| Abstrak/Abstract |
Conductivity change in skin layers has been classified by source
indicator ???????? (k=1: Stratum corneum, k=2: Epidermis, k=3: Dermis,
k=4: Fat, and k=5: Stratum corneum + Epidermis) trained from
feedforward neural network (FNN) in bioelectrical impedance
spectroscopy (BIS). In BIS studies, treating the skin as a bulk, limits
the differentiation of conductivity changes in individual skin layers,
however skin layer classification using FNN shows promise in
accurately categorizing skin layers, which is essential for predicting
source indicators ???????? and initiating skin dielectric characteristics
diagnosis. The ???????? is trained by three main conceptual points which
are (i) implementing FNN for predicting k in conductivity change, (ii)
profiling four impedance inputs ???????? consisting of magnitude input
????|????|, phase angle input ????????, resistance input ????????, and reactance input
???????? for filtering nonessential input, and (iii) selecting low and high
frequency pair (????????????ℎ ) by distribution of relaxation time (DRT) for
eliminating parasitic noise effect. The training data set of FNN is
generated to obtain the ???????? ∈ ????10×17×10 by 10,200 cases by
simulation under configuration and measurement parameters. The
trained skin layer classification is validated through experiments
with porcine skin under various sodium chloride (NaCl) solutions
???????????????????? = {15, 20, 25, 30, 35}[mM] in the dermis layer. FNN
successfully classified conductivity change in the dermis layer from
experiment with accuracy of 90.6% for the bipolar set-up at ????6
????ℎ =
10 & 100 [kHz] and with the same accuracy for the tetrapolar at
????8
????ℎ = 35 & 100 [kHz] . The measurement noise and systematic
error in the experimental results are minimized by the proposed
method using the feature extraction based on ???????? at ????????????ℎ. |
