Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/180657
Title: An Innovative Wearable Computing Framework For Early Detection of Cardiac Anomalies
Researcher: Keskar, Swati D
Guide(s): Banerjee, Rahul
Keywords: Computer Science, Wearable Computing Framework, Cardiac Anomalies
University: Birla Institute of Technology and Science
Completed Date: 2015
Abstract: This work attempts to address the problem of early identification of select types of cardiac anomalies using a wearable computing approach. The primary research objective of the work involved developing an architectural framework which could be used for continuous real-time processing and analysis of input physiological signals acquired by using body-worn, non-invasive sensors. Continuous monitoring of cardiac activity, timely processing and detection of any deviation from normal state may save the life of the wearer, by providing help in time. In order to achieve continuous monitoring of cardiac activity, periodic depolarization and repolarization of the heart needs to be observed. This activity which is regulated by an electrical excitation system, creates body surface potential. After carefully studying various leads based systems, choice of Vectorcardiographic five-electrode Frank Lead System was used to acquire this body surface potential in the form of an electrical signal. This signal could be potentially corrupt and noisy due to various reasons such as power interference, etc. In order to extract correct information, the signal obtained was thus preprocessed for removing noise and baseline wander. At the next stage, relevant information needs to be extracted for further analysis. This led to the development of a novel, simple algorithm aimed at carrying out the task of segmentation and detection of characteristic points. These significant points along with their timestamps were stored in an array. A set of parameters was therefore identified for extraction from this signal. A set of temporal parameters like R-R interval, Heart Rate, QRS interval, QT interval and ST depression were derived from the resultant array stored by the algorithm developed, for the interpretation of various heart diseases. newlineOne of the significant features of the work presented here is the combination of offline and online techniques employed for processing. In addition to the online processing method discussed in the foregoing
Pagination: 117p.
URI: http://hdl.handle.net/10603/180657
Appears in Departments:Computer Science & Information Systems

Files in This Item:
File Description SizeFormat 
thesis_swati_2004phxf021p.pdfAttached File4.41 MBAdobe PDFView/Open


Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.