Classification of ECG signals using dynamic fuzzy neural networks
Electrocardiogram is a diagnostic tool which records the heart’s electrical activity over a period of time. This bioelectric signal is non-linear in nature and it called an (ECG) Electrocardiograph. Therefore, it is an essential tool for assessing heart function. The electi9cal current due to the de...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2009
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/18799 |
| _version_ | 1826115622640025600 |
|---|---|
| author | Rajagopalan Srivathsan |
| author2 | Wang Jianliang |
| author_facet | Wang Jianliang Rajagopalan Srivathsan |
| author_sort | Rajagopalan Srivathsan |
| collection | NTU |
| description | Electrocardiogram is a diagnostic tool which records the heart’s electrical activity over a period of time. This bioelectric signal is non-linear in nature and it called an (ECG) Electrocardiograph. Therefore, it is an essential tool for assessing heart function. The electi9cal current due to the depolarization of the Sinus Atria node stimulates the surrounding myocardium and spreads into the heart tissues. A small proportion of the electrical current flows through the body surface. By applying electrodes on the skin at the selected points, the electrical potential generated by this current can be recorded as and ECG signal.
The interpretation of the ECG signal is an application of pattern recognition. By storing essential features of the ECG signal and recognizing them enables automatic categorization of the signals into their respective classes. An experienced cardiologist can easily diagnose various heart diseases by examining the ECG waveforms. The use of these computer-based automated ECG analyzers can considerably reduce the physician’s workload. These analysers provide assistance to the cardiologist to diagnose the ECG signals faster and with great accuracy.
Four steps are involved in the ECG signals pattern recognition, namely Signal Pre-Processing stage, QRS-detection, Feature Extraction and Classification of ECG Features using Dynamic Fuzzy Neural Networks (DFNN). The performance of the DFNN is compared with various other adaptive fuzzy neural/ neural network algorithms through simulation studies. |
| first_indexed | 2024-10-01T03:58:11Z |
| format | Thesis |
| id | ntu-10356/18799 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:58:11Z |
| publishDate | 2009 |
| record_format | dspace |
| spelling | ntu-10356/187992023-07-04T15:25:21Z Classification of ECG signals using dynamic fuzzy neural networks Rajagopalan Srivathsan Wang Jianliang School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Medical electronics Electrocardiogram is a diagnostic tool which records the heart’s electrical activity over a period of time. This bioelectric signal is non-linear in nature and it called an (ECG) Electrocardiograph. Therefore, it is an essential tool for assessing heart function. The electi9cal current due to the depolarization of the Sinus Atria node stimulates the surrounding myocardium and spreads into the heart tissues. A small proportion of the electrical current flows through the body surface. By applying electrodes on the skin at the selected points, the electrical potential generated by this current can be recorded as and ECG signal. The interpretation of the ECG signal is an application of pattern recognition. By storing essential features of the ECG signal and recognizing them enables automatic categorization of the signals into their respective classes. An experienced cardiologist can easily diagnose various heart diseases by examining the ECG waveforms. The use of these computer-based automated ECG analyzers can considerably reduce the physician’s workload. These analysers provide assistance to the cardiologist to diagnose the ECG signals faster and with great accuracy. Four steps are involved in the ECG signals pattern recognition, namely Signal Pre-Processing stage, QRS-detection, Feature Extraction and Classification of ECG Features using Dynamic Fuzzy Neural Networks (DFNN). The performance of the DFNN is compared with various other adaptive fuzzy neural/ neural network algorithms through simulation studies. Master of Science (Computer Control and Automation) 2009-07-20T02:07:49Z 2009-07-20T02:07:49Z 2008 2008 Thesis http://hdl.handle.net/10356/18799 en 89 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Medical electronics Rajagopalan Srivathsan Classification of ECG signals using dynamic fuzzy neural networks |
| title | Classification of ECG signals using dynamic fuzzy neural networks |
| title_full | Classification of ECG signals using dynamic fuzzy neural networks |
| title_fullStr | Classification of ECG signals using dynamic fuzzy neural networks |
| title_full_unstemmed | Classification of ECG signals using dynamic fuzzy neural networks |
| title_short | Classification of ECG signals using dynamic fuzzy neural networks |
| title_sort | classification of ecg signals using dynamic fuzzy neural networks |
| topic | DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Medical electronics |
| url | http://hdl.handle.net/10356/18799 |
| work_keys_str_mv | AT rajagopalansrivathsan classificationofecgsignalsusingdynamicfuzzyneuralnetworks |