International Journal of Image, Graphics and Signal Processing (IJIGSP)
IJIGSP Vol. 18, No. 5, 8 Oct. 2026
Cover page and Table of Contents: PDF (size: 2776KB)
Lyapunov-Stable Multispectral Edge Deep Learning for Critical Injury Triage and Resource Optimisation in Emergency Response
PDF (2776KB), PP.126-184
Views: 0 Downloads: 0
Author(s)
Serhii Vladov
1,2
Zhengbing Hu
3
Dmytro Uhryn
2,*
Yuriy Ushenko
2
Victoria Vysotska
1,4
Vladyslav Doroshenko
1
Daniil Zinchenko
1
Index Terms
Multispectral System, Edge Computing, Deep Learning, Lesion Detection, Triage, Emergency Response, Financial Security, Resource Optimisation, Simulated Dataset, Stability Analysis.
Abstract
Traumatic injuries in emergency response scenarios require rapid and reliable assessment methods capable of supporting medical prioritisation and efficient resource management. This paper presents a multispectral edge deep learning system designed for early injury detection, assistance prioritisation, and financial-resource decision support in emergency response environments. The proposed approach integrates RGB, thermal, near-infrared (NIR), depth, and contextual information within an edge-based analytical framework that combines multispectral data fusion, adaptive attention-based weighting of sensor modalities, convolutional neural networks for feature extraction and lesion segmentation, severity classification, triage index estimation, and resource allocation optimisation. The developed mathematical model describes the interaction among sensory processing, local inference, decision-making, and feedback-based model updating, and system stability is analysed using a Lyapunov-based approach under specified modelling assumptions. The system was evaluated on a simulated dataset containing N = 1000 multispectral observations, including 150 test samples for final performance assessment. The obtained results demonstrated promising 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 considered real-time processing threshold of 500 ms. Compared with the baseline emergency response scenario without multispectral edge-based decision support, the proposed approach reduced triage decision errors by 18.6% and unproductive resource utilisation costs by 16.4%. The contribution of this research is the formulation of an integrated multispectral edge deep learning framework that combines injury detection, automated triage assessment, resource optimisation, and financial risk considerations within a unified decision-support architecture. The results indicate the potential of the proposed approach to improve emergency response processes. However, further validation on real-world clinical and operational datasets is required to confirm its practical applicability.
Cite This Paper
Serhii Vladov, Zhengbing Hu, Dmytro Uhryn, Yuriy Ushenko, Victoria Vysotska, Vladyslav Doroshenko, Daniil Zinchenko, "Lyapunov-Stable Multispectral Edge Deep Learning for Critical Injury Triage and Resource Optimisation in Emergency Response", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.18, No.5, pp. 126-184, 2026. DOI:10.5815/ijigsp.2026.05.08
Reference
[1]World Health Organization: Injuries and violence. Available online: https://www.who.int/news-room/fact-sheets/detail/injuries-and-violence
[2]World Health Organization: Road traffic injuries. Available online: https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries
[3]Y. Xu, T. M. Khan, Y. Song, and E. Meijering, “Edge deep learning in computer vision and medical diagnostics: A comprehensive survey,” Artificial Intelligence Review, vol. 58, 93, 2025, doi: 10.1007/s10462-024-11033-5
[4]A. Rocha, M. Monteiro, C. Mattos, M. Dias, J. Soares, R. Magalhães, and J. Macedo, “Edge AI for Internet of Medical Things: A literature review”, Computers and Electrical Engineering, 116, 109202, 2024. https://doi.org/10.1016/j.compeleceng.2024.109202
[5]World Bank Group: A Decade of Saving Lives Through Road Safety Investments. Available online: https://www.worldbank.org/en/results/2024/03/25/a-decade-of-saving-lives-through-road-safety-investments
[6]C. E. Marcussen, K. B. Bräuner, H. Alstrøm, and A. M. Møller, “Accuracy of prehospital triage systems for mass casualty incidents in trauma register studies—A systematic review and meta-analysis of diagnostic test accuracy studies,” Injury, vol. 53, no. 8, pp. 2725–2733, 2022, https://doi.org/10.1016/j.injury.2022.05.006
[7]T. Cheng, K. Staats, A. H. Kaji, N. D’Arcy, K. Niknam, and J. J. Donofrio-Odmann, “Comparison of prehospital professional accuracy, speed, and interrater reliability of six pediatric triage algorithms,” JACEP Open, vol. 3, no. 1, e12613, 2022, https://doi.org/10.1002/emp2.12613
[8]J. M. Zachariasse, N. Seiger, P. P. M. Rood, C. F. Alves, P. Freitas, F. J. Smit, G. R. Roukema, and H. A. Moll, “Validity of the Manchester Triage System in emergency care: A prospective observational study,” PLOS ONE, vol. 12, no. 2, Art. no. e0170811, 2017, https://doi.org/10.1371/journal.pone.0170811
[9]M. Hegarty-Craver, H. Davis-Wilson, P. Gaur, H. Walls, D. Dausch, and D. Temple, Wearable Sensors for Service Members and First Responders: Considerations for Using Commercially Available Sensors in Continuous Monitoring. Research Triangle Park, NC, USA: RTI Press, 2024.
[10]J. Gutiérrez, V. Rodríguez, and S. Martín, “Comprehensive review of vision-based fall detection systems,” Sensors, vol. 21, no. 3, 947, 2021, https://doi.org/10.3390/s21030947
[11]E. Alam, S. Sufian, P. Dutta, and M. Leo, “Vision-based human fall detection systems using deep learning: A review,” Computers in Biology and Medicine, vol. 146, 105626, 2022, https://doi.org/10.1016/j.compbiomed.2022.105626
[12]Y. He, B. Deng, H. Wang, L. Cheng, K. Zhou, S. Cai, and F. Ciampa, “Infrared machine vision and infrared thermography with deep learning: A review,” Infrared Physics & Technology, vol. 116, 103754, 2021, https://doi.org/10.1016/j.infrared.2021.103754
[13]D. Kesztyüs, S. Brucher, C. Wilson, and T. Kesztyüs, “Use of infrared thermography in medical diagnosis, screening, and disease monitoring: A scoping review,” Medicina, vol. 59, no. 12, 2139, 2023, https://doi.org/10.3390/medicina59122139
[14]G. Rouhafzay, S. Rowlands, A. J. Valencia, S. Yang, P. Payeur, H. Tian, and J. Dickens, “Multi-spectral imaging and data fusion for real-time bleeding detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025, pp. 4561–4568.
[15]A. Rancea, I. Anghel, and T. Cioara, “Edge Computing in Healthcare: Innovations, Opportunities, and Challenges,” Future Internet, vol. 16, no. 9, 329, 2024, https://doi.org/10.3390/fi16090329
[16]M. Satyanarayanan, “The Emergence of Edge Computing,” Computer, vol. 50, no. 1, pp. 30–39, 2017, https://doi.org/10.1109/MC.2017.9
[17]D. Borrmann, J. Elseberg, K. Lingemann, and A. Nüchter, “The 3D Hough Transform for Plane Detection in Point Clouds: A Review and a New Accumulator Design,” 3D Research, vol. 2, no. 2, 3, 2011, https://doi.org/10.1007/3DRes.02(2011)3
[18]S. Hwang, J. Park, N. Kim, Y. Choi, and I. S. Kweon, “Multispectral pedestrian detection: Benchmark dataset and baseline,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1037–1045. https://doi.org/10.1109/CVPR.2015.7298706.
[19]M. Brenner, N. H. Reyes, T. Susnjak, and A. L. C. Barczak, “MM5: Multimodal image capture and dataset generation for RGB, depth, thermal, UV, and NIR,” Information Fusion, vol. 126, 103516, 2026. https://doi.org/10.1016/j.inffus.2025.103516
[20]M. Brenner, N. H. Reyes, T. Susnjak, and A. L. C. Barczak, “RGB-D and Thermal Sensor Fusion: A Systematic Literature Review,” IEEE Access, vol. 11, pp. 82410–82442, 2023, https://doi.org/10.1109/access.2023.3301119
[21]S. Kalamkar and A. Geetha Mary, “Multimodal image fusion: A systematic review,” Decision Analytics Journal, vol. 9, 100327, 2023. https://doi.org/10.1016/j.dajour.2023.100327
[22]C. Shorten and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of Big Data, vol. 6, 60, 2019, https://doi.org/10.1186/s40537-019-0197-0
[23]F. Yang, G. Zamzmi, S. Angara, S. Rajaraman, A. Aquilina, Z. Xue, S. Jaeger, E. Papagiannakis, and S. K. Antani, “Assessing inter-annotator agreement for medical image segmentation,” IEEE Access, vol. 11, pp. 21300–21312, 2023. https://doi.org/10.1109/ACCESS.2023.3249759
[24]S. W. Lee, “Methods for testing statistical differences between groups in medical research: Statistical standard and guideline of Life Cycle Committee,” Life Cycle, vol. 2, e1, 2022, https://doi.org/10.54724/lc.2022.e1
[25]H. J. Yang and H. S. Lee, “Common statistical methods used in medical research,” Kosin Medical Journal, vol. 40, no. 1, pp. 21–30, 2025, https://doi.org/10.7180/kmj.24.160
[26]Y. Zhou, Y. Zhu, and W. K. Wong, “Statistical tests for homogeneity of variance for clinical trials and recommendations,” Contemporary Clinical Trials Communications, vol. 33, 101119, 2023, https://doi.org/10.1016/j.conctc.2023.101119
[27]D. Chicco, A. Sichenze, and G. Jurman, “A simple guide to the use of Student’s t-test, Mann–Whitney U test, Chi-squared test and Kruskal–Wallis test in biostatistics,” BioData Mining, vol. 18, no. 1, 56, 2025, https://doi.org/10.1186/s13040-025-00465-6
[28]G. Hripcsak, L. Zhang, Y. Chen, K. Li, M. A. Suchard, P. B. Ryan, and M. J. Schuemie, “Assessing covariate balance with small sample sizes,” Statistics in Medicine, vol. 44, no. 18–19, e70212, 2025. https://doi.org/10.1002/sim.70212
[29]C. Wongoutong, “The impact of neglecting feature scaling in k-means clustering,” PLOS ONE, vol. 19, no. 12, e0310839, 2024, https://doi.org/10.1371/journal.pone.0310839
[30]A. Naghizadeh and D. N. Metaxas, “Condensed Silhouette: An optimized filtering process for cluster selection in K-means,” Procedia Computer Science, vol. 176, pp. 205–214, 2020, https://doi.org/10.1016/j.procs.2020.08.022
[31]W. Junthopas, K. Khamdee, and P. Khamdee, “Pre-determining the optimal number of clusters for k-means clustering using the parameters package in R and distance metrics,” Applied Sciences, vol. 15, no. 21, 11372, 2025, https://doi.org/10.3390/app152111372
[32]I. T. Utami, F. Suryaningrum, and D. Ispriyanti, “K-means cluster count optimization with Silhouette Index validation and Davies Bouldin Index: Case study—coverage of pregnant women, childbirth, and postpartum health services in Indonesia in 2020,” BAREKENG: Jurnal Ilmu Matematika dan Terapan, vol. 17, no. 2, pp. 707–716, 2023, https://doi.org/10.30598/barekengvol17iss2pp0707-0716
[33]D. Chicco, A. Campagner, A. Spagnolo, D. Ciucci, and G. Jurman, “The Silhouette coefficient and the Davies-Bouldin index are more informative than Dunn index, Calinski-Harabasz index, Shannon entropy, and Gap statistic for unsupervised clustering internal evaluation of two convex clusters,” PeerJ Computer Science, vol. 11, e3309, 2025. https://doi.org/10.7717/peerj-cs.3309
[34]A. J. Suda, A. Franke, M. Hertwig, and K. Gooßen, “Management of mass casualty incidents: a systematic review and clinical practice guideline update,” European Journal of Trauma and Emergency Surgery, vol. 51, no. 1, 5, 2025. https://doi.org/10.1007/s00068-024-02727-0
[35]F. Pu, Z. Li, Y. Wu, C. Ma, and R. Zhao, “Recent advances in disaster emergency response planning: Integrating optimization, machine learning, and simulation,” Safety Emergency Science, vol. 1, no. 1, 9590007, 2025. https://doi.org/10.26599/SES.2025.9590007
[36]J. Wei, Z. Zou, W. Lai, J. Du, J. Zhao, Z. Liu, and S. Wang, “RGB-Thermal cameras calibration based on Maximum Index Map,” Computers and Electrical Engineering, vol. 123, 110234, 2025. https://doi.org/10.1016/j.compeleceng.2025.110234
[37]W. Yang, H. Luo, K.-W. Tse, H. Hu, K. Liu, B. Li, and C.-Y. Wen, “Autonomous–Targetless Extrinsic Calibration of Thermal, RGB, and LiDAR Sensors,” IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1–11, 2024. https://doi.org/10.1109/TIM.2024.3480237
[38]J. E. Bloom et al., “Healthcare and economic cost burden of emergency medical services treated non-traumatic shock using a population-based cohort in Victoria, Australia,” BMJ Open, vol. 14, no. 4, e078435, 2024. https://doi.org/10.1136/bmjopen-2023-078435
[39]M. S. Rasmussen, Y. Zhang, N. Andelic, and E. Aas, “Health care costs and service utilization in the first year following moderate to severe traumatic injury,” BMC Health Services Research, vol. 24, 1535, 2024. https://doi.org/10.1186/s12913-024-12016-6
[40]D. Orso, L. Flaibani, U. G. Sisto, M. Bonsano, F. Fonda, R. Pangallo, and T. Bove, “Survival and cost-effectiveness of helicopter versus ground emergency medical services: A systematic review and meta-analysis with meta-regression and trial sequential analysis,” Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine, vol. 33, no. 1, 160, 2025. https://doi.org/10.1186/s13049-025-01478-0
[41]T. K. Das, S. K. Das, S. Bissoyi, and D. K. Patel, “Self-adaptive Resource Allocation in Fog-Cloud Systems Using Multi-agent Deep Reinforcement Learning with Meta-learning,” International Journal of Intelligent Systems and Applications (IJISA), vol. 18, no. 1, pp. 107–118, 2026, https://doi.org/10.5815/ijisa.2026.01.08
[42]C. S. Odeyemi and O. M. Olaniyan, “Development of a Facenet Enhanced Secured Smart Office System,” International Journal of Intelligent Systems and Applications (IJISA), vol. 16, no. 1, pp. 41–51, 2024, https://doi.org/10.5815/ijisa.2024.01.04
[43]V. S. Rana, A. Joshi, and K. K. Verma, “Lightweight 3DCNN-BiLSTM Model for Human Activity Recognition using Fusion of RGBD Video Sequences,” International Journal of Information Technology and Computer Science (IJITCS), vol. 17, no. 6, pp. 176–193, 2025, https://doi.org/10.5815/ijitcs.2025.06.10
[44]S. Vladov, L. Chyrun, E. Muzychuk, V. Vysotska, V. Lytvyn, T. Rekunenko, A. Basko, “Intelligent Method for Generating Criminal Community Influence Risk Parameters Using Neural Networks and Regional Economic Analysis,” Algorithms, vol. 18, no. 8, 523, 2025, https://doi.org/10.3390/a18080523
[45]S. Vladov, Ł. Ścisło, A. Sachenko, H. Foros, D. Zhuravlov, V. Vysotska, V. Varlakhov, S. Sachenko, J. Krupiński, O. Brusakova, “Neural Network DDoS Mitigation System With Forensic Audit Support for Cyber Police,” IEEE Access, vol. 13, pp. 204628–204655, 2025, https://doi.org/10.1109/access.2025.3634478
[46]S. Vladov, Y. Shmelov, R. Yakovliev, “Optimization of Helicopters Aircraft Engine Working Process Using Neural Networks Technologies,” CEUR Workshop Proceedings, vol. 3171, pp. 1639–1656, 2022. URL: https://ceur-ws.org/Vol-3171/paper117.pdf
[47]S. Vladov, R. Yakovliev, O. Hubachov, J. Rud, “Neuro-Fuzzy System for Detection Fuel Consumption of Helicopters Turboshaft Engines,” CEUR Workshop Proceedings, vol. 3628, pp. 55–72, 2023. URL: https://ceur-ws.org/Vol-3628/paper5.pdf
[48]S. Vladov, M. Petchenko, Y. Shmelov, S. Drozdova, R. Yakovliev, “Helicopters Turboshaft Engines Parameters Identification at Flight Modes Using Neural Networks,” in Proceedings of the 2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT), Lviv, Ukraine, 2022, pp. 5–8. https://doi.org/10.1109/csit56902.2022.10000444
[49]K. Naoufel, “Towards Automated Diagnosis of Heart Diseases: A Study of Machine Learning Techniques,” International Journal of Engineering and Manufacturing (IJEM), vol. 16, no. 2, pp. 143–155, 2026, https://doi.org/10.5815/ijem.2026.02.09
[50]S. Vladov, A. Banasik, A. Sachenko, W. M. Kempa, V. Sokurenko, O. Muzychuk, P. Pikiewicz, A. Molga, V. Vysotska, “Intelligent Method of Identifying the Nonlinear Dynamic Model for Helicopter Turboshaft Engines,” Sensors, vol. 24, no. 19, p. 6488, Oct. 2024, https://doi.org/10.3390/s24196488
[51]S. Vladov, Y. Shmelov, R. Yakovliev, M. Petchenko, “Neural Network Method for Parametric Adaptation Helicopters Turboshaft Engines On-Board Automatic Control System Parameters,” CEUR Workshop Proceedings, vol. 3403, pp. 179–195, 2023. URL: https://ceur-ws.org/Vol-3403/paper15.pdf
[52]R. S. Lutfi, “A Neutrosophic-Based Unsupervised Approach for Sudden Drift Detection,” International Journal of Intelligent Systems and Applications (IJISA), vol. 18, no. 2, pp. 139–155, 2026, https://doi.org/10.5815/ijisa.2026.02.10
[53]S. Sularno, B. Wendi, A. P. Putri, A. Kamal, and F. Wang, “Data-driven classification of tsunami evacuation suitability using XGBoost: A case study in Padang City,” International Journal of Intelligent Systems and Applications (IJISA), vol. 18, no. 1, pp. 90–106, 2026. https://doi.org/10.5815/ijisa.2026.01.07
[54]G. Wali and C. Bulla, “A Resource Management Model for Healthcare Internet of Things Using Deep Learning and Bio-inspired Algorithms,” International Journal of Information Engineering and Electronic Business (IJIEEB), vol. 17, no. 1, pp. 68–89, 2025, https://doi.org/10.5815/ijieeb.2025.01.05
[55]S. Ablamskyi, E. Kazić Çakar, and I. Hloviuk, “A comparative study of wartime rapes: The experience of Bosnia and Herzegovina and Ukraine,” Baltic Journal of Law & Politics, vol. 17, no. 1, pp. 136–162, 2024, https://doi.org/10.2478/bjlp-2024-0007
[56]L. C. Gamarra-Amaya, I. Hloviuk, and S. Ablamskyi, “Implementation of international legal frameworks to combat domestic violence in Ukraine and Colombia,” Via Inveniendi et Iudicandi, vol. 18, no. 2, pp. 209–233, 2024, https://doi.org/10.15332/19090528.9740
[57]S. Ablamskyi, V. Galagan, I. Basysta, and Z. Udovenko, “Detention of a person suspected of committing a criminal offense during martial law in Ukraine,” Revista Brasileira de Políticas Públicas, vol. 13, no. 3, pp. 452–467, 2023, https://doi.org/10.5102/rbpp.v13i3.9129
[58]V. V. Romaniuk and S. Ye. Ablamskyi, “Criteria for the admissibility of digital (electronic) evidence in criminal proceedings,” Law and Safety, vol. 93, no. 2, pp. 140–150, 2024, https://doi.org/10.32631/pb.2024.2.13
[59]S. Ablamskyi, A. Kavunska, O. Perederii, O. Tymofiiv, and A. Zuhdi, “Adaptation of the legal system of Ukraine in the era of digitalization: Challenges, threats and possible ways to overcome them,” Revista Jurídica Portucalense, no. 37, 2025, https://doi.org/10.34625/issn.2183-2705(37)2025.ic-19
[60]V. Sokurenko, K. Levchenko, S. Ablamskyi, O. Pereira de Lima Jr, G. Šimić, and V. Romaniuk, “The legal regime of the martial state in Ukraine and its impact on the conduct of pre-trial investigation: New challenges and their overcoming,” Via Inveniendi et Iudicandi, vol. 19, no. 2, pp. 92–111, 2024, https://doi.org/10.15332/19090528.10671
[61]S. Ablamskyii, I. Hloviuk, E. Kazić Çakar, and I. Zinkovskyy, “Addressing enforced disappearances in criminal law: Legal and procedural perspectives from Ukraine and Bosnia and Hercegovina,” Prawo i Więź, vol. 57, no. 4, pp. 896–914, 2025, https://doi.org/10.36128/PRIW.VI57.1329
[62]S. Ye, T. Wang, M. Ding, and X. Zhang, “F-DARTS: Foveated Differentiable Architecture Search Based Multimodal Medical Image Fusion,” IEEE Transactions on Medical Imaging, vol. 42, no. 11, pp. 3348–3361, Nov. 2023, https://doi.org/10.1109/TMI.2023.3283517.
[63]X. Zhou, Y. Sun, M. Deng, W. C. W. Chu, and Q. Dou, “Robust Semi-supervised Multimodal Medical Image Segmentation via Cross Modality Collaboration,” in Medical Image Computing and Computer Assisted Intervention (MICCAI 2024), Springer, LNCS 15001, pp. 57–67, 2024, https://doi.org/10.1007/978-3-031-72378-0_6.
[64]S. Ding, J. Li, J. Wang, S. Ying, and J. Shi, “Multimodal Co-Attention Fusion Network With Online Data Augmentation for Cancer Subtype Classification,” IEEE Transactions on Medical Imaging, vol. 43, no. 11, pp. 3977–3989, Nov. 2024, https://doi.org/10.1109/TMI.2024.3405535.
[65]R. Berzoini, E. D’Arnese, D. Conficconi, and M. D. Santambrogio, “NERONE: The Fast Way to Efficiently Execute Your Deep Learning Algorithm at the Edge,” IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 3, pp. 1252–1260, Mar. 2024, https://doi.org/10.1109/JBHI.2023.3296142.
[66]J. M. Rodríguez Corral, J. Civit-Masot, F. Luna-Perejón, I. Díaz-Cano, A. Morgado-Estévez, and M. Domínguez-Morales, “Energy Efficiency in Edge TPU vs. Embedded GPU for Computer-Aided Medical Imaging Segmentation and Classification,” Engineering Applications of Artificial Intelligence, vol. 127, 107298, 2024, https://doi.org/10.1016/j.engappai.2023.107298.
[67]X. Xu, K. Yan, S. Han, B. Wang, X. Tao, and P. Zhang, “Learning-Based Edge-Device Collaborative DNN Inference in IoVT Networks,” IEEE Internet of Things Journal, vol. 11, no. 5, pp. 7989–8004, Mar. 2024, https://doi.org/10.1109/JIOT.2023.3317785.