IoT Based System for Heart Monitoring and Arrhythmia Detection Using Machine Learning

Abstract

Internet of Things (IoT) technologies allow building a digital representation of people, objects, or physical phenomena to be available on the Internet. Thus, stakeholders can access this information from remote places or computational systems could analyze this data to find patterns, make decisions, or execute actions. For instance, a doctor could diagnose patients by analyzing the received data from an IoT system even when patients are located in a remote place. This article proposes an IoT system for monitoring electrocardiogram (ECG) signal and processing heart data in order to generate an alert when an arrhythmia is present. This system involves a Polar H10 heart sensor, machine-learning models to classify heart events, and communication technology to share and store patient’s information. In the first place, the architecture of the IoT monitoring system and the communication between the components are described by discussing the designing criteria. Second, the experimentation process performs the training and the assessment of three classification algorithms, random forest, convolutional neural network, and k-nearest neighbors. The results show that k-nearest neighbor has the best accuracy percentage classifying the arrhythmias under study (premature ventricular contraction 94%, fusion of ventricular beat 81%, and supraventricular premature beat 82%); also, it is able to discern normal and unclassifiable beats with 93% and 97%, respectively.

Statistical Review of Health Monitoring Models for Real-Time Hospital Scenarios

“…MDA CNN [25] 7.0 BCNN [26] 6.4 LWS [27] 7.4 MAC TM [28] 8.3 QL [29] IBCN [30] 6.8 CEF [31] 7.0 MSI MLP [32] 8.0 UHMM [33] 6.5 KNN Based System [34] 8.1 OFS RGA [35] 5.7 US MNN [36] 6.4 MIP EIS [37] 7.0 MR CNN [38] 6.1 LAAC [39] 6.0 LSCs [40] 5.7 PC3NN [41] 5.7 LSTM Based System [42] 6.1 ECM [44] 7.4…”

“…In [33] presents a universal health management and monitoring system in resource-constrained environments based on IoT. An IoT used for health indexing method using heterogeneous neural networks is proposed in [35] and presents an insole optical fibre sensor architecture for remote gait analysis. Finally, [36] proposes an IoT-based unobtrusive sensing system for sleep quality monitoring and assessment, and [37] discusses IoT-associated impedimetric biosensing for point-of-care monitoring of kidney health.…”

“…These models are used for context-specific applications and can be extended to larger deployments via the augmentation of training and validation datasets. These models must also be deployed for distributed computing applications via Cloudlets eHealth Framework (CEF) [31], multiple sensor interfaces with Multilayer Perceptron (MSI MLP) [32], Universal Health Management and Monitoring (UHMM) [33], kNN-based System [34], and use of Optical Fibre Sensors (OFS) for Remote Gait Analysis (RGA) via incremental and continuous learning (ICL) [35], which assists in designing HMSMs with high efficiency, and low delay characteristics. Figure 6 .…”

A Novel Framework for Data Assessment That Uses Edge Technology to Improve the Detection of Communicable Diseases

“…M. Safa et al [ 18 ] proposed a novel prediction method for cardio stress using a machine learning algorithm in IoT devices. The proposed method uses the K-nearest algorithm and supports vector machine approaches.…”

Automated Arrhythmia Classification Using Farmland Fertility Algorithm with Hybrid Deep Learning Model on Internet of Things Environment

“…In this architecture, the HADM database was deployed while the KNN algorithm was employed to make both ECG-HMCM as well as the Gridsearch method applicable for hyperparameter optimization. In literature [16], a new technique was introduced for the identification of the SVCA using the ECG signals. The Fixed Frequency Range Empirical Wavelet Transform (EWT) (FFREWT) filter bank was proposed for multi-scale examination of the ECG signals.…”