انتخاب ویژگی برای تشخیص آریتمی های قلبی با استفاده از بهینه‌سازی ازدحام ذرات باینری چند هدفه

سیگنال الکتروکاردیوگرام، یکی از مهم ترین ابزار برای طبقه بندی انواع مختلف آریتمی های قلبی است. معمولاً سیگنال های ecg، حاوی نویزهای متفاوتی هستند. در این مقاله، تکنیک تجزیه مد تجربی گروهی که در آن هر تابع مد ذاتی (imf)، شامل تنها یک مولفه ی فرکانسی است، برای حذف نویز به کار رفته است. با کمک پنجره بندی مناسب بر روی کمپلکس qrs متشکل از جمع سه imf اول، حذف نویز با کمترین اعوجاج انجام شده و با استفاده از تبدیل موجک گسسته، نویزهای باقیمانده نیز از بین رفته است. سپس با به کارگیری تجزیه بسته ی موجک، از سیگنال ویژگی استخراج شده است که ویژگی های بهینه، با روش بهینه‌سازی ازدحام ذرات باینری چند هدفه انتخاب شده اند. در نهایت از شبکه عصبی پس انتشار، برای طبقه بندی استفاده گردیده که مقدار دقت 12/99 درصد برای 17 عدد سیگنال اخذ شده از پایگاه داده ی mitbih، به دست آمده است.

Features selection for cardiac arrhythmia diagnosis using multiple objective binary particle swarm optimization

Introduction: Any heart activity disorder may lead an irregularity in is rhythm, or cardiac arrhythmia. An ECG signal is one of the major tools for classifying different types of cardiac arrhythmias. ECG signals usually contain various noises. To have a better signal processing, it is essential to remove noises in a way that a signal structure never become subject to distortion. After the step of noise removal, selection of an appropriate method is of paramount importance for feature extraction. Optimal features can be selected to improve efficiency and reduce calculations. Materials and Methods: This article used the ensemble empirical mode decomposition (EEMD) in which any intrinsic mode function (IMF) contains only a single frequency component for noise removal. The noise removal operation with the least distortion is possible using an appropriate windowing on a QRS complex containing sum of the first three IMFs. Later, the remaining noises can be removed using discrete wavelet transform (DWT). The results of using the EEMDDWT combined method were compared with EMD and DWT combination. After the noise removal step, feature extraction was performed through a wavelet packet decomposition. It is capable of signal decomposition at all frequencies. Multiple objective binary particle swarm optimization (MOBPSO) method was used to select optimal features and the effect of this method on the results was examined. Finally, the back propagation neural network (BPNN) and a support vector machine based on particle swarm optimization were used for classification. Result: This article used 17 signals received from the MITBIH database. The acquired data belong to 6 different types of classes. After preprocessing, feature extraction, feature selection, and classification on the input data, it is observed that the proposed technique of EEMDDWT is an appropriate method for noise removal and MOBPSO is a suitable method for the selection of best features. The BPNN classifier managed to classify cardiac arrhythmias with a higher accuracy and the values for accuracy, sensitivity, specificity, and positive predictive value were 99.12%, 97.08%, 99.38%, and 97.12%, respectively.