis based on rough set and extreme learning machine: RS+ELM. TurkishJournal of Electrical Engineering and Computer Sciences. (2013) 21: 2079 – 2091. , 2013 .

[15]  William Nick Street,et al.  Breast Cancer Diagnosis and Prognosis Via Linear Programming , 1995, Oper. Res..

[16]  Parameswaran Ramachandran,et al.  Adaptive bandwidth kernel density estimation for next-generation sequencing data , 2013, BMC Proceedings.

[17]  A. B. M. Shawkat Ali,et al.  Computational intelligence for microarray data and biomedical image analysis for the early diagnosis of breast cancer , 2012, Expert Syst. Appl..

[18]  Xu Zhou,et al.  Parallel hybrid PSO with CUDA for lD heat conduction equation , 2015 .

[19]  Kemal Polat,et al.  A new hybrid method based on fuzzy-artificial immune system and k-nn algorithm for breast cancer diagnosis , 2007, Comput. Biol. Medicine.

[20]  J. Faraway,et al.  Bootstrap choice of bandwidth for density estimation , 1990 .

[21]  Uneb Gazder,et al.  Factors Affecting Performance of Parametric and Non-parametric Models for Daily Traffic Forecasting , 2014, ANT/SEIT.

[22]  D. W. Scott,et al.  Biased and Unbiased Cross-Validation in Density Estimation , 1987 .

[23]  Dimitrios Gunopulos,et al.  Feature selection for the naive bayesian classifier using decision trees , 2003, Appl. Artif. Intell..

[24]  Verónica Bolón-Canedo,et al.  A review of feature selection methods on synthetic data , 2013, Knowledge and Information Systems.

[25]  Zhifei Zhang,et al.  International Journal of Approximate Reasoning Diverse Reduct Subspaces Based Co-training for Partially Labeled Data , 2022 .

[26]  Hans-Peter Seidel,et al.  Nonparametric Density Estimation with Adaptive, Anisotropic Kernels for Human Motion Tracking , 2007, Workshop on Human Motion.

[27]  Nasser Ghasem-Aghaee,et al.  A novel ACO-GA hybrid algorithm for feature selection in protein function prediction , 2009, Expert Syst. Appl..

[28]  Cheng-Lung Huang,et al.  A distributed PSO-SVM hybrid system with feature selection and parameter optimization , 2008, Appl. Soft Comput..

[29]  Karim Faez,et al.  Feature Selection Using Ant Colony Optimization (ACO): A New Method and Comparative Study in the Application of Face Recognition System , 2007, ICDM.

[30]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[31]  Sreeram Ramakrishnan,et al.  A hybrid approach for feature subset selection using neural networks and ant colony optimization , 2007, Expert Syst. Appl..

[32]  Adam Krzyzak,et al.  Classification of Breast Cancer Malignancy Using Cytological Images of Fine Needle Aspiration Biopsies , 2008, Int. J. Appl. Math. Comput. Sci..

[33]  S. Sheather.  A data-based algorithm for choosing the window width when estimating the density at a point , 1983 .

[34]  Hugo Jair Escalante,et al.  Particle Swarm Model Selection , 2009, J. Mach. Learn. Res..

[35]  Mengjie Zhang,et al.  Pareto front feature selection: using genetic programming to explore feature space , 2009, GECCO.

[36]  Yu-Chiang Frank Wang,et al.  Group lasso regularized multiple kernel learning for heterogeneous feature selection , 2011, The 2011 International Joint Conference on Neural Networks.

[37]  A. Bowman.  An alternative method of cross-validation for the smoothing of density estimates , 1984 .

[38]  Shih-Wei Lin,et al.  Particle swarm optimization for parameter determination and feature selection of support vector machines , 2008, Expert Syst. Appl..

[39]  Ashok Ghatol,et al.  Feature selection for medical diagnosis : Evaluation for cardiovascular diseases , 2013, Expert Syst. Appl..

[40]  Mengjie Zhang,et al.  New fitness functions in binary particle swarm optimisation for feature selection , 2012, 2012 IEEE Congress on Evolutionary Computation.

[41]  Ilias Maglogiannis,et al.  An intelligent system for automated breast cancer diagnosis and prognosis using SVM based classifiers , 2009, Applied Intelligence.

[42]  Cheng-Lung Huang,et al.  A GA-based feature selection and parameters optimizationfor support vector machines , 2006, Expert Syst. Appl..

[43]  Daoliang Li,et al.  Feature selection based on improved ant colony optimization for online detection of foreign fiber in cotton , 2014, Appl. Soft Comput..

[44]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[45]  Charles C. Taylor,et al.  Bootstrap choice of the smoothing parameter in kernel density estimation , 1989 .

[46]  Min-Sen Chiu,et al.  Pareto-optimal solutions based multi-objective particle swarm optimization control for batch processes , 2011, Neural Computing and Applications.

[47]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[48]  Amiya Kumar Rath,et al.  Rough ACO: A Hybridized Model for Feature Selection in Gene Expression Data , 2010 .

[49]  Nor Ashidi Mat Isa,et al.  A genetic algorithm-based multi-objective optimization of an artificial neural network classifier for breast cancer diagnosis , 2013, Neural Computing and Applications.

[50]  Adem Alpaslan Altun,et al.  Cost optimization of mixed feeds with the particle swarm optimization method , 2011, Neural Computing and Applications.

[51]  Xiangyang Wang,et al.  Feature selection based on rough sets and particle swarm optimization , 2007, Pattern Recognit. Lett..

[52]  Zuren Feng,et al.  An efficient ant colony optimization approach to attribute reduction in rough set theory , 2008, Pattern Recognit. Lett..

[53]  Dayou Liu,et al.  A support vector machine classifier with rough set-based feature selection for breast cancer diagnosis , 2011, Expert Syst. Appl..

[54]  Ratna Babu Chinnam,et al.  mr2PSO: A maximum relevance minimum redundancy feature selection method based on swarm intelligence for support vector machine classification , 2011, Inf. Sci..

[55]  R. E. Abdel-Aal,et al.  GMDH-based feature ranking and selection for improved classification of medical data , 2005, J. Biomed. Informatics.

[56]  W. N. Street,et al.  Computer-derived nuclear features distinguish malignant from benign breast cytology. , 1995, Human pathology.

[57]  Jenq-Neng Hwang,et al.  Nonparametric multivariate density estimation: a comparative study , 1994, IEEE Trans. Signal Process..

[58]  I. Haritaoglu,et al.  Background and foreground modeling using nonparametric kernel density estimation for visual surveillance , 2002 .

[59]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[60]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[61]  L. Davis,et al.  Background and foreground modeling using nonparametric kernel density estimation for visual surveillance , 2002, Proc. IEEE.

[62]  Mengjie Zhang,et al.  Particle swarm optimisation for feature selection in classification: Novel initialisation and updating mechanisms , 2014, Appl. Soft Comput..

[63]  Wei-Chang Yeh,et al.  A new hybrid approach for mining breast cancer pattern using discrete particle swarm optimization and statistical method , 2009, Expert Syst. Appl..

[64]  O. Mangasarian,et al.  Pattern Recognition Via Linear Programming: Theory and Application to Medical Diagnosis , 1989 .

[65]  M. Rudemo.  Empirical Choice of Histograms and Kernel Density Estimators , 1982 .

[66]  Cicilia R. M. Leite,et al.  Fuzzy method for pre-diagnosis of breast cancer from the Fine Needle Aspirate analysis , 2012, Biomedical engineering online.

[67]  Richard Weber,et al.  Simultaneous feature selection and classification using kernel-penalized support vector machines , 2011, Inf. Sci..

[68]  Seyed Mojtaba Hosseini Bamakan,et al.  A Novel Feature Selection Method based on an Integrated Data Envelopment Analysis and Entropy Model , 2014, ITQM.

[69]  Zexuan Zhu,et al.  Wrapper–Filter Feature Selection Algorithm Using a Memetic Framework , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[70]  Kenli Li,et al.  Hybrid particle swarm optimization for parameter estimation of Muskingum model , 2014, Neural Computing and Applications.

[71]  Yılmaz Kaya,et al.  A new intelligent classifier for breast cancer diagnosis based on a rough set and extreme learning machine: RS + ELM , 2013 .