Multi-objective Feature Selection: Hybrid of Salp Swarm and Simulated Annealing Approach

Met-heuristics are becoming increasingly popular in solving real world problems. Modern meta-heuristics leading to a new branch of optimization, called meta-heuristic optimization. These applied to all areas of data mining, planning and scheduling, design, machine intelligence, and features selection (FS). FS is used to remove noise from data and dimensionality reduction; these properties could give rise to simplicity of rules, speed of learning, predictive accuracy and visualizes the data. Salp Swarm (SSA) is a recent meta-heuristic optimization method that mimics the innate behaviour of the Salp swarm chain. In this study, SSA is hybridised with a simulated annealing (SA). SA is employed as internal functions to improve the exploitation ability that utilizes to accept a worse quality solution than the current one. The performance of suggested approach is evaluated on 16 datasets including two high dimensional from UCI repository and compared with the native (SSA) and other (FS) approaches include ALO and PSO, the experimental results clearly proved the adequacy of the proposed approach to search the features space for optimal features. SSA-SA gave excellent performance as a multi objective optimisation where achieved two contradictory goals, maximal accuracy of a classification with minimal size of features on all used datasets.

[1]  Xin-She Yang,et al.  BBA: A Binary Bat Algorithm for Feature Selection , 2012, 2012 25th SIBGRAPI Conference on Graphics, Patterns and Images.

[2]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[3]  Rich Caruana,et al.  Greedy Attribute Selection , 1994, ICML.

[4]  Jacob Zahavi,et al.  Using simulated annealing to optimize the feature selection problem in marketing applications , 2006, Eur. J. Oper. Res..

[5]  Hossam Faris,et al.  Salp Swarm Algorithm: A bio-inspired optimizer for engineering design problems , 2017, Adv. Eng. Softw..

[6]  Hossam M. Zawbaa,et al.  Feature selection based on antlion optimization algorithm , 2015, 2015 Third World Conference on Complex Systems (WCCS).

[7]  David M. W. Powers,et al.  Evolutionary feature selection and electrode reduction for EEG classification , 2012, 2012 IEEE Congress on Evolutionary Computation.

[8]  Clarisse Dhaenens,et al.  Optimization and Big Data , 2016 .

[9]  Michael J. A. Berry,et al.  Data Mining Techniques: For Marketing, Sales, and Customer Relationship Management , 2004 .

[10]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[11]  Karim Faez,et al.  An improved feature selection method based on ant colony optimization (ACO) evaluated on face recognition system , 2008, Appl. Math. Comput..

[12]  Hiroshi Motoda,et al.  Feature Selection for Knowledge Discovery and Data Mining , 1998, The Springer International Series in Engineering and Computer Science.

[13]  Qiang Shen,et al.  Nature inspired feature selection meta-heuristics , 2015, Artificial Intelligence Review.

[14]  M.N.S. Swamy,et al.  Search and Optimization by Metaheuristics: Techniques and Algorithms Inspired by Nature , 2016 .

[15]  Qiang Shen,et al.  Feature Selection With Harmony Search , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[16]  Nikhil R. Pal,et al.  Genetic programming for simultaneous feature selection and classifier design , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[17]  Jerzy W. Bala,et al.  Hybrid Learning Using Genetic Algorithms and Decision Trees for Pattern Classification , 1995, IJCAI.

[18]  El-Ghazali Talbi,et al.  Comparison of population based metaheuristics for feature selection: Application to microarray data classification , 2008, 2008 IEEE/ACS International Conference on Computer Systems and Applications.

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

[20]  Chelsea Dobbins,et al.  A Machine Learning Algorithm for Searching Vectorised RDF Data , 2013, 2013 27th International Conference on Advanced Information Networking and Applications Workshops.

[21]  Laurence P. Madin,et al.  Field observations on the feeding behavior of salps (Tunicata: Thaliacea) , 1974 .

[22]  Joaquín A. Pacheco,et al.  A variable selection method based on Tabu search for logistic regression models , 2009, Eur. J. Oper. Res..

[23]  Huan Liu,et al.  Spectral Feature Selection for Data Mining , 2011 .

[24]  Salwani Abdullah,et al.  Investigating a round robin strategy over multi algorithms in optimising the quality of university course timetables , 2011 .

[25]  Enrique Alba,et al.  Gene selection in cancer classification using PSO/SVM and GA/SVM hybrid algorithms , 2007, 2007 IEEE Congress on Evolutionary Computation.

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

[27]  Byung Ro Moon,et al.  Hybrid Genetic Algorithms for Feature Selection , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Majdi M. Mafarja,et al.  Hybrid Whale Optimization Algorithm with simulated annealing for feature selection , 2017, Neurocomputing.