EEG features extraction using neuro-fuzzy systems and shift-invariant wavelet transforms for epileptic seizures diagnosing

Akhbardeh, Alireza; Farrokhi, Mohammad; Tehrani, A. Vahabian

doi:10.1109/iembs.2004.1403203

Cited by 16 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The compression of waves using wavelets and their performance evaluation is discussed in [2]. A Neuro-Fuzzy system with Invariant Wavelets is used to classify EEG spikes in [3], however, the system cannot be extended to a more general system. In [4], a new feature extraction process for time series data using DWT (Discrete Wavelet Transform) and DFT (Discrete Fourier Transform) has been employed but it can be used only for a specific purpose.…”

Section: Related Workmentioning

confidence: 99%

Generic Feature Extraction for Classification using Fuzzy C - Means Clustering

Srinivasa

Singh²,

Thomas³

et al. 2005

2005 3rd International Conference on Intelligent Sensing and Information Processing

View full text Add to dashboard Cite

Knowledge Discovery and Data Mining(KDD) process includes preprocessing, transformation, data mining and knowledge extraction. The two important tasks ofdata mining are clustering and classification. In this paper, we propose a generic feature extraction for classification using Fuzzy CMeans(FCM) clustering. The raw data is preprocessed, normalized and then data points are clustered using fuzzy cmeans technique. Feature vectors for all the classes are generated by extracting the most relevant features from the corresponding clusters and used for further classification.Artificial Neural Network and Support Vector Machines are used to perform the classification task. Experiments are conducted on four datasets and the accuracy obtained by performing specific feature extraction for a particular data set is compared with generic feature extraction scheme. The algorithm performs relatively well with respect to classification results when compared with the specific feature extraction technique.

show abstract

Section: Related Workmentioning

confidence: 99%

Generic Feature Extraction for Classification using Fuzzy C - Means Clustering

Srinivasa

Singh²,

Thomas³

et al. 2005

2005 3rd International Conference on Intelligent Sensing and Information Processing

View full text Add to dashboard Cite

show abstract

“…In this work we used compactly supported Biorthogonal Spline wavelets with p=2, p =4 to find wavelet coefficient of every BCG cycle [ ] x n at level 6 using the iterative FWT algorithm [6,7,8,9]. Our practical experiences showed that using p=2, p =4 is enough and the most important features of the BCG waveforms were saved at level 6 of iteration FWT, as maximum level of decreasing signal dimension (N) from 250 to 4.…”

Section: Resultsmentioning

confidence: 99%

“…The simplest method is dyadic. By using it, the fast wavelet transform can be presented as: [6,7,8,9] :…”

Section: B-1-wavelets As Time-frequency Analysis Methodsmentioning

confidence: 99%

“…The suggested high-resolution method for features computing uses a special kind of wavelet, called Shift-Invariant Biorthonormal Wavelet Transform [6,7,8,9]. The properties of this kind of wavelet are good for our application because we would like to reduce the dimension of the BCG cycle optimally.…”

Section: B Computing Bcg Features Based On Shift-invariant Biorthonomentioning

confidence: 99%

“…A transform with a scale parameter is used, digitized around a k sequence [6,7,8,9]: If the decomposition and reconstruction filters of filter bank are different, the resulting wavelet basis is nonorthogonal. The stability of this discrete wavelet basis does not degrade by increasing decomposition level in iterative fast wavelet transform.…”

Section: B-2-fast Wavelet Transform (Fwt)mentioning

confidence: 99%

See 2 more Smart Citations

The heart disease diagnosing system based on force sensitive chair's measurement, biorthogonal wavelets and neural networks

Akhbardeh

Junnila

Koivuluoma

et al.

Proceedings, 2005 IEEE/ASME International Conference on Advanced Intelligent Mechatronics.

Self Cite

View full text Add to dashboard Cite

The Heart Disease Diagnosing (HDD) system consists of a sensitive movement EMFI-film sensor installed under the upholstery of a chair. Whilst a man rests on the chair, this force sensitive sensor produces a single electrical signal containing components reflective of cardiac-Ballistocardiogram (BCG), respiratory, and body movement related motion. Among different measurements of body activities, BCG has an interesting property that no electrodes are needed to be attached to the body during recording. This makes it suitable for evaluation of mans heart condition in any place such as home, car, or office. This paper describes briefly our developed HDD system and especially a combined intelligent signal processing method to detect, extract features, and finally cluster BCG cycles. The system is designed to assist medical doctors to diagnose heart diseases of subject under test. Indeed, it is a fully automatic system which is not sensitive to any BCG latency as well as non-linear disturbance. It uses high resolution Biorthogonal wavelet transform to extract essential BCG features and then clusters them using Artificial Neural Networks (ANNs). Some evaluations using recordings from normal young, normal old and abnormal old volunteers indicated that our combined method is reliable and has high performance.

show abstract

An Intelligent Ballistocardiographic Chair using a Novel SF-ART Neural Network and Biorthogonal Wavelets

et al. 2006

View full text Add to dashboard Cite

This paper presents a comparative analysis of novel supervised fuzzy adaptive resonance theory (SF-ART), multilayer perceptron (MLP) and Multi Layer Perceptrons (MLP) neural networks over Ballistocardiogram (BCG) signal recognition. To extract essential features of the BCG signal, we applied Biorthogonal wavelets. SF-ART performs classification on two levels. At first level, pre-classifier which is self-organized fuzzy ART tuned for fast learning classifies the input data roughly to arbitrary (M) classes. At the second level, post-classification level, a special array called Affine Look-up Table (ALT) with M elements stores the labels of corresponding input samples in the address equal to the index of fuzzy ART winner. However, in running (testing) mode, the content of an ALT cell with address equal to the index of fuzzy ART winner output will be read. The read value declares the final class that input data belongs to. In this paper, we used two well-known patterns (IRIS and Vowel data) and a medical application (Ballistocardiogram data) to evaluate and check SF-ART stability, reliability, learning speed and computational load. Initial tests with BCG from six subjects (both healthy and unhealthy people) indicate that the SF-ART is capable to perform with a high classification performance, high learning speed (elapsed time for learning around half second), and very low computational load compared to the well-known neural networks such as MLP which needs minutes to learn the training material. Moreover, to extract essential features of the BCG signal, we applied Biorthogonal wavelets. The applied wavelet transform requires no prior knowledge of the statistical distribution of data samples.

show abstract

EEG features extraction using neuro-fuzzy systems and shift-invariant wavelet transforms for epileptic seizures diagnosing

Cited by 16 publications

References 3 publications

Generic Feature Extraction for Classification using Fuzzy C - Means Clustering

Generic Feature Extraction for Classification using Fuzzy C - Means Clustering

The heart disease diagnosing system based on force sensitive chair's measurement, biorthogonal wavelets and neural networks

An Intelligent Ballistocardiographic Chair using a Novel SF-ART Neural Network and Biorthogonal Wavelets

Contact Info

Product

Resources

About