Skin layer classification by feedforward neural network in bioelectrical impedance spectroscopy.

Autor: Ibrahim KA; Department of Mechanical Engineering, Graduate School of Science and Engineering, Chiba University, Chiba, Japan., Baidillah MR; Research Center for Electronics, National Research and Innovation Agency, KST Samaun Samadikun, Bandung, Indonesia., Wicaksono R; Electrical and Information Engineering Department, Faculty of Engineering, Universitas Gadjah Mada, Yogyakarta, Indonesia., Takei M; Department of Mechanical Engineering, Graduate School of Science and Engineering, Chiba University, Chiba, Japan.
Jazyk: angličtina
Zdroj: Journal of electrical bioimpedance [J Electr Bioimpedance] 2023 Aug 10; Vol. 14 (1), pp. 19-31. Date of Electronic Publication: 2023 Aug 10 (Print Publication: 2023).
DOI: 10.2478/joeb-2023-0004
Abstrakt: Conductivity change in skin layers has been classified by source indicator o k ( 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 o k and initiating skin dielectric characteristics diagnosis. The o k is trained by three main conceptual points which are (i) implementing FNN for predicting k in conductivity change, (ii) profiling four impedance inputs α ξ consisting of magnitude input α | z |, phase angle input α θ , resistance input α R , and reactance input α x for filtering nonessential input, and (iii) selecting low and high frequency pair ( f r l h ) by distribution of relaxation time (DRT) for eliminating parasitic noise effect. The training data set of FNN is generated to obtain the α ξ ∈ R 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 C NaCl = {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 f 6 l h = 10   & 100   [ kHz] and with the same accuracy for the tetrapolar at f 8 l 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 α ξ at f r l h .
Competing Interests: Conflict of interest Authors state no conflict of interest.
(© 2023 Kiagus Aufa Ibrahim et al., published by Sciendo.)
Databáze: MEDLINE
Externí odkaz: