Fog-Computing-Based Heartbeat Detection and Arrhythmia Classification Using Machine Learning
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 decis...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-02-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/12/2/32 |
| _version_ | 1811292063684100096 |
|---|---|
| author | Alessandro Scirè Fabrizio Tropeano Aris Anagnostopoulos Ioannis Chatzigiannakis |
| author_facet | Alessandro Scirè Fabrizio Tropeano Aris Anagnostopoulos Ioannis Chatzigiannakis |
| author_sort | Alessandro Scirè |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-13T04:39:49Z |
| format | Article |
| id | doaj.art-9d3d14667bdd4357a0b899a28edf0a07 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-04-13T04:39:49Z |
| publishDate | 2019-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-9d3d14667bdd4357a0b899a28edf0a072022-12-22T03:02:03ZengMDPI AGAlgorithms1999-48932019-02-011223210.3390/a12020032a12020032Fog-Computing-Based Heartbeat Detection and Arrhythmia Classification Using Machine LearningAlessandro Scirè0Fabrizio Tropeano1Aris Anagnostopoulos2Ioannis Chatzigiannakis3Department of Computer, Control and Management Engineering “Antonio Ruberti”, Sapienza University of Rome, 00185 Rome, ItalyDepartment of Computer, Control and Management Engineering “Antonio Ruberti”, Sapienza University of Rome, 00185 Rome, ItalyDepartment of Computer, Control and Management Engineering “Antonio Ruberti”, Sapienza University of Rome, 00185 Rome, ItalyDepartment of Computer, Control and Management Engineering “Antonio Ruberti”, Sapienza University of Rome, 00185 Rome, ItalyDesigning 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.https://www.mdpi.com/1999-4893/12/2/32ECGautomated detection of abnormalitiesheartbeat classificationdata miningrecurrent neural networklong-short term memoryalgorithm engineeringexperimental evaluation |
| spellingShingle | Alessandro Scirè Fabrizio Tropeano Aris Anagnostopoulos Ioannis Chatzigiannakis Fog-Computing-Based Heartbeat Detection and Arrhythmia Classification Using Machine Learning Algorithms ECG automated detection of abnormalities heartbeat classification data mining recurrent neural network long-short term memory algorithm engineering experimental evaluation |
| title | Fog-Computing-Based Heartbeat Detection and Arrhythmia Classification Using Machine Learning |
| title_full | Fog-Computing-Based Heartbeat Detection and Arrhythmia Classification Using Machine Learning |
| title_fullStr | Fog-Computing-Based Heartbeat Detection and Arrhythmia Classification Using Machine Learning |
| title_full_unstemmed | Fog-Computing-Based Heartbeat Detection and Arrhythmia Classification Using Machine Learning |
| title_short | Fog-Computing-Based Heartbeat Detection and Arrhythmia Classification Using Machine Learning |
| title_sort | fog computing based heartbeat detection and arrhythmia classification using machine learning |
| topic | ECG automated detection of abnormalities heartbeat classification data mining recurrent neural network long-short term memory algorithm engineering experimental evaluation |
| url | https://www.mdpi.com/1999-4893/12/2/32 |
| work_keys_str_mv | AT alessandroscire fogcomputingbasedheartbeatdetectionandarrhythmiaclassificationusingmachinelearning AT fabriziotropeano fogcomputingbasedheartbeatdetectionandarrhythmiaclassificationusingmachinelearning AT arisanagnostopoulos fogcomputingbasedheartbeatdetectionandarrhythmiaclassificationusingmachinelearning AT ioannischatzigiannakis fogcomputingbasedheartbeatdetectionandarrhythmiaclassificationusingmachinelearning |