Fetal ECG monitoring is a routine clinical detection method that can reflect the changes of fetal heart in utero in real time. At present, most of the clinical fetal heart rate detection adopts the ultrasonic Doppler method, which is technically difficult and highly specialized in operation and expensive. This study introduces a fetal ECG detection system based on the maternal abdominal electrode method. The weak fetal ECG changes are sensed through the maternal abdominal electrode, and the mixed ECG signal is obtained through the corresponding amplification and filtering circuit. Finally, the obtained signal is passed through WiFi, transmitted to the host computer. The host computer uses the adaptive filtering algorithm to estimate the fetal ECG signal. The system has strong feasibility, low operation expertise, low cost, and is more convenient.

Atrial fibrillation is a common arrhythmia, and its diagnosis is interfered by many factors. In order to achieve applicability in diagnosis and improve the level of automatic analysis of atrial fibrillation to the level of experts, the automatic detection of atrial fibrillation is very important. This study proposes an automatic detection algorithm for atrial fibrillation based on BP neural network (back propagation network) and support vector machine (SVM). The electrocardiogram (ECG) segments in the MIT-BIH atrial fibrillation database are divided into 10, 32, 64, and 128 heartbeats, respectively, and the Lorentz value, Shannon entropy, K-S test value and exponential moving average value are calculated. These four characteristic parameters are used as the input of SVM and BP neural network for classification and testing, and the label given by experts in the MIT-BIH atrial fibrillation database is used as the reference output. Among them, the use of atrial fibrillation in the MIT-BIH database, the first 18 cases of data are used as the training set, and the last 7 cases of data are used as the test set. The results show that the accuracy rate of 92% is obtained in the classification of 10 heartbeats, and the accuracy rate of 98% is obtained in the latter three categories. The sensitivity and specificity are both above 97.7%, which has certain applicability. Further validation and improvement in clinical ECG data will be done in next study.
Humans ; Atrial Fibrillation/diagnosis* ; Support Vector Machine ; Heart Rate ; Algorithms ; Neural Networks, Computer ; Electrocardiography

Ventricular fibrillation is the most common pathophysiological mechanism leading to cardiac arrest. If cardiac arrest can be rescued in time, the survival rate of patients can be greatly improved. Therefore, rapid and accurate identification of ventricular fibrillation is extremely important. This paper proposes an automatic detection algorithm for ventricular fibrillation based on random forest and BP (back propagation) neural network. Pass the ECG signal through a 6 s moving window, calculate 6 kinds of characteristic parameters according to the time-frequency domain information of the signal, use these 6 kinds of characteristic parameters as the input of the classifier, carry out classification and test, and give the authoritative experts in the database. A total of 44 cases of related data were used to evaluate the method. The results show that using the ten-fold cross-validation method, the accuracy of classification of ventricular fibrillation in the CU database (Creighton University Ventricular Tachyarrhythmia Database) and the AHA database (the American Heart Association Database) has reached 96.38% and 99.45%, which has certain applicability.

Breathing is of great significance in the monitoring of patients with obstructive sleep apnea hypopnea syndrome, perioperative monitoring and intensive care. In this study, a respiratory monitoring and verification system based on optical capacitance product pulse wave (PPG) is designed, which can synchronously collect human PPG signals. Through algorithm processing, the characteristic parameters of PPG signal are calculated, and the respiratory signal and respiratory frequency can be extracted in real time. In order to verify the accuracy of extracting respiratory signal and respiratory rate by the algorithm, the system adds the nasal airflow respiratory signal acquisition module to synchronously collect the nasal airflow respiratory signal as the standard signal for comparison and verification. Finally, the root mean square error between the respiratory rate extracted by the algorithm from the pulse wave and the standard respiratory rate is only 1.05 times/min.
Algorithms ; Electrocardiography ; Heart Rate ; Humans ; Photoplethysmography ; Respiration ; Respiratory Rate ; Signal Processing, Computer-Assisted ; Sleep Apnea, Obstructive