Improving BCI performance by task-related trial pruning

Sannelli, Claudia; Braun, Mikio L.; Müller, Klaus‐Robert

doi:10.1016/j.neunet.2009.08.006

Cited by 21 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, there exist a certain number of users who cannot generate discriminative task-related brain signals in every trial. Recently, Sannelli, Braun, and Müller (2009) developed a method to prune such undesirable trials by comparing true labels and their predictions. They computed CSP only with reliable trials, which can improve BCI classification performance and stabilize the features at the same time.…”

Section: Resultsmentioning

confidence: 99%

Robust Common Spatial Filters with a Maxmin Approach

et al. 2014

Self Cite

View full text Add to dashboard Cite

Electroencephalographic signals are known to be nonstationary and easily affected by artifacts; therefore, their analysis requires methods that can deal with noise. In this work, we present a way to robustify the popular common spatial patterns (CSP) algorithm under a maxmin approach. In contrast to standard CSP that maximizes the variance ratio between two conditions based on a single estimate of the class covariance matrices, we propose to robustly compute spatial filters by maximizing the minimum variance ratio within a prefixed set of covariance matrices called the tolerance set. We show that this kind of maxmin optimization makes CSP robust to outliers and reduces its tendency to overfit. We also present a data-driven approach to construct a tolerance set that captures the variability of the covariance matrices over time and shows its ability to reduce the nonstationarity of the extracted features and significantly improve classification accuracy. We test the spatial filters derived with this approach and compare them to standard CSP and a state-of-the-art method on a real-world brain-computer interface (BCI) data set in which we expect substantial fluctuations caused by environmental differences. Finally we investigate the advantages and limitations of the maxmin approach with simulations.

show abstract

Section: Resultsmentioning

confidence: 99%

Robust Common Spatial Filters with a Maxmin Approach

et al. 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…Other methods robustify the variance estimation in CSP by applying L p -norms (Wang et al, 2012b;Park and Chung, 2013). The authors of (Sannelli et al, 2009) apply trial pruning in order to separate signal from noise and (Parra et al, 2005) discuss several methods for minimum noise estimation. A beta divergence method for robust spatial filtering is proposed in this thesis and has been prepublished in (Samek et al, 2013b).…”

Section: Robust Estimationmentioning

confidence: 99%

On robust spatial filtering of EEG in nonstationary environments

Samek

2016

It - Information Technology

View full text Add to dashboard Cite

bibliography 119 I N T R O D U C T I O NVariability is the law of life, and as no two faces are the same, so no two bodies are alike, and no two individuals react alike and behave alike under the abnormal conditions which we know as disease. (Sir William Osler, 1903) T he Canadian physician Sir William Osler (1849 -1919 revolutionized the medical world of the 19th century by advocating an approach to therapy which focuses on the needs of individual patients. He recognized the great variability among individuals with respect to their physical conditions, their mental status and their responses to drugs and concluded that focusing solely on clinical signs and symptoms does not result in the most effective therapy. The development of this novel patient-centered paradigm made him the father of personalized medicine; a branch of medicine that is also very popular today due to a better understanding of the genetic influences on a person's risk of acquiring certain diseases.In the last two decades personalized approaches have also revolutionized the field of Brain-Computer Interfacing (BCI). A BCI system (see e.g. Wolpaw et al., 2002;Dornhege et al., 2007;Wolpaw and Wolpaw, 2012) aims to decode the intention of a user from recordings of brain activity and to use this information for controlling a computer application or a robotic device. Today's BCIs extract user-specific features from electroencelographic (EEG) recordings and adapt to the user's signal characteristics. This subject-centered or machine learning approach not only largely reduces the calibration time in comparison to classical BCI systems based on neurofeedback training (Kamiya et al., 1969) but also increases classification accuracy. Unfortunately, EEG responses to a stimulus or a task not only differ from subject to subject but also from trial to trial and from day to day. This change in the signal properties over time is termed the intrinsic nonstationarity of EEG (Kaplan et al., 2005) and constitutes a major challenge for data analysis and classification by violating a basic assumption of many machine learning methods, namely that data are sampled from a fixed (but unknown) distribution (Vapnik, 1998;Hastie et al., 2001). The analysis of EEG is further aggravated by the presence of artifacts in the data, e.g., eye movements, muscular activity or loose electrodes. The lack of robustness to unexpected events and the nonstationary nature of EEG are major reasons in explaining why current BCI technology is seldom used in out-of-lab scenarios and clinical practice. Since artifacts and nonstationarity can not be fully eliminated, even with the best experimental protocol, robust and invariant feature 1 2 introduction representations are required for optimal signal analysis and high classification accuracy. structure of the thesisThis thesis is divided into three parts. The first part introduces the basic concepts of motor imagery-based Brain-Computer Interfacing and discusses the advantages and limitations of several state-of-the-art spatial filtering al...

show abstract

“…Utilizan como espacio de características los valores de ERD/ERS y MRP recogidos en cada uno de los ensayos realizados por diversos sujetos en lugar del promediado de ambas características para todos los ensayos. Es por tanto destacable que, en aquellos estudios en los que trabaja con datos experimentales, para mejorar la relación señalruido (Sannelli et al, 2009), se realiza un promediado de las características de la señal EEG sobre varios ensayos de diferentes sujetos. De este modo, obvian la variabilidad propia de cada sujeto en cuanto a los valores subjetivos de esas características y a las ventanas temporales en las que se producen, dando lugar a ICCs con baja precisión.…”

Section: Identificación Del Movimiento Voluntariounclassified

Metodología para la Creación de una Interfaz Cerebro-Computador Aplicada a la Identificación de la Intención de Movimiento

Castillo¹,

Serrano²,

Ibáñez³

et al. 2011

Revista Iberoamericana de Automática e Informática Industrial R

View full text Add to dashboard Cite

Resumen: Las Interfaces Cerebro-Computador proporcionan un canal para enviar órdenes al mundo exterior haciendo uso de medidas electrofisiológicas de la actividad cerebral. En este artículo se presenta la combinación de un método de selección de características y un algoritmo de clasificación probabilístico para construir el modelo predictivo de la intención anticipada de movimiento voluntario de pacientes con temblor a partir de un solo ensayo. Los resultados obtenidos muestran una potencial de discriminación del 70%, una tasa de error aceptable (6.6%) y una rápida respuesta (cada 250ms), lo que indica que esta combinación es una buena base para la construcción de ICCs que no requieran entrenamiento del usuario de forma personalizada, asíncrona y adaptativa.

show abstract

Improving BCI performance by task-related trial pruning

Cited by 21 publications

References 21 publications

Robust Common Spatial Filters with a Maxmin Approach

Robust Common Spatial Filters with a Maxmin Approach

On robust spatial filtering of EEG in nonstationary environments

Metodología para la Creación de una Interfaz Cerebro-Computador Aplicada a la Identificación de la Intención de Movimiento

Contact Info

Product

Resources

About