Fog-Computing-Based Heartbeat Detection and Arrhythmia Classification Using Machine Learning

Abstract

Designing advanced health monitoring systems is still an active research topic. Wearable and remote monitoring devices enable monitoring of physiological and clinical parameters (heart rate, respiration rate, temperature, etc.) and analysis using cloud-centric machine-learning applications and decision-support systems to predict critical clinical states. This paper moves from a totally cloud-centric concept to a more distributed one, by transferring sensor data processing and analysis tasks to the edges of the network. The resulting solution enables the analysis and interpretation of sensor-data traces within the wearable device to provide actionable alerts without any dependence on cloud services. In this paper, we use a supervised-learning approach to detect heartbeats and classify arrhythmias. The system uses a window-based feature definition that is suitable for execution within an asymmetric multicore embedded processor that provides a dedicated core for hardware assisted pattern matching. We evaluate the performance of the system in comparison with various existing approaches, in terms of achieved accuracy in the detection of abnormal events. The results show that the proposed embedded system achieves a high detection rate that in some cases matches the accuracy of the state-of-the-art algorithms executed in standard processors.

Implementing and Evaluating Health as a Service in Fog and Cloud Computing using Raspberry Pi

“…In [57], the model ECG based analysis model is proposed which discussed the effect of geographical constraint on the energy efficiency, and it proves that Article [59] says, the Fog computing is a scalable solution to the cloud computing which can store and process near the edge devices. Articles referred [56][57][58][59], are using fog computing approach for health care need. They are also classifying the arrhythmias from ECG signals and processing ECG signals too.…”

“…fog computing based health care architecture is capable to save the energy. S. Alessandro et al in article[58] have used fog computing to detect the arrhythmias in the ECG signal. They have used different machine learning techniques for the same.…”

Investigating Feature Selection and Random Forests for Inter-Patient Heartbeat Classification

“…In recent years, thanks to the availability of pocket or wearable devices for single lead ECG recording, it has become possible to perform the acquisition of the ECG signal even in ambulatory contexts for applications of prevention and risk management. The successful application and dissemination of such approaches require the development not only of reliable, but also lightweight algorithms for the automatic detection and classification of signal anomalies in order to reduce the amount of data and the number of events needed to be sent to the physician for making a proper risk assessment and giving advice [1].…”

A Novel Cost-Efficient Framework for Critical Heartbeat Task Scheduling Using the Internet of Medical Things in a Fog Cloud System

“…To spot heart irregularities, electrocardiography (ECG) signals are the primary source of evaluation that is widely used by medical specialists arround the world [3]. However, due to the sporadic nature of ECG signals, it is necessary to monitor patients continuously to have for accurate analysis of the heart problems [4]. Recently, advancements in Internet of Things (IoT) based medical sensors have grown progressively [5][6][7][8][9][10][11][12][13][14][15]; especially in heartbeat sensors that generate real-time delay-sensitive data that require immediate action for the results [16,17].…”

“…Generally, these sensors are integrated with limited constraint devices. Thus, fog computing is a promising and delay-efficient paradigm, where computing and capability are offered at the edge of IoT network [4,18,19]. It is noticed that each heartbeat-based medical application is composed of critical tasks and less delay-sensitive tasks.…”