Journal article
Ensemble Learning Approach via Kalman Filtering for a Passive Wearable Respiratory Monitor
IEEE journal of biomedical and health informatics, v 23(3), pp 1022-1031
May 2019
PMID: 30040664
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
Objective: Utilizing passive radio frequency identification (RFID) tags embedded in knitted smartgarment devices, we wirelessly detect the respiratory state of a subject using an ensemble-based learning approach over an augmented Kalman-filtered time series of RF properties. Methods: We propose a novel approach for noise modeling using a "reference tag," a second RFID tag worn on the body in a location not subject to perturbations due to respiratory motions that are detected via the primary RFID tag. The reference tag enables modeling of noise artifacts yielding significant improvement in detection accuracy. The noise is modeled using autoregressive moving average (ARMA) processes and filtered using stateaugmented Kalman filters. The filtered measurements are passed through multiple classification algorithms (naive Bayes, logistic regression, decision trees) and a new similarity classifier that generates binary decisions based on current measurements and past decisions. Results: Our findings demonstrate that state-augmented Kalman filters for noise modeling improves classification accuracy drastically by over 7.7% over the standard filter performance. Furthermore, the fusion framework used to combine local classifier decisions was able to predict the presence or absence
Metrics
Details
- Title
- Ensemble Learning Approach via Kalman Filtering for a Passive Wearable Respiratory Monitor
- Creators
- Sayandeep Acharya - Department of Electrical and Computer Engineering, Drexel University College of Engineering, Philadelphia, PA, USAWilliam M Mongan - Department of Computer Science, Drexel University College of Computing and Informatics, Philadelphia, PA, USAIlhaan Rasheed - Department of Electrical and Computer Engineering, Drexel University College of Engineering, Philadelphia, PA, USAYuqiao Liu - Department of Electrical and Computer Engineering, Drexel University College of Engineering, Philadelphia, PA, USAEndla Anday - Department of Pediatrics, Drexel University College of Medicine, Philadelphia, PA, USAGenevieve Dion - Westphal College of Media Arts and Design, Drexel University, Philadelphia, PA, USAAdam Fontecchio - Department of Electrical and Computer Engineering, Drexel University College of Engineering, Philadelphia, PA, USATimothy Kurzweg - School of Engineering, Penn State Behrend, Erie, PA, USAKapil R Dandekar - Department of Electrical and Computer Engineering, Drexel University College of Engineering, Philadelphia, PA, USA
- Publication Details
- IEEE journal of biomedical and health informatics, v 23(3), pp 1022-1031
- Publisher
- IEEE
- Grant note
- Commonwealth of Pennsylvania 1430212 / National Science Foundation (10.13039/100000001) U01EB023035 / National Institute of Biomedical Imaging and Bioengineering (10.13039/100000070)
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Electrical and Computer Engineering; Pediatrics; Fashion Design
- Web of Science ID
- WOS:000467060400013
- Scopus ID
- 2-s2.0-85050378052
- Other Identifier
- 991014878443804721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Computer Science, Information Systems
- Computer Science, Interdisciplinary Applications
- Mathematical & Computational Biology
- Medical Informatics