Relevant feature selection and ensemble classifier design using bi-objective genetic algorithm

Das, Asit Kumar; Pati, Soumen Kumar; Ghosh, Arpita

doi:10.1007/s10115-019-01341-6

Cited by 16 publications

(9 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparison is done based on number of features selected and the accuracy of the classifiers used. The feature selection algorithms used are (i) Rough-spanning tree based feature selection algorithm (RMST) [43], (ii) Classification of vocal and non-vocal segments in audio clips using genetic algorithm based feature selection (GAFS) [55] (iii) Relevant feature selection and ensemble classifier design using bi-objective genetic algorithm (RFSA) [56], (iv) Acoustic feature selection for automatic emotion recognition from speech (AFSS) [57], (v) Exploring boundary region of rough set theory for feature selection (RSFS) [52], and (vi) Speech-Based Emotion Recognition: Feature Selection by Self-Adaptive Multi-Criteria Genetic Algorithm (SFGA) [58]. To measure the accuracy of the classifiers based on reduced feature set, we have considered eight different classifiers, namely Support vector machine (SVM), K -nearest neighbors (KNN), Decision tree (DT), Neural network (NN), Random forest (RF), Naïve Bayes (NB), Adaboost (BST), and Sequential minimal optimization (SMO).…”

Section: Evaluation Of Proposed Bffsbr Feature Selection Methodsmentioning

confidence: 99%

A rough set theory and deep learning based predictive system for gender recognition using audio speech

Yasmin

Das

Nayak

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Speech is one of the most delicate medium through which gender of the speakers can easily be identified. Though the related research has shown very good progress in machine learning but recently, deep learning has imparted a very good research area to explore the deficiency of gender discrimination using traditional machine learning techniques. In deep learning techniques, the speech features are automatically generated by the reinforcement learning from the raw data which have more discriminating power than the human generated features. But in some practical situations like gender recognition, it is observed that combination of both types of features sometimes provides comparatively better performance. In the proposed work, we have initially extracted and selected some informative and precise acoustic features relevant to gender recognition using entropy based information theory and Rough Set Theory (RST). Next, the audio speech signals are directly fed into the deep neural network model consists of Convolution Neural Network (CNN) and Gated Recurrent Unit network (GRUN) for extracting features useful for gender recognition. The RST selects precise and informative features, CNN extracts the locally encoded important features, and GRUN reduces the vanishing gradient and exploding gradient problems. Finally, a hybrid gender recognition system is developed combining both generated feature vectors. The developed model has been tested with five bench mark and a simulated dataset to evaluate its performance and it is observed that combined feature vector provides more effective gender recognition system specially when transgender is considered as a gender type together with male and female.

show abstract

Section: Evaluation Of Proposed Bffsbr Feature Selection Methodsmentioning

confidence: 99%

A rough set theory and deep learning based predictive system for gender recognition using audio speech

Yasmin

Das

Nayak

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This work belongs to a class of genetic-based machine learning (GBML). Feature selection through GA has been wrapped up with different classifiers: support vector machine, 35 nearest neighbor classifier, 75 ensemble learning, 76 random forest, 77 and decision trees. 78 Most of the classification processes in the previous work related to texture classification use support vector machines and random forest classifier.…”

Section: Related Workmentioning

confidence: 99%

Enhanced texture classification through feature compaction using dihybrid bio‐inspired computation techniques

Bagavathi¹,

Saraniya²

2021

Concurrency and Computation

View full text Add to dashboard Cite

Synchronous data processing is often preferred considering the volume of data available and the requirement of processed data. Data volume increase from current technical advancements should be balanced and suitably dealt with efficient feature processing techniques. Feature selection can efficiently improve the concurrency in data processing on a completely uncorrelated and separately processable feature set.Texture analysis is a significant application of image processing that analyses specific patterns in an image. As the volume of image data available for producing better classification models progressively moves to be out of the human-manageable range, it is the automation methods that aid the researchers to manage the data. When the number of samples in the data and the dimensionality of the problem is too high, the purpose of data analysis is often compromised. Feature engineering can be utilized to improve the efficiency of the model with a smaller subset of features. This work proposes dibyhrid bio-inspired computation based feature compaction, that is a combination of improvised genetic algorithm and selective tabu search for texture classification problem.Machine learning techniques are employed to evaluate and minimize the validation error from the applied computational methods.

show abstract

“…This number may run in thousands. With the collection of all the data, a gene expression profile for the cell is generated [15].…”

Section: Introductionmentioning

confidence: 99%

EapGAFS: Microarray Dataset for Ensemble Classification for Diseases Prediction

Krishna

Rajarajeswari

2022

IJRITCC

View full text Add to dashboard Cite

Microarray data stores the measured expression levels of thousands of genes simultaneously which helps the researchers to get insight into the biological and prognostic information. Cancer is a deadly disease that develops over time and involves the uncontrolled division of body cells. In cancer, many genes are responsible for cell growth and division. But different kinds of cancer are caused by a different set of genes. So to be able to better understand, diagnose and treat cancer, it is essential to know which of the genes in the cancer cells are working abnormally. The advances in data mining, machine learning, soft computing, and pattern recognition have addressed the challenges posed by the researchers to develop computationally effective models to identify the new class of disease and develop diagnostic or therapeutic targets. This paper proposed an Ensemble Aprior Gentic Algorithm Feature Selection (EapGAFS) for microarray dataset classification. The proposed algorithm comprises of the genetic algorithm implemented with aprior learning for the microarray attributes classification. The proposed EapGAFS uses the rule set mining in the genetic algorithm for the microarray dataset processing. Through framed rule set the proposed model extract the attribute features in the dataset. Finally, with the ensemble classifier model the microarray dataset were classified for the processing. The performance of the proposed EapGAFS is conventional classifiers for the collected microarray dataset of the breast cancer, Hepatities, diabeties, and bupa. The comparative analysis of the proposed EapGAFS with the conventional classifier expressed that the proposed EapGAFS exhibits improved performance in the microarray dataset classification. The performance of the proposed EapGAFS is improved ~4 – 6% than the conventional classifiers such as Adaboost and ensemble.

show abstract

Relevant feature selection and ensemble classifier design using bi-objective genetic algorithm

Cited by 16 publications

References 38 publications

A rough set theory and deep learning based predictive system for gender recognition using audio speech

A rough set theory and deep learning based predictive system for gender recognition using audio speech

Enhanced texture classification through feature compaction using dihybrid bio‐inspired computation techniques

EapGAFS: Microarray Dataset for Ensemble Classification for Diseases Prediction

Contact Info

Product

Resources

About