ECG R-R Interval Automatic Detection Using IOT

In this day and age, devotion to one's own body is one of the key factors taken into account. An electrical activity of the human heart is represented by the electrocardiogram (ECG) signal. Numerous heart disorders may be diagnosed using it. The tools that provide outcomes quickly while simultaneously maintaining accuracy. With the aid of the Raspberry Pi's cutting-edge technology and classification techniques, a multi-thread approach is provided to detect any falling event as well as the user's relative electrocardiogram (ECG) signal. Bluetooth or Wi-Fi are used for wireless connection, which gives embedded devices flexibility and extensibility. This project's objective is to classify an ECG signal into normal and pathological classifications in order to identify the kind of arrhythmia. Artificial neural networks (ANNs) are used to diagnose cardiac arrhythmia diseases in order to do this. Using MATLAB, EMB (empirical mode decomposition) approach is used to accurately classify ECG signals. Measures including mean squared error (MSE), classification specificity, sensitivity, accuracy, and precision are used to assess the classification performance. The classifier reaches a 100% accuracy rate. It has been investigated how image processing works in IOT-based systems. A variety of technologies based on image processing become a part of IOT-based applications. The article provides a summary of the function of image processing in IOT based intelligent systems in several application fields. The Work might be beneficial for creating and experimenting with the new image processing applications in IOT-based systems.