2018
DOI: 10.48550/arxiv.1803.09848
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Epileptic Seizure Detection: A Deep Learning Approach

Abstract: Epilepsy is the second most common brain disorder after migraine. Automatic detection of epileptic seizures can considerably improve the patients' quality of life. Current Electroencephalogram (EEG)-based seizure detection systems encounter many challenges in real-life situations. The EEGs are non-stationary signals and seizure patterns vary across patients and recording sessions. Moreover, EEG data are prone to numerous noise types that negatively affect the detection accuracy of epileptic seizures. To addres… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
31
1

Year Published

2018
2018
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 15 publications
(36 citation statements)
references
References 55 publications
0
31
1
Order By: Relevance
“…For the cross-patient experiments, the average sensitivity, specificity and precision of 83.72%, 84.06% and 85.36% are respectively achieved, and the standard deviations being 0.1349, 0.1379 and 0.1020, respectively. These results exceed the current state-of-the-art performances on the noisy data of CHB-MIT in [17], [18] and [4]. The extensive experimental results show that the performance of the proposed new approach is promising and has high stability, with smaller variations compared to existing methods.…”
Section: Introductioncontrasting
confidence: 54%
See 1 more Smart Citation
“…For the cross-patient experiments, the average sensitivity, specificity and precision of 83.72%, 84.06% and 85.36% are respectively achieved, and the standard deviations being 0.1349, 0.1379 and 0.1020, respectively. These results exceed the current state-of-the-art performances on the noisy data of CHB-MIT in [17], [18] and [4]. The extensive experimental results show that the performance of the proposed new approach is promising and has high stability, with smaller variations compared to existing methods.…”
Section: Introductioncontrasting
confidence: 54%
“…Besides, though EEG signals are in general dynamic and non-linear, during a sufficiently small time period, the signal may be considered to be stationary. Based on the above three observations and inspired by an architecture in [18], we design a new approach by using bidirectional long shortterm memory (BiLSTM) integrated with an attention mechanism. Firstly, we introduce an attention mechanism over EEG channels.…”
Section: Introductionmentioning
confidence: 99%
“…Because seizure detection, which is often of a real-time flavor, is often treated as the seizure/non-seizure classification problem, many machine learning methods have been developed 7,[9][10][11][12][18][19][20][21] . Recently, deep learning techniques have been applied to the seizure detection problem 4,[13][14][15]22 . The evaluations of these methods are conducted with patientspecific or across-patients experiments.…”
Section: Related Workmentioning
confidence: 99%
“…Hussein et al design a deep neural network for seizure/non-seizure classification by using LSTM 22 . It extracts temporal features by using LSTM.…”
Section: Vidyaratne Et Al Propose a Deep Recurrent Architecture By Co...mentioning
confidence: 99%
See 1 more Smart Citation