A principal component analysis ensemble classifier for P300 speller applications

Elsawy, Amr; Eldawlatly, Seif; Taher, Mohamed; Aly, Gamal M.

doi:10.1109/ispa.2013.6703782

Cited by 12 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where M is the number of classifiers, the score of each classifier is score i and a i is the classifier weight which is based on the mean of the eigenvalues of the corresponding principal component [4]. The predicted row of the target symbol is the row with maximum final score across all rows ( ) row row score r max = (6) and, similarly, the predicted column of the target symbol is the column with maximum final score across all columns ( ) col col score c max = (7)…”

Section: Feature Extraction and Classification Methodsmentioning

confidence: 99%

“…In addition, we reduced the number of trials for each symbol to 10 trials compared to 15 trials which we used in our previous studies [4,5]. For each of the 6 subjects, we recorded a labeled dataset of 20 characters as training data and an unlabeled online testing dataset of 12 symbols (i.e.…”

Section: A Datasetsmentioning

confidence: 99%

“…In both applications, we utilize a principal component analysis (PCA) ensemble classifier which we have recently introduced that has low computational complexity and achieves acceptable classification accuracy [4,5]. In this paper, we use PCA for feature extraction and Fisher's Linear Discriminant for classification.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

P300-based applications for interacting with smart mobile devices

Elsawy

Eldawlatly

2015

2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)

Self Cite

View full text Add to dashboard Cite

Smart mobile devices are widely used nowadays in daily life activities. Interacting with these devices, however, requires users to use their hands to touch the screen of the device which deprives users with hand disabilities from using them. In this paper, we introduce a Brain-Computer Interface (BCI) system that allows users to interact with smart mobile devices using electroencephalography (EEG) signals. Two applications are introduced for Android-based devices: RunApp and ImgView. RunApp enables users to select and run any installed application on the device while ImgView allows viewing and manipulating images. Both applications rely on the P300 signal paradigm. We utilize a computationally-efficient Principal Component Analysis (PCA) ensemble classifier to identify P300 signals. Results demonstrate the efficacy of the introduced applications using limited training data and limited number of trials with an average online accuracy of 79.17±13.69% for RunApp and 87.5±8.74% for ImgView for 6 different subjects. In addition, we demonstrate the cross-subject generalization capability of the algorithm where we got average online accuracy of 54.17±20.2.4% for RunApp and 55.56±11.38% for ImgView. These results demonstrate the feasibility of running BCI applications on smart mobile devices.

show abstract

Section: Feature Extraction and Classification Methodsmentioning

confidence: 99%

Section: A Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

P300-based applications for interacting with smart mobile devices

Elsawy

Eldawlatly

2015

2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The classification is based on the use of machine algorithms of feature selection process or feature reduction process. Reduce the redundancy and irrelevant features from a data set having correlated variables to avoid the error on a validation the data set [5]. The process of decimation has always been proved to be useful as it provides acceptable classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

Classification of Red Blood Cells using Principal Component Analysis Technique

Alkrimi¹,

Tome²,

George³

2019

EJERS

View full text Add to dashboard Cite

Principal component analysis (PCA) is based feature reduction that reduces the correlation of features. In this research, a novel approach is proposed by applying the PCA technique on various morphologies of red blood cells (RBCs). According to hematologists, this method successfully classified 40 different types of abnormal RBCs. The classification of RBCs into various distinct subtypes using three machine learning algorithms is important in clinical and laboratory tests for detecting blood diseases. The most common abnormal RBCs are considered as anemic. The RBC features are sufficient to identify the type of anemia and the disease that caused it. Therefore, we found that several features extracted from RBCs in the blood smear images are not significant for classification when observed independently but are significant when combined with other features. The number of feature vectors is reduced from 271 to 8 as time resuming in training and accuracy percentage increased to 98%.

show abstract

Control of the 6-Axis Robot Using a Brain-Computer Interface Based on Steady State Visually Evoked Potential (SSVEP)

Kubacki

Milecki

2019

Lecture Notes in Mechanical Engineering

View full text Add to dashboard Cite

A principal component analysis ensemble classifier for P300 speller applications

Cited by 12 publications

References 12 publications

P300-based applications for interacting with smart mobile devices

P300-based applications for interacting with smart mobile devices

Classification of Red Blood Cells using Principal Component Analysis Technique

Control of the 6-Axis Robot Using a Brain-Computer Interface Based on Steady State Visually Evoked Potential (SSVEP)

Contact Info

Product

Resources

About