Improving visual evoked potential feature classification for person recognition using PCA and normalization

Palaniappan, Ramaswamy; Ravi, Kumar

doi:10.1016/j.patrec.2005.10.020

Cited by 60 publications

(35 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In literature, some low-passed filters have been used for EEG signal such as elliptic and Butterworth filter with second order to remove the noise from original signal [20,21]. In this work we have chosen Butterworth low-passed filter with cut-off frequency 6-30Hz as the pass-stop are maximally flat, which resolve in quality output signal for different band.…”

Section: A Pre-processing Of the Signalmentioning

confidence: 99%

Information-Theoretic Measures on Intrinsic Mode Function for the Individual Identification Using EEG Sensors

Kumari

Vaish

2015

IEEE Sensors J.

View full text Add to dashboard Cite

In spite of recent advances, the interest in extracting knowledge hidden in the electroencephalogram(EEG) signals is rapidly growing, as well as their application in the computational neuro engineering field such as mobile robot control, wheelchair control and person identification using brainwaves. The large number of methods for EEG feature extraction demands a good feature for every task. Digging up the most unique feature would be worth for identification of individual using EEG signal. This research presents a novel approach for feature extraction of electroencephalogram (EEG) signal using the Empirical mode decomposition (EMD) and information-theoretic-method (ITM). The EMD technique is applied to decompose an EEG signal into set of intrinsic mode function (IMF). These decomposed signals are of the same length and in the same time domain as the Original Signal. Hence, EMD method preserves varying frequencies in time. To measure the performance of the features, we have used Hybrid learning for classification where we have selected Learning Vector Quantization Neural Network (LVQ-NN) with fuzzy algorithm. Furthermore, to investigate the performance and accuracy of each subject over the different cognitive tasks based on Cohen's kappa coefficient. The results are compared with past methods in literature for feature extraction and classification methods. Results confirm that proposed features present a satisfactory performance.

show abstract

Section: A Pre-processing Of the Signalmentioning

confidence: 99%

Information-Theoretic Measures on Intrinsic Mode Function for the Individual Identification Using EEG Sensors

Kumari

Vaish

2015

IEEE Sensors J.

View full text Add to dashboard Cite

show abstract

“…The final classification accuracy on 20 subjects was 94.2%. In 2006, the same author proposed an improvement respect to his previous study from 2003 [20]. Background noise was reduced by means of Principal Component Analysis (PCA) and then an ensemble of classifiers, namely fuzzy logic, discriminant analysis and k-nearest neighbor (kNN) was used.…”

Section: Eeg-based Cognitive Biometrics: Related Workmentioning

confidence: 99%

Authentication of Brain-Computer Interface Users in Network Applications

López-Gordo

Ron-Angevín

Pelayo

2015

Advances in Computational Intelligence

View full text Add to dashboard Cite

Abstract. Cognitive biometrics aims to user authentication (or identification)by direct measure of electrophysiological signals as response to specific stimuli. In the literature, authentication paradigms for network applications are intended for healthy and independent users with complete control of their muscles. This excludes people with severe motor impairment, such as Brain-computer interface (BCI) users. Conversely, BCIs permit communication with users even in extreme impairment conditions, such as those suffering from locked-in syndrome or in advanced stage of Amyotrophic lateral sclerosis. The downside of BCIs is their very poor performance that, measured in terms of throughput and bit error rate, could lead to impracticable authentication. Specifically, current network applications require users to type long usernames and passwords formed with characters chosen from a large dataset. This forces long BCI sessions that users can not afford due to their heavy cognitive workload. In this paper we present some EEG-based authentication approaches and discuss some relevant aspects that a BCI-based authentication approach should consider for users with severe motor impairment.

show abstract

“…This technique helps to reduce the dimensionality, however retain the important features from the raw data by projecting the features in different basis [19]. According to Kaiser's rule, the eigenvectors with eigenvalues of more than 1.0 or log (eigenvalue) less than 1.0 can be considered to be selected as principal components (PC) and use as the input of the classifier [20].…”

Section: Feature Extractionmentioning

confidence: 99%

A preliminary study on in-vitro lung cancer detection using E-nose technology

Thriumani

Zakaria

Jeffree

et al. 2014

2014 IEEE International Conference on Control System, Computing and Engineering (ICCSCE 2014)

View full text Add to dashboard Cite

The existing clinical diagnostics for lung cancer are mostly based on physics, biochemical and imaging techniques. The use of electronic nose (E-nose) system to detect volatile organic compounds (VOCs) in lung cancer cells or exhaled air breath of a patient is expected to be able to classify different volatile components leading to the diagnosis of lung cancer at an early stage. In this preliminary study, a commercialized E-nose consists of an array of 32 conducting polymer sensors (Cyranose 320) was used to detect and discriminate the VOCs emitted from cancer cells which is A549 (lung cancer cell line) between MCF7 (breast cancer cell line). Blank medium was used to obtain controlled value. The VOC profiles of each sample were characterized using a classification algorithm called k-Nearest Neighbors (KNN) to test and benchmark the performance of Enose in identifying VOCs of lung cancer from different cancer cell lines. The E-nose with KNN classifier was able to classify the VOCs of lung cancer cell with over 90% successful accuracy in 30 seconds. This study can conclude that e-nose is capable to rapidly discriminate volatile organic compounds of cancerous cells which generated during cell growth.

show abstract

Improving visual evoked potential feature classification for person recognition using PCA and normalization

Cited by 60 publications

References 17 publications

Information-Theoretic Measures on Intrinsic Mode Function for the Individual Identification Using EEG Sensors

Information-Theoretic Measures on Intrinsic Mode Function for the Individual Identification Using EEG Sensors

Authentication of Brain-Computer Interface Users in Network Applications

A preliminary study on in-vitro lung cancer detection using E-nose technology

Contact Info

Product

Resources

About