Authors:
Thomas Schmid
1
;
Dorothee Günzel
2
and
Martin Bogdan
1
Affiliations:
1
Universität Leipzig, Germany
;
2
Institute of Clinical Physiology, Germany
Keyword(s):
Impedance Spectroscopy, Epithelia, HT-29/B6, IPEC-J2, Machine Learning, Feature Selection, Decision Trees, Artificial Neural Networks, Random Forests.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Computer Vision, Visualization and Computer Graphics
;
Data Manipulation
;
Electromagnetic Fields in Biology and Medicine
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Medical Image Detection, Acquisition, Analysis and Processing
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Physiological Processes and Bio-Signal Modeling, Non-Linear Dynamics
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Theory and Methods
Abstract:
In epithelial physiology, it is common to use an equivalent electric circuit with two resistor-capacitor (RC)
subcircuits in series as a model for the electrical behavior of body cells. The relation between these two
subcircuits can be quantified by a quotient of their time constants t. While this quotient is a direct indicator
of the shape of impedance spectra, its value cannot be determined directly. Here, we suggest a machine
learning-based approach to predict the t quotient from impedance spectra. We perform systematic extraction of
statistical features, algorithmic feature ranking and dimension reduction on model impedance spectra derived
from tissue-equivalent electric circuits. Our results demonstrate that this quotient can be predicted reliably
enough from implicit features to discriminate semicircular against non-semicircular impedance spectra.