Lyapunov-Stable Multispectral Edge DeepLearning for Critical Injury Triage and ResourceOptimisation in Emergency Response

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Traumatic injuries in emergency response scenarios require rapid and reliable assessment methods capable ofsupporting medical prioritisation and efficient resource management. This paper presents a multispectral edge deeplearning system designed for early injury detection, assistance prioritisation, and financial-resource decision support inemergency response environments. The proposed approach integrates RGB, thermal, near-infrared (NIR), depth, andcontextual information within an edge-based analytical framework that combines multispectral data fusion, adaptiveattention-based weighting of sensor modalities, convolutional neural networks for feature extraction and lesionsegmentation, severity classification, triage index estimation, and resource allocation optimisation. The developedmathematical model describes the interaction among sensory processing, local inference, decision-making, andfeedback-based model updating, and system stability is analysed using a Lyapunov-based approach under specifiedmodelling assumptions. The system was evaluated on a simulated dataset containing N = 1000 multispectralobservations, including 150 test samples for final performance assessment. The obtained results demonstratedpromising performance on simulated data, achieving Accuracy = 0.912 ± 0.015, Recallcrit = 0.941 ± 0.021, Precisioncrit= 0.876 ± 0.024, and F1-score = 0.908 ± 0.018. The average edge inference delay was 425 ms, satisfying the consideredreal-time processing threshold of 500 ms. Compared with the baseline emergency response scenario withoutmultispectral edge-based decision support, the proposed approach reduced triage decision errors by 18.6% andunproductive resource utilisation costs by 16.4%. The contribution of this research is the formulation of an integratedmultispectral edge deep learning framework that combines injury detection, automated triage assessment, resourceoptimisation, and financial risk considerations within a unified decision-support architecture. The results indicate thepotential of the proposed approach to improve emergency response processes. However, further validation on realworld clinical and operational datasets is required to confirm its practical applicability.