Context-Aware Artificial Intelligence for Adaptive Decision Support in Resource-Constrained Institutions

Liam Anderson

Context-Aware Artificial Intelligence for Adaptive Decision Support in Resource-Constrained Institutions

Author(s)	Dr. Liam Anderson
Country	United States
Abstract	Artificial intelligence has become increasingly relevant to institutional decision support; however, many contemporary systems implicitly assume reliable connectivity, adequate computational capacity, sufficient staffing, stable workloads, and consistently available data. These assumptions are frequently unrealistic in resource-constrained institutions, where decisions must be made under fluctuating bandwidth, limited computing infrastructure, personnel shortages, incomplete information, and sudden changes in service demand. This study proposes a Context-Aware Artificial Intelligence Decision Support System (CAAI-DSS) designed to adapt its decision logic, computational behavior, confidence thresholds, and level of human involvement according to prevailing institutional conditions. The proposed architecture integrates contextual sensing, lightweight predictive inference, adaptive resource-aware reasoning, confidence-based human escalation, and governance controls within a unified decision-support framework. A reproducible simulation-based evaluation was conducted using 1,500 synthetic decision episodes distributed across five operational scenarios: low bandwidth, restricted computing capacity, staff shortage, demand surge, and mixed-resource constraints. The proposed system was compared with a conventional static artificial intelligence decision-support configuration and a rules-based decision approach. Simulation results indicated that the context-aware model achieved an overall decision accuracy of 78.6%, compared with 61.3% for static artificial intelligence and 51.5% for the rules-based configuration. The proposed architecture also reduced simulated mean decision latency from approximately 5.18 seconds for static artificial intelligence to 2.05 seconds while selectively transferring uncertain cases to human review. Across individual scenarios, context-aware decision accuracy ranged from 75.0% to 82.0%, demonstrating greater resilience when resource conditions changed. The findings suggest that institutional artificial intelligence should not be treated merely as a predictive model but as an adaptive socio-technical decision infrastructure capable of recognizing the conditions under which a recommendation is generated. The proposed framework contributes a resource-sensitive, human-centered, and governance-aware model for institutions seeking responsible artificial intelligence adoption without depending on permanently high levels of digital infrastructure.
Keywords	context-aware artificial intelligence; adaptive decision support; resource-constrained institutions; human–AI collaboration; edge intelligence; institutional decision-making; resource optimization; explainable AI; responsible AI; adaptive computing
Field	Engineering
Published In	Volume 1, Issue 1, January-February 2020
Published On	2020-01-05

View / Download PDF File

About AJAMIR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+1-872-302-3851	editor@ajamir.com

American Journal of Advanced Multidisciplinary Innovation and Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Context-Aware Artificial Intelligence for Adaptive Decision Support in Resource-Constrained Institutions

Share this