Feature selection based on binary particle swarm optimization and neural networks for pathological voice detection

Souza, Taciana Araújo de; Souza, M A; Costa, Washington C. de A.; Costa, Silvana Cunha; Correia, Suzete; Vieira, Vinícius Jefferson Dias

doi:10.1109/la-cci.2015.7435962

Cited by 6 publications

(13 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The research by Beckers et al [9], for instance, proposes the analysis of texture in CT (computed tomography) of the entire liver to predict the development of colorectal liver metastases. Another application presented by Souza et al [10] analyzes recurrence plots of voice signals as texture images in order to identify the presence of pathology in vocal folds. The feature extraction was based on the wavelet transform of the original images.…”

Section: Imentioning

confidence: 99%

“…A technique to artificially increase the number of samples in the database was also developed. The results were also compared with Souza et al [10] which uses the same recurrence plots and a classification method based on feature extraction.…”

Section: Imentioning

confidence: 99%

“…A texture analysis was performed by Souza et al [10] on the wavelet transforms of recurrence plots of voice signals. Haralick descriptors were used for feature extraction.…”

Section: R Wmentioning

confidence: 99%

“…The database consists of 53 healthy voice files and 112 voice signals affected by pathology in the larynx, of which 51 have paralysis, 43 Reinke's edema and 18 nodules in the vocal folds. The recurrence plots used in this research were generated in the Visual Recurrence Analysis (VRA) [15] software, obtained from Souza et al [10].…”

Section: Dmentioning

confidence: 99%

See 3 more Smart Citations

Classification of Recurrence Plots of Voice Signals Using Convolutional Neural Networks

Barros¹,

Soares²,

Correia³

et al. 2020

Anais De XXXVIII Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

In the last decade, texture analysis has been widely applied to image classification. This method has great relevance on recognition of patterns in medical images surfaces. Alternatively, many studies have investigated the usage of Convolutional Neural Networks (CNNs) as a technique for classifying texture images. In this study, a low-complexity CNN was applied to recurrence plots of voice signals to distinguish the presence of laryngeal pathology. A data augmentation technique was employed to increase the number of samples. A study using the same dataset and another classification approach was considered for results comparison. The CNN proposed was proven to be more robust with a 12% increase on accuracy compared to the previous work.

show abstract

Section: Imentioning

confidence: 99%

Section: Imentioning

confidence: 99%

“…A texture analysis was performed by Souza et al [10] on the wavelet transforms of recurrence plots of voice signals. Haralick descriptors were used for feature extraction.…”

Section: R Wmentioning

confidence: 99%

Section: Dmentioning

confidence: 99%

See 2 more Smart Citations

Classification of Recurrence Plots of Voice Signals Using Convolutional Neural Networks

Barros¹,

Soares²,

Correia³

et al. 2020

Anais De XXXVIII Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

show abstract

“…Algoritmos bio-inspirados, baseados em populações, vêm sendo usados para seleção de características em vários domínios de problemas, para os quais soluções robustas são difíceis ou impossíveis de serem encontradas, usando abordagens tradicionais. Dentre eles, Otimização por Nuvens de Partículas (Particle Swarm Optimization) [7][8][9][10], Otimização de Colônia de Formigas (Ant Colony Optimization) [10][11], Busca de Cardumes de Peixes (Fish School Search) [10] e Colônia Artificial de Abelhas (Artificial Bee Colony-ABC) [12][13][14][15][16], tem se destacado.…”

Section: Introductionunclassified

Algoritmo Bio-inspirado em Colônia de Abelhas Aplicado na Seleção de Características para Detecção de Desvios Vocais

Sousa¹

2018

Proceedings XIII Brazilian Congress on Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Feature selection is an important step used in several pattern recognition tasks to identify the significant features and discard irrelevant or redundant ones from the original set. In this research, a feature selection algorithm based on binary artificial bee colony with K-NN classifier is used for the discriminative analysis between healthy voices and voices with vocal deviations (breathiness, roughness and strain). The aim is to determine which acoustic measures based on the recurrence quantification analysis are relevant and contribute more in voice signals discrimination. In thirty two tests performed, 88.33% of accuracy was obtained with a reduction of fifteen for seven features in the discrimination between healthy and strained voices, four features and accuracy of 88.33% in the classification between healthy and breathiness and a reduction for five features, with an accuracy of 93.33%, in the discrimination between healthy and rough voices.

show abstract

Chaotic Grey Wolf Optimization‐based resource allocation for Vehicle‐to‐Everything communications

Brahmi

Hamdi

Zarai

2021

Int J Communication

View full text Add to dashboard Cite

Summary Device‐to‐device (D2D) enables direct communication between Vehicle‐to‐Everything (V2X) devices. For V2X communications, efficient power control and radio sub‐channel allocation schemes are expected to accommodate the growing demand for data traffic of the increasing number of vehicular devices. We propose to investigate the resource allocation problem for V2X networks. We categorize vehicle user equipment (VUEs) into safety and non‐safety VUEs and cellular user equipment (CUEs) into real‐time and non‐real‐time CUEs according to their communication types. The objective of the proposed model is to maximize the total throughput of the system while maintaining quality of service (QoS) for CUEs and VUEs. Chaotic Grey Wolf Optimization (CGWO) algorithm, a meta‐heuristic and evolutionary algorithm, is used to solve the resource allocation problem in V2X communications. Finally, comparisons between the proposed scheme and two other meta‐heuristic algorithms, namely, Particle Swarm Optimization (PSO) and GWO for resource allocation, are carried out. The simulation results prove the effectiveness and performance of the proposed scheme in terms of resource allocation for V2X. They also demonstrate that CGWO‐based resource allocation scheme outperforms both PSO‐based and GWO‐based resource allocation schemes in terms of total achieved throughput.

show abstract

Feature selection based on binary particle swarm optimization and neural networks for pathological voice detection

Cited by 6 publications

References 7 publications

Classification of Recurrence Plots of Voice Signals Using Convolutional Neural Networks

Classification of Recurrence Plots of Voice Signals Using Convolutional Neural Networks

Algoritmo Bio-inspirado em Colônia de Abelhas Aplicado na Seleção de Características para Detecção de Desvios Vocais

Chaotic Grey Wolf Optimization‐based resource allocation for Vehicle‐to‐Everything communications

Contact Info

Product

Resources

About