Smart healthcare is an emerging field with the goal of harnessing technological advances to enhance healthcare quality. Several research projects in recent years are devoted to design of electronic devices and networking platforms to facilitate technology-based health service. One important paradigm in smart healthcare is developing tools for biomedical signal processing. Biomedical signals can directly reflect the information about patient health and therefore have been widely investigated by the research community. The essence of most signal analysis systems is to process a large training dataset and build a reference model to asses the health status of new patients. While the majority of these methods focus on improving classification performance on a collection of signals in large datasets, the predictive modeling of biomedical signals is rarely emphasized. In this work, we go one step beyond the conventional methods and intend to predict potential upcoming abnormalities before their occurrence. The approach is to build a patient-specific model and identify minor deviations from the normal signal, which can be indicative of potential upcoming significant deviations.
To enable an accurate deviation analysis, a controlled nonlinear transformation is proposed to reshape the feature space into a more symmetric geometry. We applied the developed algorithms on Electrocardiogram (ECG) signals and the results confirm the effectiveness of the proposed method in predicting upcoming heart abnormalities before their occurrence. For instance, the probability of observing a specific abnormality class increases by 10% after triggering a yellow alarm of the same type. This approach is general and has the potential to be applied to a wide range of physiological signals.
|Commitee:||Afghah, Fatemeh, Cambou, Bertrand, Razi, Abolfazl|
|School:||Northern Arizona University|
|Department:||Electrical and Computer Engineering|
|School Location:||United States -- Arizona|
|Source:||MAI 58/01M(E), Masters Abstracts International|
|Subjects:||Engineering, Biomedical engineering, Electrical engineering|
|Keywords:||Biomedical signal processing, ECG signals, Nonlinear transformation, Predictive modeling, Smart health|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be