PPubMed10 Mar 2016Cited 163×

Feature Selection via Chaotic Antlion Optimization Feature Selection via Chaotic Antlion Optimization

Hossam M. Zawbaa, E. Emary, Crina Grosan, Josh Bongard

Abstract

[pone.0150652.g004] shows the average statistical mean fitness, best fitness, worst fitness, and the standard deviation for all the methods used and for all 18 datasets. The results for the biological datasets are presented in ([pone.0150652.g005]), and those for the other non-biological datasets are presented in ([pone.0150652.g006]). We can observe that ALO and CALO generally perform better than GA and PSO. The search method adopted in ALO is more explorative than the one used in GA and PSO because ALO performs a local search around a roulette wheel selected solution, and in this way, other

A figure from Feature Selection via Chaotic Antlion Optimization Feature Selection via Chaotic Antlion Optimization — fig. from the paper

§ The Valyu brief

The paper, in five minutes

Read from the full text via Valyu Contents

A chaotic antlion optimizer (CALO) improves feature selection accuracy and stability, outperforming ALO, PSO, and GA on 18 datasets.

What’s new

i.Proposed a chaotic version of the antlion optimizer (CALO) for wrapper‑based feature selection
ii.Evaluated CALO with five chaotic maps on 18 datasets (10 biological, 8 non‑biological)
iii.Demonstrated that CALO outperforms original ALO, PSO, and GA in classification accuracy and stability
iv.Identified the tent map as the most effective chaotic map and the sinusoidal map as the least effective
v.Showed substantial feature reduction on benchmark datasets such as Breastcancer and HeartEW

How they did it

CALO integrates chaotic maps to adapt the exploration‑exploitation parameter I of the antlion optimizer, using a K‑nearest‑neighbor wrapper for feature selection. The algorithm was evaluated on 18 datasets (10 biological, 8 others) split into training, validation, and testing sets, and compared against ALO, PSO, and GA variants.

What they found

CALO achieved the highest classification accuracy on 11 of the 18 datasets.
Approximately 75% of the features selected by CALO overlapped with those chosen by GA or PSO.
For the Breastcancer dataset (9 features) CALO selected only 4 features; for the HeartEW dataset (13 features) it selected 5 features.
The tent chaotic map yielded the best performance among the five maps, while the sinusoidal map performed worst.

Caveats

✕The selected feature subset is not exactly repeatable across runs, leading to different subsets each time.
✕The method relies on a KNN wrapper; using other classifiers such as SVM or Random Forest may increase runtime.
✕Real‑time application may be problematic due to potential increased computational cost with other classifiers.

§ The Valyu brief

Reading the full paper and taking notes. This takes a few seconds…

§ Ask this paper

Ask a question about this paper

Valyu reads the full text and answers from what the paper actually says.

§ Related work in other archives

Feature Selection via Chaotic Antlion Optimization Feature Selection via Chaotic Antlion Optimization

The paper, in five minutes

Ask a question about this paper

Similar papers in all four archives

Similar papers in all four archives

The paper, in five minutes