Classification of EEG signals using Dempster Shafer theory and a k-nearest neighbor classifier

Yazdani, Amirmehdi; Ebrahimi, Touradj; Hoffmann, Ulrich

doi:10.1109/ner.2009.5109299

Cited by 69 publications

(33 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, WT-based analysis is highly effective, because it deals better with the non-stationary behavior of EEG signals than other methods. Wavelet-based features, including wavelet entropy [5], wavelet coefficients [2], and wavelet statistical features (mean, median, and standard deviations) have been reported for normal EEG analysis as well as in clinical applications [6,7]. Details on the performance of time domain, frequency domain and wavelet-based techniques employed in EEG classification for cognitive tasks and/or BCI applications are provided in the related work section and the classification accuracy of these techniques are provided in the discussion section.…”

Section: Introductionmentioning

confidence: 99%

Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques

Amin

Malik

Ahmad

et al. 2015

Australas Phys Eng Sci Med

273

View full text Add to dashboard Cite

This paper describes a discrete wavelet transform-based feature extraction scheme for the classification of EEG signals. In this scheme, the discrete wavelet transform is applied on EEG signals and the relative wavelet energy is calculated in terms of detailed coefficients and the approximation coefficients of the last decomposition level. The extracted relative wavelet energy features are passed to classifiers for the classification purpose. The EEG dataset employed for the validation of the proposed method consisted of two classes: (1) the EEG signals recorded during the complex cognitive task--Raven's advance progressive metric test and (2) the EEG signals recorded in rest condition--eyes open. The performance of four different classifiers was evaluated with four performance measures, i.e., accuracy, sensitivity, specificity and precision values. The accuracy was achieved above 98 % by the support vector machine, multi-layer perceptron and the K-nearest neighbor classifiers with approximation (A4) and detailed coefficients (D4), which represent the frequency range of 0.53-3.06 and 3.06-6.12 Hz, respectively. The findings of this study demonstrated that the proposed feature extraction approach has the potential to classify the EEG signals recorded during a complex cognitive task by achieving a high accuracy rate.

show abstract

Section: Introductionmentioning

confidence: 99%

Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques

Amin

Malik

Ahmad

et al. 2015

Australas Phys Eng Sci Med

273

View full text Add to dashboard Cite

show abstract

“…Here, EEG signals are recorded while performing three mental tasks i.e., imagination of left hand movement, right hand movement and word generation. EEG signal classification approach has been proposed in [34] using Dempster-Shafer (D-S) theory and K-Nearest Neighbor (KNN) classifier. In the study, to obtain EEG recordings, five different metal tasks have been performed.Here, the authors have compared three different KNN classifiers namely, voting KNN, distance weighted KNN, and KNN classifier based on D-S evidence theory.…”

Section: Related Workmentioning

confidence: 99%

In-Vehicle Stress Monitoring Based on EEG Signal

Begum¹,

Ahmed²

2017

IJERA

View full text Add to dashboard Cite

In recent years, improved road safety by monitoring human factors i.e., stress, mental load, sleepiness, fatigue etc. of vehicle drivers has been addressed in a number of studies. Due to the individual variations and complex dynamic in-vehicle environment systems that can monitor such factors of a driver while driving is challenging. This paper presents a drivers' stress monitoring system based on electroencephalography (EEG) signals enabling individual---focused computational approach that can generate automatic decision. Here, a combination of different signal processing i.e., discrete wavelet transform, largest Lyapunov exponent (LLE) and modified covariance have been applied to extract key features from the EEG signals. Hybrid classification approach Fuzzy-CBR (case-based reasoning) is used for decision support. The study has focused on both long and short-term temporal assessment of EEG signals enabling monitoring in different time intervals. In short time interval, which requires complex computations, the classification accuracy using the proposed approach is 79% compare to a human expert. Accuracy of EEG in developing such system is also compared with other reference signals e.g., Electrocardiography (ECG), Finger temperature, Skin conductance, and Respiration. The results show that in decision making the system can handle individual variations and provides decision in each minute time interval.

show abstract

“…The classifier proves to be effective in reducing the misclassification when the number of samples in training dataset is large. Another advantage of the KNN method over many other supervised learning methods like support vector machine (SVM), decision tree, neural network, etc., is that it can easily deal with problems in which the class size is three and higher [44,45].…”

Section: Classificationmentioning

confidence: 99%