TY - GEN
T1 - Multiclass SVM for Bladder Volume Monitoring using Electrical Impedance Measurements
AU - Santorelli, Adam
AU - Dunne, Eoghan
AU - Porter, Emily
AU - Orhalloran, Martin
N1 - Publisher Copyright:
© 2018 FESB, University of Split.
PY - 2018/11/6
Y1 - 2018/11/6
N2 - Urinary incontinence is a common condition that impacts the quality of life from those who suffer from it. Electrical impedance measurements offer the potential for a non-invasive low-cost solution to monitor changes in the bladder volume. This work focuses on using a multiclass support vector machine (SVM) algorithm to classify the fullness of the bladder into three states; not full, full, and a boundary class. This paper applies this machine learning algorithm to both simulation and experimental data. The SVM model uses the recorded voltages from electrical impedance measurements as features, is trained and optimized using a Bayesian Optimization approach, and then 10-fold cross-tested to obtain a generalized error. This paper demonstrates that simulation data with a signal-to-noise ratio of 40 dB, and experimental data from a pelvis phantom, can be perfectly separated into the three classes defined above.
AB - Urinary incontinence is a common condition that impacts the quality of life from those who suffer from it. Electrical impedance measurements offer the potential for a non-invasive low-cost solution to monitor changes in the bladder volume. This work focuses on using a multiclass support vector machine (SVM) algorithm to classify the fullness of the bladder into three states; not full, full, and a boundary class. This paper applies this machine learning algorithm to both simulation and experimental data. The SVM model uses the recorded voltages from electrical impedance measurements as features, is trained and optimized using a Bayesian Optimization approach, and then 10-fold cross-tested to obtain a generalized error. This paper demonstrates that simulation data with a signal-to-noise ratio of 40 dB, and experimental data from a pelvis phantom, can be perfectly separated into the three classes defined above.
KW - Bladder volume monitoring
KW - Classification algorithms
KW - Electrical impedance
KW - Machine learning
UR - https://www.scopus.com/pages/publications/85057726882
U2 - 10.23919/EMF-MED.2018.8526015
DO - 10.23919/EMF-MED.2018.8526015
M3 - Conference Publication
AN - SCOPUS:85057726882
T3 - EMF-Med 2018 - 1st EMF-Med World Conference on Biomedical Applications of Electromagnetic Fields and COST EMF-MED Final Event with 6th MCM
BT - EMF-Med 2018 - 1st EMF-Med World Conference on Biomedical Applications of Electromagnetic Fields and COST EMF-MED Final Event with 6th MCM
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1st EMF-Med World Conference on Biomedical Applications of Electromagnetic Fields, EMF-Med 2018
Y2 - 10 September 2018 through 13 September 2018
ER -