@article{Sachin Deshmukh_2019, title={Normalized Higher Order Statistics based Automated Cardiovascular Disease Detection using ECG}, volume={28}, url={http://sersc.org/journals/index.php/IJAST/article/view/2781}, abstractNote={<p>Since from last decade, several recent Computer Aided Diagnosis (CAD) tools introduced to assist medical professionals due to accuracy, simplicity &amp; inexpensive approach. The Electrocardiogram (ECG) signals are used with such methods for the detection of Cardiovascular Disease (CVD) detection. The efficiency of CVD detection using ECG suffered from the many research problems such as artefacts, efficient features extraction, QRS beats extraction etc. This paper presents the novel framework for CVD using the raw ECG signals. After the signal procurement, we connected the half breed pre-preparing calculation to expel the curios &amp;clamour from the crude ECG signal. In next stage, the calculation intended to extricate the QRS &amp; ST sections dependent on the dynamic thresh holding approach. This technique first gauge the Q, R, S, &amp; ST fragment from the pre-preparing ECG signal. To limit the overhead of calculation, this strategy straightforwardly connected in time-area signal with the goal that no time squanders in playing out any morphological activity. At long last, the component extraction strategy structured called Normalized Higher Order Statistics (NHOS) to separate the highlights from the combination of QRS &amp; ST divisions. The Artificial Neural Network (ANN) used to play out the characterization. The reproduction results demonstrates that proposed strategy conveyed better execution as analyzed than existing strategies.</p&gt;}, number={18}, journal={International Journal of Advanced Science and Technology}, author={Sachin Deshmukh, Sanjay Ghodake, Shashikant Ghumbre,}, year={2019}, month={Dec.}, pages={629 - 649} }