Classification of BMD and schizophrenic patients using geometrical analysis of their EEG signal covariance matrices

Alimardani, Fatemeh; Boostani, Reza; Taghavi, Mahsa

doi:10.1109/tsp.2015.7296459

Cited by 3 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Offline outlier removal is useful to estimate reliable centers of classes for classification, but results are better when a potato is applied for each class [26], [29]- [31], rather than on all matrices [24], [25] that can lead to the removal of matrices close to the center of their class but far from the mean of all matrices [53]. While the performance improvement brought by outlier removal in the reference estimate has not necessarily lead to significant improvements in controlled environments [26], [31], it certainly contributed positively in more adverse settings [11], [12].…”

Section: A Robust Mean By Offline Outlier Removalmentioning

confidence: 99%

“…1. Due to its simplicity and efficiency, the RP has been intensively used for i) online artifact rejection for P300-based BCI spellers [18]- [20] and games [21], ii) offline rejection before the statistical analysis of cognitive assessments [22], [23], iii) offline rejection before the classification of psychiatric disorders [24], [25] or motor imagery BCI [26], iv) offline rejection in the source space after applying a blind source separation (BSS) [27], v) rejection for a reliable estimation of class centers of a SSVEP-based BCI, online updated [28], or offline estimated and then used for an offline [29], [30] or for an online [31] classification. However, in all these cases, the SQI is used as a binary output resulting from the z-score thresholding and its continuous range of values is not fully exploited.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Riemannian Potato Field: A Tool for Online Signal Quality Index of EEG

Barthélemy

Mayaud

Ojeda

et al. 2019

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Electroencephalographic (EEG) recordings are contaminated by instrumental, environmental, and biological artifacts, resulting in low signal-to-noise ratio. Artifact detection is a critical task for real-time applications where the signal is used to give a continuous feedback to the user. In these applications, it is therefore necessary to estimate online a signal quality index (SQI) in order to stop the feedback when the signal quality is unacceptable. In this article we introduce the Riemannian Potato Field (RPF) algorithm as such SQI. It is a generalization and extension of the Riemannian Potato, a previously published real-time artifact detection algorithm, whose performance is degraded as the number of channels increases. The RPF overcomes this limitation by combining the outputs of several smaller potatoes into a unique SQI resulting in a higher sensitivity and specificity, regardless of the number of electrodes. We demonstrate these results on a clinical dataset totalizing more than 2200 hours of EEG recorded at home, that is, in a non-controlled environment.

show abstract

Section: A Robust Mean By Offline Outlier Removalmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Riemannian Potato Field: A Tool for Online Signal Quality Index of EEG

Barthélemy

Mayaud

Ojeda

et al. 2019

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

Classification of Bipolar Disorder and Schizophrenia Using Steady-State Visual Evoked Potential Based Features

et al. 2018

View full text Add to dashboard Cite

Enhancing Adaboost performance in the presence of class-label noise: A comparative study on EEG-based classification of schizophrenic patients and benchmark datasets

Pouya,

Boostani,

Sabeti

2024

IDA

View full text Add to dashboard Cite

The performance of Adaboost is highly sensitive to noisy and outlier samples. This is therefore the weights of these samples are exponentially increased in successive rounds. In this paper, three novel schemes are proposed to hunt the corrupted samples and eliminate them through the training process. The methods are: I) a hybrid method based on K-means clustering and K-nearest neighbor, II) a two-layer Adaboost, and III) soft margin support vector machines. All of these solutions are compared to the standard Adaboost on thirteen Gunnar Raetsch’s datasets under three levels of class-label noise. To test the proposed method on a real application, electroencephalography (EEG) signals of 20 schizophrenic patients and 20 age-matched control subjects, are recorded via 20 channels in the idle state. Several features including autoregressive coefficients, band power and fractal dimension are extracted from EEG signals of all participants. Sequential feature subset selection technique is adopted to select the discriminative EEG features. Experimental results imply that exploiting the proposed hunting techniques enhance the Adaboost performance as well as alleviating its robustness against unconfident and noisy samples over Raetsch benchmark and EEG features of the two groups.

show abstract

Classification of BMD and schizophrenic patients using geometrical analysis of their EEG signal covariance matrices

Cited by 3 publications

References 16 publications

The Riemannian Potato Field: A Tool for Online Signal Quality Index of EEG

The Riemannian Potato Field: A Tool for Online Signal Quality Index of EEG

Classification of Bipolar Disorder and Schizophrenia Using Steady-State Visual Evoked Potential Based Features

Enhancing Adaboost performance in the presence of class-label noise: A comparative study on EEG-based classification of schizophrenic patients and benchmark datasets

Contact Info

Product

Resources

About