Elaris Computing Nexus
Cross Modal Explainable Intelligence Architecture for Resource Aware Decision Optimization in Adaptive Computing Systems
Elaris Computing Nexus
Received On : 23 January 2026
Revised On : 24 March 2026
Accepted On : 30 March 2026
Published On : 06 April 2026
Volume 02, 2026
Pages : 053-066
Abstract
With the growing diversity of adaptive computing systems, there is a need for intelligent decision-making mechanisms that must optimize resource utilization, computation efficiency and maintain model transparency. However, most of the existing resource-aware optimization approaches do not consider cross-modal information integration and explainability, and thus cannot be applied to dynamic and constrained computing scenarios. In order to address these challenges, this paper presents an architecture for Cross-Modal Explainable Intelligence (CMEIA) for the Resource-Aware Decision Optimization in Adaptive Computing Systems. The proposed architecture involves the adaptive cross-modal fusion framework and the explainable intelligence module, which are used to fuse multimodal inputs and give transparent and interpretable decision pathways, respectively. A dynamic resource management engine continually adjusts the allocation of computational resources to meet contextual awareness, workload characteristics and system constraints, thereby allowing scalable and adaptive decision optimization. Unlike the traditional method which separately optimizes the resource and explains the model, the proposed model addresses all the three aspects of performance, explainability, and adaptability at the same time. Decision accuracy, utilization efficiency of resources, computational latency, energy consumption, throughput, scalability, fidelity of explanations, and level of confidence in decisions under different workloads are some of the critical performance parameters used to measure the effectiveness of CMEIA. An experimental assessment shows that the developed architecture optimizes the resources in a way that is superior, while simultaneously ensuring high levels of explainability and adaptability in heterogeneous computing environments. This framework is being used to greatly boost intelligent decision making, increase computational efficiency and yield transparent and trustworthy optimization strategies for next generation adaptive computing environments.
Keywords
Cross-Modal Explainable Intelligence, Resource-Aware Decision Optimization, Adaptive Computing Systems, Multimodal Data Fusion, Explainable Artificial Intelligence (XAI), Dynamic Resource Management.
- S. Yongqiang, “Integrating Deep Learning for Adaptive Management in Ubiquitous Computing Environments,” IEEE Access, vol. 13, pp. 213859–213885, 2025, doi: 10.1109/ACCESS.2025.3639261.
- J. Zhang and W. Wang, “Deep Learning-Based Perception and Recognition Framework for Autonomous Robots,” in Proc. 2026 Int. Conf. Robot Perception and Intelligent Control (RPIC), Mar. 2026, pp. 19–22, doi: 10.1109/RPIC68328.2026.11518084.
- C. Sharma, G. Poornalatha, and K. B. Ajitha Shenoy, “A Comprehensive Review of Recent Advances in Multimodal Multimedia Indexing and Retrieval,” IEEE Access, vol. 13, pp. 143688–143712, 2025, doi: 10.1109/ACCESS.2025.3597396.
- X. Li, X. Li, S. Hu, Z. Zhang, and K. H. Cheong, “Constraint-Driven Evolution of Multimodal Video Intelligence: A Network and System Perspective,” IEEE Trans. Netw. Sci. Eng., vol. 13, pp. 7667–7683, 2026, doi: 10.1109/TNSE.2026.3668404.
- C. Wang, “Deep Neural Network-Based Multi-Source Heterogeneous Data Fusion and Shared Computing Model in Wireless Networks,” Evolutionary Intelligence, vol. 19, no. 2, Mar. 2026, doi: 10.1007/s12065-026-01161-y.
- S. A. Cajas Ordóñez, J. Samanta, A. L. Suárez-Cetrulo, and R. S. Carbajo, “Intelligent Edge Computing and Machine Learning: A Survey of Optimization and Applications,” Future Internet, vol. 17, no. 9, p. 417, Sep. 2025, doi: 10.3390/fi17090417.
- N. SreeKanth, K. Padmanaban, R. G. Prasad, and L. Guganathan, “Responsible AI-Driven Optimized Cross-Hierarchical Structure-Detail-Aware Cascaded Capsule Neural Network for Intelligent 6G-IoT Attack Detection,” Int. J. Commun. Syst., vol. 39, no. 11, Jun. 2026, doi: 10.1002/dac.70525.
- S. Ebadinezhad and O. E. Adeshina, “The Frontier of Multi-Modal Fusion: A Systematic Review of Knowledge Graph-Guided Generative Augmentation,” in Proc. 2026 Int. Conf. Integrated Intelligence and Cognitive Engineering (ICIICE), Apr. 2026, pp. 1–7, doi: 10.1109/ICIICE69672.2026.11565368.
- X. Li, H. Li, C. Sun, Q. Fan, Z. Han, and V. C. M. Leung, “Edge-Enhanced Intelligence: A Comprehensive Survey of Large Language Models and Edge-Cloud Computing Synergy,” IEEE Commun. Surveys Tuts., vol. 28, pp. 1248–1284, 2026, doi: 10.1109/COMST.2025.3587225.
- W. U. Khan et al., “Multi-Modal Foundation Models for Space-Air-Ground Integrated 6G and Beyond Networks: A Survey and Tutorial,” IEEE Open J. Commun. Soc., vol. 7, pp. 4623–4659, 2026, doi: 10.1109/OJCOMS.2026.3687570.
- M. Ferdowsi, N. Moustafa, M. Keshk, and B. Turnbull, “Trustworthy Intelligence: Split Learning-Embedded Large Language Models for Smart IoT Healthcare Systems,” Electronics, vol. 15, no. 7, p. 1519, Apr. 2026, doi: 10.3390/electronics15071519.
- Z. Yang et al., “Generative AI for Wireless Communication and Sensing: Toward Unified Foundation Models,” IEEE Trans. Commun., vol. 74, pp. 10510–10539, 2026, doi: 10.1109/TCOMM.2026.3704192.
- K. Jha and A. Jain, “Tiny-Transformer Based Multimodal Biometric Authentication with Edge Fusion and Federated Split Learning,” Signal Image Video Process., vol. 20, no. 8, Jun. 2026, doi: 10.1007/s11760-026-05521-0.
- J. Li et al., “Integration of Generative AI and Mobile Networking: A Comprehensive Survey,” IEEE Trans. Netw. Sci. Eng., vol. 13, pp. 4369–4405, 2026, doi: 10.1109/TNSE.2025.3639401.
- Y. Zhang, “A Resource-Aware Multi-Fidelity Optimization Framework for Multimodal Music Information Analysis,” IETE Tech. Rev., pp. 1–20, Jul. 2026, doi: 10.1080/02564602.2026.2692719.
- C. Paduraru, M. Zavelca, and A. Stefanescu, “Agentic AI for Behavior-Driven Development Testing Using Large Language Models,” in Proc. 17th Int. Conf. Agents and Artificial Intelligence (ICAART), 2025, pp. 805–815, doi: 10.5220/0013374400003890.
CRediT Author Statement
The author reviewed the results and approved the final version of the manuscript.
Conceptualization: Arulmurugan Ramu and Anandakumar Haldorai; Methodology: Arulmurugan Ramu and Anandakumar Haldorai; Software: Arulmurugan Ramu and Anandakumar Haldorai; Data Curation: Arulmurugan Ramu; Writing- Original Draft Preparation: Anandakumar Haldorai; Visualization: Arulmurugan Ramu; Investigation: Arulmurugan Ramu and Anandakumar Haldorai; Supervision: Arulmurugan Ramu and Anandakumar Haldorai; Validation: Anandakumar Haldorai; Writing- Reviewing and Editing: Arulmurugan Ramu and Anandakumar Haldorai; All authors reviewed the results and approved the final version of the manuscript.
Acknowledgements
The author(s) received no financial support for the research, authorship, and/or publication of this article.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics Declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of Data and Materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author Information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding Author
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit: https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this Article
Arulmurugan Ramu and Anandakumar Haldorai, “Cross Modal Explainable Intelligence Architecture for Resource Aware Decision Optimization in Adaptive Computing Systems”, Elaris Computing Nexus, pp. 053-066, 2026, doi: 10.65148/ECN/2026005.
Copyright
© 2026 Arulmurugan Ramu and Anandakumar Haldorai. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.