Hybrid ACO-PSO Based Approaches for Feature Selection

Menghour, Kamilia; Souici-Meslati, Labiba

doi:10.22266/ijies2016.0930.07

Cited by 24 publications

(18 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cloning is the duplication of the data in several specimens; this operation makes possible to keep information long in the workspace. A cloning is proportional to affinity because an antibody approaching more to the antigen is interesting to keep information about it which carry it for a long time and that by duplicating it in several identical specimens, and the mutation will play the role to widen the workspace [31]. We will calculate the number of clones (NC) in our algorithm using:…”

Section: The Cloningmentioning

confidence: 99%

“…Then, HMOFSA algorithm is used to choose the selected features from examples. The attained partial outcomes will be combined into a final vector [29] methods: PSO and ACO, Manghour proposed three hybrid bio-inspired approaches for FS task (ACO-PSO1, ACO-PSO2 and ACO-PSO3) [31]. In [32], the Ant Colony, Artificial Bee and Firefly Algorithms were used to select the most relevant features in a dataset then a Genetic Algorithm can create a new population of chromosomes using as initial population the populations generated by the three algorithms used (ACO, ABC and FA) instead of a random one.…”

Section: Proposed Approachmentioning

confidence: 99%

See 1 more Smart Citation

Firefly Optimization Using Artificial Immune System for Feature Subset Selection

Kihel¹,

Chouraqui²

2019

IJIES

View full text Add to dashboard Cite

At first glance, the feature selection is a crucial step in a pattern recognition system. The main objective of this selection is to reduce the features number, by eliminating irrelevant and redundant attributes. In addition, we try to maintain or improve the classifier performance using neural network algorithm. Nevertheless, a new stochastic search strategy inspired by the clonal selection theory in an artificial immune system is proposed for feature subset selection. We have used the firefly and clonal selection algorithms to select the most relevant features in a dataset. In our proposed strategy, feature selection algorithm is formulated as an optimization problem that searches an optimum with less number of features in a feature space and a good accuracy. The goal of our study is to achieve a balance between the classification accuracy and the size of the feature subsets selected using two new hybrid algorithms based on Immune Firefly Algorithm (IFA). Our proposed approach has been evaluated on 10 standard datasets taken from UCI repository. The experimental outcomes have been compared to some popular feature selection methods. The comparison of results shows that our methods significantly outperform most of the used feature selection algorithms.

show abstract

Section: The Cloningmentioning

confidence: 99%

Section: Proposed Approachmentioning

confidence: 99%

Firefly Optimization Using Artificial Immune System for Feature Subset Selection

Kihel¹,

Chouraqui²

2019

IJIES

View full text Add to dashboard Cite

show abstract

“…This paper discusses a hybrid meta-heuristic algorithm that combines the quality of diverse meta-heuristic techniques in the next section. [10]. The GA-DE crossover phase uses DE perturbation phase to improve the convergence.…”

Section: Figure 1: Malignant Tumor Detection Stepsmentioning

confidence: 99%

Implementation of Hybrid ACO-PSO-GA-DE Algorithm for Mammogram Classification

Bala¹,

Priti²

2019

IJRTE

View full text Add to dashboard Cite

Breast Cancer is one of the fastest growing cancer that causes women to death in the world. The early detection of breast cancer improves the chances of its cure. The malignant tumor that is the sign of breast cancer can be detected by mammography. This paper develops a technique to classify the mammogram images as normal, benign or malignant. This paper applies HAPGD (Hybrid ACO (Ant Colony Optimization), PSO (Particle Swarm Optimization), GA (Genetic Algorithm), and DE (Differential Evolution)) classification algorithm to texture features extracted from the mammogram image. The analysis has been done on the DDSM and MIAS dataset by using classification accuracy, specificity, and sensitivity as the parameter with three state of art algorithms i.e. SVM classifier (without any optimization technique), Firefly (SVM with Firefly optimization), ACO-PSO-GA (SVM with hybrid ACO-PSO-GA optimization). The improvement in the performance measures against three state of art techniques shows the significance of the algorithm.

show abstract

“…The performance of HAPGD algorithm is compared with hybrid meta-heuristic algorithms i.e. ACO-PSO [12], ACO-GA [13], PSO-GA [14], GA-DE [15] and ACO-PSO-GA [10] using the parameters described above on 7 datasets given in table 1 has been done in this section. The results are evaluated by executing the algorithms 20 times and taking the average of results.…”

Section: Performance Analysismentioning

confidence: 99%

Hybrid ACO-PSO-GA-DE Algorithm for Big Data Classification

2019

ijrte

View full text Add to dashboard Cite

This paper designs a technique to classify big data efficiently. This work considers the processing of big data as an optimization problem due to the trade-off between accuracy and time and solves this optimization problem by using a meta-heuristic approach. The HAPGD (Hybrid ACO (Ant Colony Optimization), PSO (Particle Swarm Optimization), GA (Genetic Algorithm), and DE (Differential Evolution)) classification algorithm is designed by using the support vector machine (SVM) along with hybrid ACO-PSO-GA-DE algorithm that hybrids exploration capability of ACO with exploitation capability of PSO whose balance is maintained using modified GA. The GA has been modified by using the DE algorithm. The presented technique performs classification efficiently as shown in results on seven datasets using different analysis parameters due to balanced exploration and exploitation search with fast convergence

show abstract

Hybrid ACO-PSO Based Approaches for Feature Selection

Cited by 24 publications

References 61 publications

Firefly Optimization Using Artificial Immune System for Feature Subset Selection

Firefly Optimization Using Artificial Immune System for Feature Subset Selection

Implementation of Hybrid ACO-PSO-GA-DE Algorithm for Mammogram Classification

Hybrid ACO-PSO-GA-DE Algorithm for Big Data Classification

Contact Info

Product

Resources

About