Comparative Analysis of Classification Features for ECG Signal Classification on Raspberry Pi Using Wearable Sensor Data

The classification of Electrocardiogram (ECG) signals plays a crucial role in monitoring and diagnosing cardiac conditions. With the advancements in wearable sensor technology, ECG signals can now be acquired conveniently in real-time using portable devices such as Raspberry Pi. However, the efficient extraction and selection of classification features from ECG signals remain a challenging task. In this study, we present a comparative analysis of classification features for automated ECG signal classification on Raspberry Pi. We evaluate and compare various feature extraction techniques, such as PQRS morphology, RR Interval, and wavelet. The performance of these features is assessed using a machine-learning algorithm random forest. To conduct the experiments, we use proven ECG signal data from MIT BIH arrhythmia, feature extraction techniques were applied to the preprocessed data to derive informative features for classification. The extracted features were used to train and test the machine-learning models. Furthermore, the classifier models were used to predict heartbeats types from wearable sensor data in real time and continuously. The results of our comparative analysis demonstrate the effectiveness and suitability of different feature extraction methods for ECG signal classification on the resource-constrained Raspberry Pi platform. We identify the most discriminative features and evaluate their impact on classification performance. Moreover, we explore the trade-offs between computational complexity and classification accuracy. We discuss the advantages and limitations of each feature extraction technique and provide insights into the feasibility of implementing real-time ECG signal classification systems on wearable devices. Overall, this study contributes to the field of ECG signal analysis by providing a comprehensive comparative analysis of classification features for ECG signal classification on the Raspberry Pi platform. The results and insights obtained from this research can guide the development of efficient and accurate wearable-based ECG monitoring systems for timely diagnosis and intervention in cardiac healthcare applications.