Feature selection based on rough sets and particle swarm optimization

By Xiangyang Wang, Jie Yang, Xiao-long Teng, Weijun Xia, Richard Jensen. Pattern Recognition Letters, 2007

874 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Information Systems

View Paper: https://www.semanticscholar.org/paper/acf0fd6937b99e039affc1960a5b6178a84685fc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Information Systems

Citations in the corpus

Moth–flame optimization algorithm: variants and applications (2019, background): “…[46] Parameter Three [31] Three [107] Three [85] Five [88] Three [25] Four [135] Complexity O ( nlogn ) [71] O ð n : D O ð nm 2 Þ Wang et al. [126] O ð HMS (cid:5) M þ HMS (cid:5) log ð HMS ÞÞ [124] Convergence Smoothconvergencewithfastrate [71] Slowconvergencerate[110] [127] [72] Suffer…”
Particle swarm optimisation for feature selection in classification: Novel initialisation and updating mechanisms (2014, methodology): “[27] propose a filter feature selection algorithm based on an improved binary PSO and rough set.”
Particle Swarm Optimization for Feature Selection in Classification: A Multi-Objective Approach (2013, neutral): “[36] propose a filter feature selection”
ECG-based heartbeat classification for arrhythmia detection: A survey (2016, background): “It could bring important contribution to the literature by allowing better understanding of correlation among heart diseases and features extracted from ECG. State-of-art techniques for attribute selection, such as Genetic Algorithms (GA) [109,110] and particle swarm optimization (PSO) [111,112] can”
Multi-Objective Particle Swarm Optimization Approach for Cost-Based Feature Selection in Classification (2017, methodology): “So the cost values of all the D features can be represented by the following vector: U ¼ ½u1; u2; . . . ; uD ; uj 2 ½0; 1 ; j ¼ 1; 2; . . . ; D: (7) For a particle XiðtÞ, supposing its decoded solution is ZiðtÞ, the average of all selected features is used to estimate the whole cost ofXiðtÞ in this…”
A novel chaotic salp swarm algorithm for global optimization and feature selection (2018, neutral): “The performance of the proposed approach is compared with original SSA and five other well-known metaheuristic algorithms; artificial bee colony (ABC), moth flame optimization (MFO), particle swarm optimization (PSO), chicken swarm optimization (CSO) and gray wolf optimizer (GWO) The rest of this pa”
Feature selection for high-dimensional classification using a competitive swarm optimizer (2016, methodology): “have suggested a filter feature selection approach based on rough set and PSO [38].”
BGSA: binary gravitational search algorithm (2010, background): “There are many optimization problems such as feature selection and dimensionality reduction ( Avishek and Maiti 2010; Beretaa and Burczynski 2007; Wang et al. 2007; Chuang et al. 2008; Zeng et al. 2009), data mining (Srinivasa et al. 2007), unit commitment (Yuan et al. 2009), and cell formation (Wu”
A discrete particle swarm optimization method for feature selection in binary classification problems (2010, methodology): “In both Talbi et al. (2008) and Wang et al. (2007), each particle’s position is updated such that the features are decided to be included in the subset independent of one another.”
Supervised hybrid feature selection based on PSO and rough sets for medical diagnosis (2014, methodology): “[16] Feature selection For feature selection, this work applies Genetic Algorithm Particle Swarm Optimization (PSO) PSO and Rough Set-based Feature Selection (PSORSFS) Hannah Inbarani et al.”
Feature Selection With Harmony Search (2012, background): “A cross comparison against other search approaches is given in Section VI-A, including GAs [56], PSO [53], and HC, where both GAs and PSO are evolutionary global optimization heuristics.”
Feature subset selection in large dimensionality domains (2010, methodology): “We compare our algorithms with the following benchmark algorithms: four commonly used greedy search algorithms (sequential 73 backward selection [15], sequential forward selection [16], sequential floating forward selection [18], and sequential float- 75 ing backward selection [18]) and four popular”