A hybrid machine learning model for classifying time series

Abstract

A time series is a sequence of numerical data points in equal time intervals and/or successive order. Time series are used in many fields to understand the behavior of systems, to make predictions, to create solutions to problems, etc. Electroencephalogram (EEG) and electrocardiogram (ECG) are frequently used in the diagnosis of diseases and research in this field. EEG signals examine the neural activity of the brain, while ECG examines the work of the heart muscle and neural conduction system. These signs contain a large amount of information about the functioning of the brain and heart functions. In order to use this information, experts in the field of signal processing must evaluate these signals. Due to the successful application methods of EEG and ECG signals in classification problems, various fields of artificial intelligence applications are frequently used by experts. In this study, a new hybrid model has been developed to classify EEG and ECG signals. These signals of five different classes have been used as the feature vector in the training of machine learning algorithms with 10 statistical parameters (8 normalized, 2 real signals). These algorithms are designed to give the best performance. In the proposed hybrid model, a machine learning model consisting of four stages is used. In the experimental studies, it has been observed that the proposed hybrid method gives better results than the normal classification process. The obtained results are given in the experimental studies section in detail.