Table of ContentsSummaryIntroductionReview of ECG Signal MorphologyDescription of the DatasetMethodologyThe steps followed in this work can be summarized as follows:Results and DiscussionsConclusionSummaryElectrocardiography (ECG or ECG) is a technique non-invasive widely used to determine the condition of the human heart and detect any abnormal cardiac behavior. ECG analysis computer systems can help doctors quickly detect dangerous events such as ventricular fibrillation in patients at high cardiac risk. The first and crucial part of automatic ECG signal analysis is to accurately identify and measure the characteristics of the ECG signal, i.e., locate the exact position of the P-wave onset and offset points , QRS and T. In this paper, we propose a rapid technique to accurately identify these key reference points using local windows around the R peaks. The proposed method was tested on a standard QT database and very high accuracy above 99% is achieved when identifying different segments of the ECG signal. Say no to plagiarism. Get a tailor-made essay on “Why violent video games should not be banned”?Get the original essayIntroductionAn ECG signal comes from the electrical activity of the heart which coordinates the contraction and relaxation of the different chambers of the heart. Analysis of ECG signal and detection of its characteristic points can be used to identify various heart rhythm abnormalities, chest pain and other diseases. A cardiac cycle in an ECG signal includes P, QRS and T wave complexes. The field of automatic ECG analysis has become quite mature. Much work has been carried out to identify the characteristic points of ECG signals. However, most of them use sophisticated and complex signal processing techniques that make them computationally expensive. In [11], Pan Tompkins proposed a method that recognizes QRS complexes using information about the slope, amplitude and width of the signal. But the double threshold technique used in this method to find missed complexes is only useful if the heart rate is regular and does not allow missing beats to be found in the event of abnormalities. In [12], all P, QRS and T complexes are detected using the wavelet transform method, but P and T onsets and offsets are not detected very accurately under significant influence of noise. [13] shows the detection of the P wave in addition to the QRS complex using the hidden Markov model. In [14], QRS complexes are detected using moving average filters, but this methodology is not robust to false positives or false negatives. The QRS complex detection technique proposed in [15] applied first-order derivative and adaptive threshold adjustment to detect complexes. and filtered high-frequency noise using a discrete wavelet transform. [16] introduces a new fast version of the ECG delineation algorithm using line fitting but is not robust against some arrhythmias where no waves are detected. A support vector machine was used for P and T wave detection in [17]. In [18], QRS complexes were grouped into different groups using self-organizing neural networks for detection. The algorithm proposed in [19] can be evaluated for clinical and telehealth ECG data. The work of [20] describes a complex QRS detector based on the dyadic wavelet transform. It gave good performance for contractionsmultiform premature ventricular, bigeminy and couplets. [21] uses the S transformation to isolate QRS complexes and Shannon energy to localize R waves. Detection of QRS complexes is also found in [22] and was achieved using a differential equation operation. In [23] a QRS complex detector with limited hardware resources was proposed. In our paper, we aim to detect P, QRS and T complexes reliably and robustly using local windowing which gives very high detection accuracy and has O(N) computational complexity in detecting P, Q, S waves and T. This article is organized as follows. In Section 2, we present a brief discussion on the anatomy of the ECG signal and its characteristic waveforms. Section 3 provides a description of the dataset that was used to evaluate the proposed method. In Section 4, we discuss the methodologies and algorithms implemented in this work. The results obtained by the evaluation are presented in sections 5 and 6 with quantitative and qualitative interpretations. Finally, Section 7 concludes the article. Examining ECG Signal Morphology The ECG captures the direction and magnitude of electrical depolarization and repolarization generated by a person during their heartbeat cycle. The components of a normal ECG trace consist of several waveforms, each indicating an electrical event during a heartbeat. These waveforms are called P wave, QRS complex and T wave, as shown in Fig. There is another small wave called the U wave which follows the T wave and which is not always observable due to its small size [2]. We ignore the U wave in this work. The P wave marks the start of the ECG cycle and is the first short upward movement of the ECG tracing. This indicates that the atria are contracting and pumping blood into the ventricles. It is followed by the QRS complex, normally starting with a downward deviation, denoted Q; a greater upward deviation, a peak noted R; then a descending S wave. Figure 1. Schematic diagram of a single ECG wave. The QRS complex represents ventricular depolarization and contraction. The PR interval indicates the transit time of the electrical signal to travel from the sinus node to the ventricles. The T wave is normally a modest upward waveform representing ventricular repolarization. However, in some cases, the T wave can be inverted [3]. Each of these waves has a characteristic duration. The P-Wave lasts approximately 80 ms. The normal PR interval in an ECG wave varies from 120 ms to 200 ms. The duration of the PR segment is 50 ms to 120 ms. The duration of the QRS complex is approximately 80 ms to 120 ms. The duration of the ST segment is 80 ms to 120 ms. The duration of the ST interval is 320 ms. The QT interval depends on heart rate. Normal QT intervals are less than 450 ms for men and 460 ms for women, but can vary from 270 ms at a heart rate of 150 beats per minute to 500 ms at a heart rate of 40 beats per minute [4] . Dataset Description Several databases are available for studying and analyzing ECG data. The dataset used in this paper is the QT database which contains 105 records, each with a duration of 15 minutes [5]. It was created by incorporating new data from patient Holter recordings into the MIT-BIH Arrhythmia Database, the European Society of Cardiology ST-T Database, and several other databases [6- 7]. The sampling frequency of all records in this database is 250 Hz. The reason for choosing this database for the evaluation of ouralgorithm is that reference annotations were given to mark waveform boundaries in addition to those already marked in the other databases. More specifically, this database includes annotations for P and T complexes in addition to annotations for Q, R and S complexes, thus helping us to compare our obtained results. Methodology From the discussion on ECG signal morphology in section 2, it can be observed that the points of interest viz. P, Q, R, S and T have a distinct and characteristic physical appearance. Furthermore, if one of these points is known, then the other points can be identified from its neighborhood with fairly good precision. For example, peak P is the local maximum between peak R of the corresponding wave and peak T of the previous wave; Q trough is the local minimum between the P peak and the R peak. Similar neighborhood characteristics exist for S and T waves. Thus, by knowing only the position of the R peak, all other waves can be identified from the signal . In this work, we exploit these local characteristics of P, Q, R, Set T waves to localize them. The steps followed in this work can be summarized as follows: Step 1: The digitized ECG data from the database is filtered with a band-pass FIR filter with a lower and upper cutoff frequency of 3 Hz and 45 Hz respectively to remove noises from electromyogram (EMG) signals, high-frequency interference, DC shift, and baseline wandering [8]. Step 2: From the filtered signal, the R peak is extracted using the R segmentation algorithm proposed by Hamilton in [9]. Step 3: After extracting the location of the R peaks, the location of the remaining four peaks is calculated using a local context window in the vicinity of the corresponding R peak. The main contribution of this work is in step 3 and is discussed in detail in the following subsections. After filtering the signal and locating the R peaks, we proceed to localize the P peaks. As stated previously, the P peak is approximated as the local maximum between the R peak and the T peak of the previous wave. However, considering the entire region between the T peak and the R peak can lead to an increase in false positives since this region is quite large, and can be noisy. and have several peaks and troughs. Therefore, a reduced context window with a duration of 100 ms is chosen, shifted from the R peak by 100 ms to the left. A typical boundary of the P-wave detection pop-up is marked A and B, as shown in Figure 2. The P-wave peak is considered the maximum of the values ​​in the pop-up. T peak detection As discussed in section 2, the T peak have the unique property of being inverted in some cases. So in the pop-up, the T peak will either be the minimum or the maximum, whichever has the maximum amplitude. To remove this ambiguity, all values ​​in the window are squared. Thus, the peak T will necessarily be at the location of the value having a maximum square amplitude. However, there is a problem. In the event of an inverted T peak, the voltage level at the peak may be below 0 V, and possibly between 0 mV and -1 mV. In this case, squaring a value between 0 and 1 will in turn reduce its magnitude. So a threshold of 1mV is added to all the values ​​before squaring them. T peaks occur quite a long time after the QRS wave and may be present in a wide region. Thus, the size of the pop-up window is increased to a duration of 200 ms and is shifted to the right by 200 ms relative to the position of peak R. Figure 5 shows the boundaries of windows A and B for locating the pic T. Results and discussions In this section,.