A stable hybrid method for feature subset selection using particle swarm optimization with local search

Dhrif, Hassen; Giraldo, Luis G. Sánchez; Kubát, Miroslav; Wuchty, Stefan

doi:10.1145/3321707.3321816

Cited by 9 publications

(2 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As already mentioned, meta heuristics in previous decades simulate organisms’ collective behaviors. In particular, this algorithm has generated an important development in several regions associated with optimization 7 . The optimal selection is made by a metaheuristic algorithm; in a rational interval, the cloud generates better solutions 8 .…”

Section: Introductionmentioning

confidence: 99%

MapReduce-based big data classification model using feature subset selection and hyperparameter tuned deep belief network

Rajendran

Khalaf

Alotaibi

et al. 2021

Sci Rep

123

View full text Add to dashboard Cite

In recent times, big data classification has become a hot research topic in various domains, such as healthcare, e-commerce, finance, etc. The inclusion of the feature selection process helps to improve the big data classification process and can be done by the use of metaheuristic optimization algorithms. This study focuses on the design of a big data classification model using chaotic pigeon inspired optimization (CPIO)-based feature selection with an optimal deep belief network (DBN) model. The proposed model is executed in the Hadoop MapReduce environment to manage big data. Initially, the CPIO algorithm is applied to select a useful subset of features. In addition, the Harris hawks optimization (HHO)-based DBN model is derived as a classifier to allocate appropriate class labels. The design of the HHO algorithm to tune the hyperparameters of the DBN model assists in boosting the classification performance. To examine the superiority of the presented technique, a series of simulations were performed, and the results were inspected under various dimensions. The resultant values highlighted the supremacy of the presented technique over the recent techniques.

show abstract

Section: Introductionmentioning

confidence: 99%

MapReduce-based big data classification model using feature subset selection and hyperparameter tuned deep belief network

Rajendran

Khalaf

Alotaibi

et al. 2021

Sci Rep

123

View full text Add to dashboard Cite

show abstract

“…Furthermore, only knowledge of the real data distribution can define an optimal subset. Since these data characteristics are generally hidden, methods for estimating appropriate and redundant features are applied [4]. A huge number of features cannot be addressed by conventional machine learning approaches.…”

Section: Introductionmentioning

confidence: 99%

Improved Feature Selection Model for Big Data Analytics

et al. 2020

View full text Add to dashboard Cite

Although there are many attempts to build an optimal model for feature selection in Big Data applications, the complex nature of processing such kind of data makes it still a big challenge. Accordingly, the data mining process may be obstructed due to the high dimensionality and complexity of huge data sets. For the most informative features and classification accuracy optimization, the feature selection process constitutes a mandatory pre-processing phase to reduce dataset dimensionality. The exhaustive search for the relevant features is time-consuming. In this paper, a new binary variant of the wrapper feature selection grey wolf optimization and particle swarm optimization is proposed. The K-nearest neighbor classifier with Euclidean separation matrices is used to find the optimal solutions. A tent chaotic map helps in avoiding the algorithm from locked to the local optima problem. The sigmoid function employed for converting the search space from a continuous vector to a binary one to be suitable to the problem of feature selection. Crossvalidation K-fold is used to overcome the overfitting issue. A variety of comparisons have been made with well-known and common algorithms, such as the particle swarm optimization algorithm, and the grey wolf optimization algorithm. Twenty datasets are used for the experiments, and statistical analyses are conducted to approve the performance and the effectiveness and of the proposed model with measures like selected features ratio, classification accuracy, and computation time. The cumulative features picked through the twenty datasets were 196 out of 773, as opposed to 393 and 336 in the GWO and the PSO, respectively. The overall accuracy is 90% relative to other algorithms ' 81.6 and 86.8. The total processing time for all datasets equals 184.3 seconds, wherein GWO and PSO equal 272 and 245.6, respectively. INDEX TERMS Particle swarm optimization (PSO), grey wolf optimization (GWO), data mining, big data analytics, feature selection.

show abstract

Stability of Feature Selection Algorithms

Theng

Bhoyar

2022

Artificial Intelligence on Medical Data

View full text Add to dashboard Cite

A stable hybrid method for feature subset selection using particle swarm optimization with local search

Cited by 9 publications

References 45 publications

MapReduce-based big data classification model using feature subset selection and hyperparameter tuned deep belief network

MapReduce-based big data classification model using feature subset selection and hyperparameter tuned deep belief network

Improved Feature Selection Model for Big Data Analytics

Stability of Feature Selection Algorithms

Contact Info

Product

Resources

About