Classification of ECG Signals Using Particle Swarm Optimization and Extreme Learning Machine
Journal Title: International Journal of Engineering Sciences & Research Technology - Year 30, Vol 3, Issue 7
Abstract
The ECG is one of the mainly effective investigative tools to detect cardiac diseases. It is a technique to calculate and record dissimilar electrical potentials of the heart. The electrical potential generated by electrical action in cardiac tissue is calculated on the surface of the human body. Present flow, in the variety of ions, signals reduction of cardiac muscle fibers important to the heart's pumping action. This ECG can be classified as standard and abnormal signals. In this work, a systematic experimental study was conducted to demonstrate the advantage of the generalization capability of the Particle Swarm Optimization Extreme Learning Machine (PSO-ELM) compared with Extreme Learning Machine (ELM) approach in the automatic classification of ECG beats. The simplificationpresentation of the ELM classifier has not attained the nearest maximum accuracy of ECG signal classification. To attain the maximum accuracy the PSO-ELM classifier design by searching for the best value of the parameters that tune it’sdistinguish function, and upstream by looking for the best subset of features that feed the classifier. The experiments were conducted on the ECG data from the Massachusetts Institute of Technology–Beth Israel Hospital (MIT– BIH) arrhythmia database to categorize five kinds of abnormal waveforms and normal beats. In particular, the sensitivity of the PSO-ELM classifier is tested and that is compared with ELM. The attained results clearly confirm the superiority of the PSO-ELM approach when compared to ELM classifiers.
Authors and Affiliations
Dr. S. Karpagachelvi
Keywords
Related Articles
- EP ID EP143058
- DOI -
- Views 49
- Downloads 0
PERFORMANCE IMPROVEMENT OF IMAGE DATA COMMUNICATION OVER MIMO-WLAN USING DIFFERENT WAVELET DOMAIN MEDIAN FILTERING TECHNIQUES
In wireless communication, the receiver side bit error rate strongly affected by channels noise, synchronization error, interference, and wireless multipath fading channels, Multiple-input and multiple-output( MIM...
NUMERICAL INVESTIGATION OF SHELL AND TUBE HEAT EXCHNGER FOR HEAT TRANSFER OPTIMIZATION: A Review
An un-baffled shell-and-tube heat exchanger design with respect to heat transfer coefficient and pressure drop is investigated by numerically modelling. The flow and temperature fields inside the shell and tubes are res...
EFFECT OF SURFACTANT (N-BUTANOL) BEHAVIORS ON SUBCOOLED NUCLEATE POOL BOILING OVER MICROWIRE
The flow and heat transfer characteristics of nanofluid were attracting many researchers during the last two decades. Convection heat transfer in it is especially important for its potential applications. In this i...
Spectrum sensing Techniques In Cognitive Radio
The growing insist of wireless applications has put a lot of constraint on the usage of available radio spectrum which is limited and valuable resource. However, a fixed spectrum assignment has lead to under utilization...
Electrical Properties of InxGa1
Electrical resistivity and Hall Effect measurement study were grown on single crystal GaAs at 77K and in a temperature region between 273K to 323K. From the measurements it is found that GaAs and In and In0.205Ga0.79...