ItemArticle

Hybrid fractional thermoelasticmachine learning framework for heat and mass transfer in skin tissue: Enhanced simulations using AtanganaBaleanu, CattaneoVernotte models, and KNNSVM classifiers

Title
Hybrid fractional thermoelasticmachine learning framework for heat and mass transfer in skin tissue: Enhanced simulations using AtanganaBaleanu, CattaneoVernotte models, and KNNSVM classifiers
Creator
Singhal, Abhinav; Seema; Saeed, Abdulkafi Mohammed; Tiwari, Rakhi; Chaudhary, Anjali
Description
This study presents a hybrid computational framework that couples advanced fractional thermoelastic modeling with machine-learning-based safety classification for heat and mass transfer in skin tissue. The classical CattaneoVernotte (CV) non-Fourier heat conduction law is extended through the AtanganaBaleanu (AB) fractional operator to capture memory-driven thermal responses, finite thermal wave propagation, and nonlocal biological effects more accurately than traditional Fourier-type formulations. Closed-form expressions are derived using Laplace transforms and inverted numerically to obtain transient temperature, displacement, dilation, and stress fields within the tissue. The AB fractional model demonstrates smoother thermal evolution, reduced overshoot, and lower stress concentrations relative to the CV model, reflecting improved biomedical safety margins during rapid thermal exposure. To enable real-time risk assessment, synthetic datasets generated from the thermoelastic simulations are used to train Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) classifiers. The ML models reliably distinguish safe and risky thermal regimes, with SVM offering superior generalization and KNN capturing localized variations. The novelty of this work lies in directly integrating fractional physics-based modeling with machine-learning classification for thermal safety diagnosticsestablishing a unified paradigm for predictive biomedical heat transfer. The framework advances thermal therapy planning, burn-injury prevention, implant design, and smart clinical monitoring. While the current study is based on idealized geometry and simulated data, future extensions will incorporate in-vivo tissue characteristics, complex skin layers, and deep learning models to further enhance clinical applicability. 2025 Elsevier Ltd
Source
International Communications in Heat and Mass Transfer;Volume;171;Issue;;Article No.;110074;
Date
01-01-2026
Publisher
Elsevier Ltd
Subject
AtanganaBaleanu operator; Bioheat transfer; Biomedical applications; CattaneoVernotte law; Fractional models; Heat and mass transfer; Hybrid simulations; KNN; Laplace transform; Machine learning; SVM; Thermal stress; Thermoelasticity
Coverage
Singhal A., Christ University, Bengaluru, 560029, India; Seema, Christ University, Bengaluru, 560029, India; Saeed A.M., Department of Mathematics, College of Science, Qassim University, Buraydah, 51452, Saudi Arabia; Tiwari R., University Department of Mathematics, Babasaheb Bhimrao Ambedkar Bihar University, Muzaffarpur, India; Chaudhary A., Department of Management, College of Business Administration, Princess Nourah bint Abdulrahman University, P.O.Box 84428, Riyadh, 11671, Saudi Arabia
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISSN: 7351933; CODEN: IHMTD
Format
online
Language
English
Type
Article

Citation

Singhal, Abhinav; Seema; Saeed, Abdulkafi Mohammed; Tiwari, Rakhi; Chaudhary, Anjali, “Hybrid fractional thermoelasticmachine learning framework for heat and mass transfer in skin tissue: Enhanced simulations using AtanganaBaleanu, CattaneoVernotte models, and KNNSVM classifiers,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 19, 2026, https://archives.christuniversity.in/items/show/22279.

Output Formats