• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.92-95
• /
• 2020

In this paper, the new architecture of seizure prediction using CNN and LSTM and DWT was presented. In the proposed architecture, EEG data was labeled into a preictal and interictal section, and DWT was adopted to the preprocessing process to apply the characteristics of the time and frequency domain of the processed EEG signal. Also, CNN was applied to extract the spatial characteristics of each electrode used for EEG measurement, and LSTM neural network was applied to verify the logical order of the preictal section. The learning of the proposed architecture utilizes the CHB-MIT Scalp EEG dataset, and the sliding window technique is applied to balance the dataset between the number of interictal sections and the number of preictal sections. As a result of the simulation of the proposed architecture, a sensitivity of 81.22% and an FPR of 0.174 were obtained.

• Clinical and Experimental Pediatrics
• /
• v.50 no.7
• /
• pp.672-677
• /
• 2007

Purpose : To assess the prevalence and characteristics of headache comorbidity with epilepsy in children and adolescents in a specialty epilepsy clinic. Methods : Two hundred twenty nine consecutive patients attending the Chosun University Hospital Pediatric Epilepsy Clinic (mean age $10.0{\pm}4.1\;years$, range 4-17, M:F ratio 1.1:1.0) were interviewed with a standardized headache questionnaire. Headache was classified according to the International Classification of Headache Disorders, 2nd Edition and epilepsy was classified according to the International League Against Epilepsy. Disability was assessed using pediatric migraine disability assessment (PedMIDAS). Results : Of the 229 epilepsy patients, 86 (37.6%) had co-morbid headache. Of the headache patients, 64 (74.4%) had migraine (65.6%- migraine without aura, 20.3% - migraine with aura, 14.1% - probable migraine). The mean headache frequency was $7.2{\pm}8.4$ per month, mean duration was $2.2{\pm}4.0$ hours, mean severity was $5.2{\pm}2.2$ out of 10, and mean PedMIDAS score was $13.0{\pm}35.4$. The proportion of females was not higher in epilepsy with headache patients (48.8%) compared to epilepsy patients alone (48.0%). In the patients with migraine, 48.4% had complex partial seizures, 17.2% had simple partial seizures, and 34.4% had generalized seizures (P=0.368). A postictal association of migraine was reported in 18.8% with 17.2% reporting a preictal headache, and 7.8% reporting an ictal headache. Conclusion : The prevalence of headache in pediatric epilepsy is higher than that in general pediatric population, suggesting a co-morbidity of headache in epilepsy patients with migraine being the most frequent headache disorder. Altered cerebral excitability resulting in an increased occurrence of spreading depression may explain the headache comorbidity with epilepsy. Further studies are needed to assess the etiology of this co-morbidity as well as assess the frequency, duration, severity and disability response to antiepileptic drugs.