EEG signal classification using PCA, ICA, LDA and support vector machines

By Abdulhamit Subasi, M. Ismail Gursoy. Expert systems with applications, 2010

1,193 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Signal Processing

View Paper: https://www.semanticscholar.org/paper/669180d28222c5c141ee3c0b4f0a735105a12350

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Usha R. Acharya
2. Jessica Clark
3. Xiaojun Chang
4. Oliver Faust
5. Amir Adeli
6. Nick S. Jones
7. José Luis Contreras-Vidal
8. Alexander Craik

In Cognitive Neuroscience

1. Usha R. Acharya
2. Ben D. Fulcher
3. Nick S. Jones
4. Oliver Faust
5. Amir Adeli
6. Hojjat Adeli
7. José Luis Contreras-Vidal
8. Alexander Craik

In Signal Processing

1. Ben D. Fulcher
2. Nick S. Jones
3. Usha R. Acharya
4. Hojjat Adeli
5. José Luis Contreras-Vidal
6. Alexander Craik
7. Xiaojun Chang
8. Mubarak Shah

Citations in the corpus

• Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques (2015, methodology): “The classifiers’ performances were computed using the most commonly used parameters, are the accuracy, sensitivity, specificity, precision, and Kappa statistic [38].”
• Making Sense of Spatio-Temporal Preserving Representations for EEG-Based Human Intention Recognition (2020, methodology): “For the classifier components, traditional methods like linear discriminant analysis (LDA), support vector machine (SVM), and tree ensemble algorithms, such as random forest (RF) and XGboost, are commonly used in EEG classification [18], [27], [28].”
• Deep Learning Human Mind for Automated Visual Classification (2016, methodology): “Existing works, such as [24, 1], employing Support Vec-”
• Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis. (2015, positive): “The following features are used for the two class classification of epilepsy: Approximate Entropy (ApEn) on DWT coefficients [40,41], relative wavelet energy [42], line length feature [43], Principal Component Analysis (PCA), Independent Component Analysis (ICA) and Linear Discriminant Analysis (LDA”
• Highly comparative time-series analysis: the empirical structure of time series and their methods (2013, methodology): “75 per cent using re-sampled subsegments of this dataset [13].”
• Dimensionality Reduction via Matrix Factorization for Predictive Modeling from Large, Sparse Behavioral Data (2015, methodology): “9 Relatedly, SVD is also used simply to improve the “manageability” of the feature space, as in Thorleuchter et al. (2012). Unfortunately, in the context of the data on which this paper focuses, if the original matrix A is sparse, the resulting L and R matrices from SVD will not necessarily be spars”
• Deep learning for electroencephalogram (EEG) classification tasks: a review (2019, methodology): “3 analysis (PCA) and local Fisher’s discriminant analysis (LFDA) are typically used to reduce dimensionality of the features [5]; classic supervised learning methods such as linear discriminant analysis (LDA), support vector machines (SVM), and decision trees are common in neural classification [6, ”