EEG feature extraction and selection techniques for epileptic detection: A comparative study

Hussein, Ramy; Mohamed, Amr; Shahan, Khaled; Mohamed, Abduljalil

doi:10.1109/isci.2013.6612397

Cited by 8 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it has complexity C JCLO = N W F L · C t , where C t is the complexity of solving the optimization problem in (20). For DCL algorithm, it solves the optimization problem in (21) N W F L times to get the application layer parameters, then solves the optimization problem in (22) once to get the MAC-PHY layer parameters. Therefore, it has complexity C DCL = N W F L · C p + C ts , where C p is the complexity of solving the optimization problem in (21) and C ts is the complexity of solving the optimization problem in (22).…”

Section: Simulation Resultsmentioning

confidence: 99%

“…For DCL algorithm, it solves the optimization problem in (21) N W F L times to get the application layer parameters, then solves the optimization problem in (22) once to get the MAC-PHY layer parameters. Therefore, it has complexity C DCL = N W F L · C p + C ts , where C p is the complexity of solving the optimization problem in (21) and C ts is the complexity of solving the optimization problem in (22). Regarding JCL-ESL algorithm, it solves the optimization problem in (24) N W F L times.…”

Section: Simulation Resultsmentioning

confidence: 99%

“…Regarding the thresholding-based DWT compression, it is applied using one of the wavelet families, categories and decomposition levels as in [22].…”

Section: Application Layermentioning

confidence: 99%

“…The optimization variables in (22) are the transmission rates r i . It can be solved using the conventional convex optimization methods [26].…”

Section: A Disjoint Cross-layer Algorithm (Dcl)mentioning

confidence: 99%

See 3 more Smart Citations

Energy-aware cross-layer optimization for EEG-based wireless monitoring applications

Awad

Hussein

Mohamed

et al. 2013

38th Annual IEEE Conference on Local Computer Networks

Self Cite

View full text Add to dashboard Cite

Body Area Sensor Networks (BASNs) for healthcare applications have gained significant research interests recently due to the growing number of patients with chronic diseases requiring constant monitoring. Because of the limited power source and small form factors, BASNs have distinguished design and operational challenges, particularly focusing on energy optimization. In this paper, an Energy-Delay-Distortion cross-layer design that aims at minimizing the total energy consumption subject to data delay deadline and distortion threshold constraints is proposed. The optimal encoding and transmission energy are computed to minimize the total energy consumption in a delay constrained wireless body area sensor network. This cross-layer framework is proposed, across Application-MAC-Physical layers, under a constraint that all successfully received packets must have their delay smaller than their corresponding delay deadline and with maximum distortion less than the application distortion threshold. Due to the complexity of the optimal-proposed solution, sub-optimal solutions are also proposed. These solutions have close-to-optimal performance with lower complexity. In this context, there is complexity/energy-consumption trade-off, as shown in the simulation results.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Section: Simulation Resultsmentioning

confidence: 99%

“…Regarding the thresholding-based DWT compression, it is applied using one of the wavelet families, categories and decomposition levels as in [22].…”

Section: Application Layermentioning

confidence: 99%

“…The optimization variables in (22) are the transmission rates r i . It can be solved using the conventional convex optimization methods [26].…”

Section: A Disjoint Cross-layer Algorithm (Dcl)mentioning

confidence: 99%

See 2 more Smart Citations

Energy-aware cross-layer optimization for EEG-based wireless monitoring applications

Awad

Hussein

Mohamed

et al. 2013

38th Annual IEEE Conference on Local Computer Networks

Self Cite

View full text Add to dashboard Cite

show abstract

“…The aforementioned set of wavelet families can be applied for the feature extraction purpose. To obtain maximum classification accuracy, Daubechies 6 with 7 levels of decomposition is utilized [24]. Classical statistics (maximum, minimum, mean and standard deviation) are obtained from each wavelet subband and combined together to devise the feature vector, which in turn used in the classification process.…”

Section: Introductionmentioning

confidence: 99%

Performance evaluation for compression-accuracy trade-off using compressive sensing for EEG-based epileptic seizure detection in wireless tele-monitoring

Abualsaud

Mahmuddin

Hussein

et al. 2013

2013 9th International Wireless Communications and Mobile Computing Conference (IWCMC)

Self Cite

View full text Add to dashboard Cite

Brain is the most important part in the human body controlling muscles and nerves; Electroencephalogram (EEG) signals record brain electric activities. EEG signals capture important information pertinent to different physiological brain states. In this paper, we propose an efficient framework for evaluating the power-accuracy trade-off for EEG-based compressive sensing and classification techniques in the context of epileptic seizure detection in wireless tele-monitoring. The framework incorporates compressive sensing-based energyefficient compression, and noisy wireless communication channel to study the effect on the application accuracy. Discrete cosine transform (DCT) and compressive sensing are used for EEG signals acquisition and compression. To obtain low-complexity energy-efficient, the best data accuracy with higher compression ratio is sought. A reconstructed algorithm derived from DCT of daubechie's wavelet 6 is used to decompose the EEG signal at different levels. DCT is combined with the best basis function neural networks for EEG signals classification. Extensive experimental work is conducted, utilizing four classification models. The obtained results show an improvement in classification accuracies and an optimal classification rate of about 95% is achieved when using NN classifier at 85% of CR in the case of no SNR value. The satisfying results demonstrate the effect of efficient compression on maximizing the sensor lifetime without affecting the application's accuracy.

show abstract

Adaptive energy-aware encoding for DWT-based wireless EEG tele-monitoring system

Hussein

Awad

El-Sherif

et al. 2013

2013 IEEE Digital Signal Processing and Signal Processing Education Meeting (DSP/SPE)

View full text Add to dashboard Cite

EEG feature extraction and selection techniques for epileptic detection: A comparative study

Cited by 8 publications

References 13 publications

Energy-aware cross-layer optimization for EEG-based wireless monitoring applications

Energy-aware cross-layer optimization for EEG-based wireless monitoring applications

Performance evaluation for compression-accuracy trade-off using compressive sensing for EEG-based epileptic seizure detection in wireless tele-monitoring

Adaptive energy-aware encoding for DWT-based wireless EEG tele-monitoring system

Contact Info

Product

Resources

About