A Hybrid of Genetic Algorithm and Support Vector Machine for Feature Reduction and Detection of Vocal Fold Pathology

Majidnezhad, Vahid; Kheidorov, Igor E.

doi:10.5815/ijigsp.2013.09.01

Cited by 3 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Genetic Algorithm (GA) is a nature-inspired optimization approach that searches for a single solution while evaluating various potential solutions. Practically optimization strategies have recently been (Majidnezhad & Kheidorov, 2013). Following this, Rodriguez et al had taken advantage of cosine similarity to classify EMG signal data categorized into subjects with muscle fatigue and nonfatigue.…”

Section: Feature Size Reductionmentioning

confidence: 99%

Review of Emg Signal Classification Approaches Based on Various Feature Domains

Jain

Garg

2021

mijst

View full text Add to dashboard Cite

Electromyography (EMG) is a widely used analytical practice that relays the health-status of the muscles or the nerve cells by monitoring their electrical impulses. However, it inherits the poor signal-to-noise ratio in addition to occasional signal distortions that significantly challenges the efficacy of this technique. Therefore, since the advent of this technology, numerous researchers have dedicated their study to improve the signal quality by reducing inherent noise in addition to offering its automated classification. In the present work, the authors have presented an overview of various existing researches in the field of electro-myographic signals classification involving various state-of-art techniques. A comprehensive survey has been provided while discussing the EMG signal analytic techniques involving different domains along with their performance. In the process, research not published before 2010 in various authenticated sources, such as Elsevier, PubMed, Springer, IEEE, and other articles and reports that are under the coverage of Web of Science and Google Scholar were analyzed. The review examined the suitability of various existing techniques to empower the healthcare sector based on the

show abstract

Section: Feature Size Reductionmentioning

confidence: 99%

Review of Emg Signal Classification Approaches Based on Various Feature Domains

Jain

Garg

2021

mijst

View full text Add to dashboard Cite

show abstract

“…Also, some of the well-known classifiers for the classification phase in the previous works were used such as support vector machine (SVM) [16][17][18][19], Gaussian mixture model (GMM) [20][21][22], artificial neural network (ANN) [23][24][25], and hidden Markov model (HMM) [26][27][28].…”

Section: Introductionmentioning

confidence: 99%

A novel hybrid of genetic algorithm and ANN for developing a high efficient method for vocal fold pathology diagnosis

Majidnezhad

2015

J AUDIO SPEECH MUSIC PROC.

Self Cite

View full text Add to dashboard Cite

In this paper, an initial feature vector based on the combination of the wavelet packet decomposition (WPD) and the Mel frequency cepstral coefficients (MFCCs) is proposed. For optimizing the initial feature vector, a genetic algorithm (GA)-based approach is proposed and compared with the well-known principal component analysis (PCA) approach. The artificial neural network (ANN) with the different learning algorithms is used as the classifier. Some experiments are carried out for evaluating and comparing the classification accuracies which are obtained by the use of the different learning algorithms and the different feature vectors (the initial and the optimized ones). Finally, a hybrid of the ANN with the 'trainscg' training algorithm and the genetic algorithm is proposed for the vocal fold pathology diagnosis. Also, the performance of the proposed method is compared with the recent works. The experiments' results show a better performance (the higher classification accuracy) of the proposed method in comparison with the others.

show abstract