An automatic mobile-health based approach for EEG epileptic seizures detection

Menshawy, Mohamed El; Benharref, Abdelghani; Serhani, Mohamed Adel

doi:10.1016/j.eswa.2015.04.068

Cited by 59 publications

(25 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To conduct a comparison, cross-correlation

X C o r r

and peak signal to noise ratio

(P S N R)

were performed between the recorded EEG and noise-free EEG using the AICA–WT, WT and AICA rejection techniques respectively. The correlation

X C o r r

and

P S N R

between the EEG signal of interest

x

and the denoised EEG

y

is expressed in Equations (14) and (15) respectively [96,97]:

X C o r r (x, y) = \frac{\sum (x - \overset{x}{true}) (y - \overset{y}{true})}{\sqrt{\sum {(x - \overset{x}{true})}^{2} {(normaly - \overset{y}{true})}^{2}}}

P S N R = 20 \log [\frac{m a x [x]}{R M S E}]

where

\bar{x}

and

\bar{y}

are the mean of the recorded and noise-free EEG

x

and

y

, respectively, and

N

is the length of the selected window and RMSE is the root-mean-square error that can be calculated using Equation (16):

R M S E = \sqrt{\frac{1}{N} \sum_{i = 1}^{N} {(x - y)}^{2}}

…”

Section: Methodsmentioning

confidence: 99%

Automatic Artifact Removal in EEG of Normal and Demented Individuals Using ICA–WT during Working Memory Tasks

Al-Qazzaz

Ali

Ahmad

et al. 2017

Sensors

View full text Add to dashboard Cite

Characterizing dementia is a global challenge in supporting personalized health care. The electroencephalogram (EEG) is a promising tool to support the diagnosis and evaluation of abnormalities in the human brain. The EEG sensors record the brain activity directly with excellent time resolution. In this study, EEG sensor with 19 electrodes were used to test the background activities of the brains of five vascular dementia (VaD), 15 stroke-related patients with mild cognitive impairment (MCI), and 15 healthy subjects during a working memory (WM) task. The objective of this study is twofold. First, it aims to enhance the recorded EEG signals using a novel technique that combines automatic independent component analysis (AICA) and wavelet transform (WT), that is, the AICA–WT technique; second, it aims to extract and investigate the spectral features that characterize the post-stroke dementia patients compared to the control subjects. The proposed AICA–WT technique is a four-stage approach. In the first stage, the independent components (ICs) were estimated. In the second stage, three-step artifact identification metrics were applied to detect the artifactual components. The components identified as artifacts were marked as critical and denoised through DWT in the third stage. In the fourth stage, the corrected ICs were reconstructed to obtain artifact-free EEG signals. The performance of the proposed AICA–WT technique was compared with those of two other techniques based on AICA and WT denoising methods using cross-correlation XCorr and peak signal to noise ratio (PSNR) (ANOVA, p ˂ 0.05). The AICA–WT technique exhibited the best artifact removal performance. The assumption that there would be a deceleration of EEG dominant frequencies in VaD and MCI patients compared with control subjects was assessed with AICA–WT (ANOVA, p ˂ 0.05). Therefore, this study may provide information on post-stroke dementia particularly VaD and stroke-related MCI patients through spectral analysis of EEG background activities that can help to provide useful diagnostic indexes by using EEG signal processing.

show abstract

“…To conduct a comparison, cross-correlation

X C o r r

and peak signal to noise ratio

(P S N R)

were performed between the recorded EEG and noise-free EEG using the AICA–WT, WT and AICA rejection techniques respectively. The correlation

X C o r r

and

P S N R

between the EEG signal of interest

x

and the denoised EEG

y

is expressed in Equations (14) and (15) respectively [96,97]:

X C o r r (x, y) = \frac{\sum (x - \overset{x}{true}) (y - \overset{y}{true})}{\sqrt{\sum {(x - \overset{x}{true})}^{2} {(normaly - \overset{y}{true})}^{2}}}

P S N R = 20 \log [\frac{m a x [x]}{R M S E}]

where

\bar{x}

and

\bar{y}

are the mean of the recorded and noise-free EEG

x

and

y

, respectively, and

N

is the length of the selected window and RMSE is the root-mean-square error that can be calculated using Equation (16):

R M S E = \sqrt{\frac{1}{N} \sum_{i = 1}^{N} {(x - y)}^{2}}

…”

Section: Methodsmentioning

confidence: 99%

Automatic Artifact Removal in EEG of Normal and Demented Individuals Using ICA–WT during Working Memory Tasks

Al-Qazzaz

Ali

Ahmad

et al. 2017

Sensors

View full text Add to dashboard Cite

show abstract

“…El Menshawy et al [14] have developed an algorithm for automated detection and analysis of epileptic seizures using signal processing techniques. Using MATLAB, they have also used feature extraction to reduce the vector space.…”

Section: Related Workmentioning

confidence: 99%

Epilepsy Detecting and Halting Mechanism Using Wireless Sensor Networks

Basu

Kumar²,

Shanmugam³

2018

ELS

View full text Add to dashboard Cite

Epilepsy is a condition that affects thousands of people worldwide. In the laboratory setting, it becomes difficult to monitor patients and analyze when the next seizure would recur. Although algorithms have been proposed for deriving when the next seizure is probable, it is difficult to generalize such models for the various types of epilepsy that are occurring every day. A more promising solution is the use of Wireless Sensor Networks (WSNs) that is proposed to simulate small electrodes used in EEG that will be placed on the scalp of the patient as a wearable device along with a portable kit that is capable of monitoring the patient in both ambulatory and resting condition. As much as a detection system is required for epilepsy, a halting mechanism is also needed to prevent such high flow of bio-electrical signals in the brain during seizures. It is estimated that millions of brain cells die during epileptic seizures, which can prove detrimental or even fatal in some cases. In order to overcome this, an IoTbased epilepsy detection and halting system with wireless sensor networks and focal cooling mechanism has been proposed in order to regionally cool the regions of the brain when a seizure is probable or suddenly occurs.

show abstract

“…The wide diffusion of mobile technologies and the increasing capabilities of mobile computing devices caused an increased interest in designing, implementing and testing innovative applications running on mobile devices to provide a wide range of useful services. Im the medical care scenario, some efforts [17,21,24] have been devoted on this appealing research. In [17], a distributed end-to-end pervasive healthcare system utilizing neural network computations for diagnosing diabetes was developed in small mobile devices.…”

Section: Related Workmentioning

confidence: 99%

“…In [17], a distributed end-to-end pervasive healthcare system utilizing neural network computations for diagnosing diabetes was developed in small mobile devices. [21] developed a new mobilebased approach to automatically detect seizures, using k-means as unsupervised classification technique. [24] have presented Generalized Discriminant Analysis and Least Square Support Vector Machine models to diagnose the diabetes disease.…”

Section: Related Workmentioning

confidence: 99%

Exploiting clustering algorithms in a multiple-level fashion: A comparative study in the medical care scenario

Cerquitelli

Chiusano

Xiao

2016

Expert Systems with Applications

View full text Add to dashboard Cite

Clustering real-world data is a challenging task, since many real-data collections are characterized by an inherent sparseness and variable distribution. An appealing domain that generates such data collections is the medical care scenario where collected data include a large cardinality of patient records and a variety of medical treatments usually adopted for a given disease pathology. This paper proposes a two-phase data mining methodology to iteratively analyze different dataset portions and locally identify groups of objects with common properties. Discovered cohesive clusters are then analyzed using sequential patterns to characterize temporal relationships among data features. To support an automatic classification of a new data objects within one of the discovered groups, a classification model is created starting from the computed cluster set. A mobile application has been also designed and developed to visualize and update data under analysis as well as categorizing new unlabeled records. A comparative study has been conducted on real datasets in the medical care scenario using diverse clustering algorithms. Results were compared in terms of cluster quality, execution time, classification performance and discovered sequential patterns. The experimental evaluation showed the effectiveness of MLC to discover interesting knowledge items and to easily exploit them through a mobile application. Results have been also discussed from a medical perspective.keywords: Cluster analysis, data with a variable distribution, diabetic patient treatments, multiple-level method, comparison.

show abstract

An automatic mobile-health based approach for EEG epileptic seizures detection

Cited by 59 publications

References 32 publications

Automatic Artifact Removal in EEG of Normal and Demented Individuals Using ICA–WT during Working Memory Tasks

Automatic Artifact Removal in EEG of Normal and Demented Individuals Using ICA–WT during Working Memory Tasks

Epilepsy Detecting and Halting Mechanism Using Wireless Sensor Networks

Exploiting clustering algorithms in a multiple-level fashion: A comparative study in the medical care scenario

Contact Info

Product

Resources

About