Heart Signal analysis on Multi-Domain Features Extraction by SVM Classifier in Smart Monitoring System
V.Agalya1, S.Sumathi2
1V.Agalya, Department of EEE, CMR Institute of Technology, Bengaluru, India
2S.Sumathi, Department of EEE, Mahendra Engineering College, Tamil Nadu, India.
Manuscript received on September 16, 2019. | Revised Manuscript received on 24 September, 2019. | Manuscript published on October 10, 2019. | PP: 1841-1843 | Volume-8 Issue-12, October 2019. | Retrieval Number: L28611081219/2019©BEIESP | DOI: 10.35940/ijitee.L2861.1081219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: According to world health organization (WHO) the heart strokes and cardiovascular diseases death rate is increases every year. Heart signal is one of the most predominant physiological signals of our body, including a large number of physiological and pathological information that can reflect the cardiovascular status. This work aims to develop a heart signal quality assessment method by three common case studies of deep breath, speaking and climbing up &down. In data collection, a total features were extracted from domain statistics. Here statistical analysis is employed for reducing dimension of a particular features. For classification of electrocardiogram (ECG) signals cardiac arrhythmias using deep learning model is used by Cubic Wavelet Transform. These parameters are used as input to these classifier with types of ECG signals. A SVM with radial basis kernel function was trained for final signal quality classification. The best effect was obtained on distinguishing resting from climbing up& down and the result showed that the classification performance was significantly improved after feature selection. These results indicate that the proposed method is effective for identifying different cases. The hardware testing was implemented and tested for the same case studies.
Keywords: Signal, Heart, Multi-Domain Features, SVM
Scope of the Article: Healthcare Informatics