Abstract: This study suggests an electrocardiogram (ECG) analysis and heart illness detection artificial intelligence of things (AIoT) system. A cloud database, a user interface on a smart device application (APP), front-end IoT-based hardware, and an AI platform for heart illness diagnosis are all included in the system. The wearable ECG patch with an analogue front-end circuit and a Bluetooth module, which is the front-end IoT-based hardware, can detect ECG signals. The APP on smart devices may identify diseases in real time and classify odd signals in addition to displaying users' real-time ECG readings. The cloud database will receive these ECG signals. Each user's ECG readings are stored in the cloud database, creating a big-data set that an AI programme may use to identify heart problems. The convolutional neural network-based approach that this study suggests has an average accuracy of 94.96 percent. The Ministry of Health and Welfare's Tainan Hospital provided the ECG dataset used in this investigation. Additionally, a cardiologist additionally carried out signal verification.
Keywords: Arrhythmia, atrial fibrillation, convolutional neural network, electrocardiogram, artificial intelligence of things, wearable device, application, cloud server.
|
DOI:
10.17148/IJARCCE.2022.11693
