Files in this item



application/pdfECE499-Sp2012-uppal.pdf (4MB)Restricted to U of Illinois
(no description provided)PDF


Title:Acoustic Heart Monitoring System
Author(s):Uppal, Karan
Contributor(s):Hasegawa-Johnson, Mark
Subject(s):heart monitoring
acoustic hear monitoring
heartbeat classification
machine learning algorithms
clustering algorithms
Abstract:This thesis explores the use of clustering algorithms in acoustic heart monitoring systems to detect the points of occurrence for a heartbeat. The proposed technique recovers heartbeats from an acoustically recorded heartbeat signal using unsupervised machine learning algorithms such as K-means clustering to cluster the provided data into different classes and identify the heartbeats from it. The K-means algorithm used to cluster the data is based on squared Euclidean distance. Experiments were conducted to determine the correct type of features, distance and number of clusters to use. Silhouette values were used to derive the appropriate number of clusters. To confirm our algorithm, datasets provided by Salutron Inc. (Menlo Park, CA) were used and the clustered data was used as a training set to train hidden Markov processes.
Issue Date:2012-05
Publication Status:unpublished
Peer Reviewed:not peer reviewed
Date Available in IDEALS:2014-01-09

This item appears in the following Collection(s)

Item Statistics