Combining accelerometer data with Gabor energy feature vectors for body movements classification in ambulatory ECG signals

Author

Kher, Rahul ; Pawar, Tanmay ; Thakar, Vikram

Author_Institution

EC Dept., G.H. Patel Coll. of Eng. & Technol., Vallabh Vidyanagar, India

fYear

2013

fDate

16-18 Dec. 2013

Firstpage

413

Lastpage

417

Abstract

Wearable ambulatory ECG (A-ECG) signals obtained using wearable ECG recorders inherently contain the motion artifacts due to various body movements of the subject. Classification of four such body movement activities (BMA) - left arm up-down, right arm up-down, waist twisting and walking-of five healthy subjects has been performed using artificial neural networks (ANN). The accelerometer data and the Gabor energy feature vectors have been combined to train the ANN. The overall BMA classification accuracy achieved by the ANN classifier is over 95%.

Keywords

accelerometers; bioelectric potentials; body sensor networks; electrocardiography; feature extraction; gait analysis; medical signal detection; medical signal processing; neural nets; signal classification; wavelet transforms; ANN classifier; BMA classification accuracy; Gabor energy feature vectors; accelerometer data; artificial neural networks; body movement activity classification; electrocardiogarphy; feature extraction; left arm up-down; motion artifacts; right arm up-down; waist twisting; walking; wearable ECG recorders; wearable ambulatory ECG signals; Accelerometers; Artificial neural networks; Electrocardiography; Feature extraction; Support vector machine classification; Wavelet transforms; A-ECG; Accelerometer data; Artificial Neural networks (ANN); Body movement activities (BMA); Gabor transform; Wearable ECG recorder;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering and Informatics (BMEI), 2013 6th International Conference on

Conference_Location

Hangzhou

Print_ISBN

978-1-4799-2760-9

Type

conf

DOI

10.1109/BMEI.2013.6746974

Filename

6746974