ECG Monitoring System Using Dry Electrodes for Artifact Classification to Prevent False Diagnoses

This study introduces a compact and efficient design for an advanced ECG monitoring and artifact classification system aimed at addressing the limitations of traditional ECG systems based on gel electrodes, which often cause skin irritation and degradation of conductivity over time. To overcome these challenges, the proposed system incorporates Orbital 21 dry electrodes, along with high processing speed and computational microcontroller, coupled with an integrated analog front-end circuit to optimize signal quality. Subsequently, a proprietary dataset is created from the designed system, categorized into three distinct classes. This dataset is used to leverage various machine learning classifiers to analyze ECG signals effectively, ensures the accurate detection and classification of ECG signal artifacts, thereby distinguishing common artifacts from pathological patterns to enhance diagnostic precision. Moreover, this innovative approach establishes the system as a reliable and efficient health assistance algorithm, showcasing significant potential for continuous monitoring and clinical applications.