Machine intelligence based identification of body movements in Ambulatory ECG (A-ECG)

Ambulatory ECG signal (A-ECG) is useful when long term cardiac monitoring of a patient is necessary. Ambulatory ECG monitoring provides electrical activity of the heart while a person is involved in doing his or her normal routine activities. Thus, the recorded ECG signal consists of cardiac signal along with motion artifacts introduced due to person's body movements during routine activities. This motion artifact has spectral overlap with cardiac signal in 1-10 Hz which corresponds to ECG features like P wave and T wave. These artifacts due to different physical activities (PA) might help in further cardiac diagnosis. For Classification of body movements, first the motion artifacts from A-ECG have been extracted using Adaptive filtering and discrete wavelet transform (DWT) approaches. The statistical parameters such as mean, median, variance, max value of extracted motion artifact signals are calculated. After that feature vector is created by combining principal components and above four parameters of respective motion artifacts signals. These combine features are fed to multilayer feed-forward neural network (MLPFNN) for classification. For this work the ECG signals of six healthy subjects (aged of 19 to 26 years) were recorded while the person performs various body movements activity like (i) up and down movement of left hand, (ii) up and down movement of right hand, (iii) waist twisting movement while standing and (iv) change in position from sitting down on chair to standing up movement in lead I configuration by using BIOPAC MP 36 signal acquiring system.