Magnitude Squared of Coherence to Detect Imaginary Movement

Filho, Sady Antônio Santos; Tierra-Criollo, Carlos Júlio; Souza, Ana Paula de; Pinto, Marcos Antonio Silva; Lima, Maria Luiza Cunha; Manzano, Gilberto Mastrocola

doi:10.1155/2009/534536

Cited by 23 publications

(22 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The responses were detected with magnitude-squared coherence (MSC) at a 5% significance level [23]. Each sweep lasted 1,024 s, and the maximum average was 480 sweeps.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Auditory steady-state responses in school-aged children: a pilot study

Resende

Carvalho

Santos

et al. 2015

Journal of NeuroEngineering and Rehabilitation

View full text Add to dashboard Cite

BackgroundThe use of Auditory Steady-State Responses (ASSRs) for auditory screening in school-aged children, particularly in children who are difficult to test and children with disabilities, has not been explored yet. This pilot study investigated the use of ASSR for auditory screening in school-aged children.Materials and methodsA cross-sectional pilot study of 23 children aged 9 to 11 with normal-hearing thresholds and seven age-matched children with permanent moderate-to-profound bilateral hearing loss were examined. The tested carrier frequencies were 500, 1,000, 2,000, and 4,000 Hz, and the stimulus was modulated between 77 and 107 Hz. The ASSRs decreased according to the tested intensity levels of 50, 40, and 30 dB sound pressure level (SPL). Sensitivity and specificity were estimated from the responses of the children with normal hearing and those with hearing loss.ResultsFor the children with normal hearing, the 2,000-Hz frequency was detected more often in both ears and at all intensity levels compared to the other frequencies. The 500- and 2,000-Hz frequencies resulted in different response patterns in both ears. The time until response detection increased in parallel with amplitude reduction, as expected. The overall time required for the test was 15 minutes, including the time spent in volunteer preparation. The sensitivity was 97% for the three intensities, and the best specificity value was 100%, which was observed at 50 dB.DiscussionThe response analysis indicated that a screening protocol for school-aged children could include 1,000, 2,000, and 4,000 Hz and that the recording of ASSRs was highly sensitive to internal and external factors. Fifty dB SPL should be considered a cut-off criterion for screening purposes because this was the intensity level with a sensitivity of 97% and a specificity of 100%.ConclusionThe use of ASSRs might be particularly useful in school-aged children who have difficulty performing subjective hearing tests. The sensitivity and specificity data suggested that the use of ASSRs was feasible as an auditory screening tool. In order to determine a protocol for screening, future studies should include a larger sample and children with mild hearing loss.

show abstract

“…The responses were detected with magnitude-squared coherence (MSC) at a 5% significance level [23]. Each sweep lasted 1,024 s, and the maximum average was 480 sweeps.…”

Section: Methodsmentioning

confidence: 99%

“…The ORD technique used the MSC at a 5% significance level [23]. In the absence of a stimulus, the MSC values tended to approach zero.…”

Section: Methodsmentioning

confidence: 99%

Auditory steady-state responses in school-aged children: a pilot study

Resende

Carvalho

Santos

et al. 2015

Journal of NeuroEngineering and Rehabilitation

View full text Add to dashboard Cite

show abstract

“…Os sinais captados pelos 17 eletrodos foram filtradas off line com um filtro digital Butterworth de ordem 2 e banda de 0,1 a 30 Hz. Cada sinal foi dividido em trechos sincronizados nos intervalos -0,7 a 2,3 s, uma vez que a resposta cortical da tarefa motora encontra-se neste período de tempo [8]. Os trechos considerados como artefatos foram removidos segundo descrito por [9].…”

Section: Materiais E Métodosunclassified

Classificação Com Máquina De Vetores De Suporte E Coerência Na Imagética Motora Com Prática Mental

Erazo-Costa¹,

Santos²,

Gomes³

et al. 2016

Anais Do 10. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

-A brain computer interface (BCI) is a system that communicates a person with an electronic device by means of mental signals. Pattern recognition is an important module for BCIs because it translates brain activity into commands for the activation of a machine. This paper aims at presenting the relation between mental practice and the algorithm classifier support vector machine in combination with the magnitude squared coherence for the classification of motor imagery movements of the index finger (imagination and spontaneous). An accuracy of 98 % was found with one subject with the training of the machine with data for the four sessions and validation of session 5. Furthermore, an incremental accuracy of the classification around the different sessions was found for all subjects with mental practice. This approach could be used for the development of BCIs.Keywords -Mental Practice, coherence, SVM. IntroduçãoA interface cérebro máquina (ICM) é um sistema capaz de comunicar um indivíduo e um dispositivo eletrônico mediante o processamento de sinais cerebrais. O principal objetivo é auxiliar pessoas com deficiência por meio do controle de membros artificiais [1].O reconhecimento de padrões de sinais de eletroencefalografia (EEG) relacionado a tarefas mentais é um módulo muito importante dentro da investigação das ICMs [2]. Para controlar este tipo de interface, os padrões devem ser identificados e convertidos em comandos para acionar uma máquina. Esta identificação é feita pelo uso de algoritmos de classificação. Dentre os classificadores, pode-se citar: classificadores lineares, redes neurais, classificadores bayesianos não lineares, classificadores do vizinho próximo e a combinação de classificadores [3]. Os estudos realizados por Ahmadi et al [4] demonstraram que a utilização de redes neurais probabilísticas recorrentes para classificação de movimentos de preensão da mão direta e esquerda com prática mental incrementou a taxa de acerto da primeira sessão (80%) -processamento off line e sem treinamento-em comparação com a última sessão e utilizando uma única imaginação (73% a 91%). Entretanto, Ming et al [5] utilizaram a Máquina de Vetores de Suporte (SVM) em conjunto com análises de componentes independentes para a classificação de movimentos motores encontrando uma taxa de acerto entre 77,6% e 91,4%.Um dos fatores mais importantes para a robustez dos classificadores é a extração de características. A técnica estatística magnitude quadrática da coerência (MSC) tem-se mostrado promissora para a detecção de tarefas motoras [6]. Por conseguinte, a MSC é utilizada neste trabalho como entrada para o algoritmo de classificação. O classificador utilizado é a máquina de vetores de suporte (SVM) porque em ICMs obteve-se os melhores resultados em experimentos síncronos e é robusto com respeito a altas dimensionalidades [3].Visando favorecer a identificação de padrões de atividade cerebral relacionada à imaginação motora (IM), este estudo tem como objetivo verificar se a prática mental baseada em IM influencia s...

show abstract

“…When a subject receive a target visual stimulus, the specific components of ERP can be detected by different electrodes. To find the target-specific components out, we estimate the Magnitude Squared of Coherence (MSC, see formula (1)) [36] of signals detected in different EEG channels.…”

Section: Magnitude Squared Of Coherences and Correlation Distances Bementioning

confidence: 99%