چکیده مقاله
Fuzzy Support vector machines FSVM have in recent years been gainfully used in various pattern recognition applications As with any classification technique, appropriate choice of the kernels and input features play an important role in FSVM performance In this study, an evolutionary scheme searches for optimal kernel types and parameters for automated seizure detection We consider the Lyapunov exponent, fractal dimension and wavelet entropy for possible feature extraction The classification accuracy of this approach is examined by applying the MIT1 Dataset and comparing results with the ANFIS and SVM The MIT BIH dataset has the electrocardiographic ECG changes in patients with partial epilepsy which two types ECG beats partial epilepsy and normal A comparison of the results shows that the performance of the evolutionary scheme outweighs that of support vector machine In the best condition, the accuracy rate of the proposed approaches reaches 100% for specificity and 95 81% for sensitivity
کلیدواژهها
نویسندگان
Matineh Zavar
Sama technical and vocational training college,Islamic Azad University, Quchan Branch, Quchan, Iran
Hadi Ghasemifard
Department of Biomedical Engineering, Tehran Science and Research Branch, Islamic Azad University, Tehran, Iran
شیوه ارجاع
Zavar, Matineh and Ghasemifard, Hadi,1395,Genetic algorithm model selection in a Fuzzy support vector machine for Automated Seizure Detection,2nd National Congress of Electrical and Computer Engineering of Iran,Ramsar
ارائهشده در
مجموعه مقالات دومین کنفرانس بین المللی یافته های نوین پژوهشی در مهندسی برق و علوم کامپیوتر24 اردیبهشت 1395 · رامسر