From Data to Action: A Unified Multi-Layer Cognitive Architecture for Intelligent Decision Systems

Jouma Ali Al-Mohamad, Ghefar Alaa Aldeen Alrefai, Suvan Mathew Churchill, Dheeraj Sajeev Kumar, Abdalla Hamid Morsi, Ahmed Saleh Department of Computer and Mobile Communication Engineering, Faculty of Information Engineering, Al-Shahbaa Private University, Aleppo, Aleppo Governorate, Syria. Department of Informatics and Communications Engineering, Faculty of Engineering, EBLA Private University, Saraqeb, Idlib Governorate, Syria. Department of Business Analytics, University of Galway, Galway, Ireland. Department of Computer Science, Zewail City of Science and Technology, October Gardens, Giza Governorate, Egypt.

Abstract: The volume and variety of data from streams of sensor data to the unstructured text contained in emails have created a disjunction between when data is available and when it is utilized in timely and trustworthy ways. Knowledge that is not used is inert. This paper provides a closed-loop cognitive architecture for changing data into information, information into knowledge, knowledge into action, and action outcomes into better future knowledge and decision-making. It uses ontologies, knowledge graphs, temporal logic, probabilistic models, deep learning, anticipated utility, robust optimization, and reinforcement learning. L1 acquires multi-source data and harmonizes semantics; L2 extracts patterns and probabilistic information; L3 builds a knowledge graph with causal and temporal relations; L4 generates decisions based on rule-based and learned policies; and L5 refines and adapts knowledge. At each layer, mathematical models, computational choices, and design compromises are discussed. One case study on critical care unit sepsis care and another on supply chain risk mitigation demonstrate success. The evaluation includes knowledge precision, recall, action regret, and update efficiency. This paper discusses uncertainty, idea drift, explainability, and future research on the knowledge-action gap in intelligent systems. 

---

Keywords: Knowledge Graphs; Reinforcement Learning; Decision Support Systems; Causal Inference; Idea Drift; Explainable AI; Closed-Loop Learning; Harmonized Semantics.

---

Received on: 19/08/2025Revised on: 06/11/2025Accepted on: 03/12/2025Published on: 03/03/2026

---

---