About the Journal
About EIIS
Engineering Informatics and Intelligent Systems (EIIS) is an international peer-reviewed journal devoted to intelligent methods, computational frameworks, and engineering information systems that support real engineering work. The journal welcomes research spanning design, analysis, manufacturing, construction, operation, maintenance, inspection, resilience, risk management, and lifecycle decision support.
EIIS is founded on a simple principle: in engineering, intelligence is only valuable when it is accountable to reality. For this reason, the journal particularly values research that combines learning with structure, such as expert knowledge, physics, logic, standards, constraints, simulation, semantics, or formal models.
EIIS is not merely interested in whether an AI system performs well on a benchmark. It is interested in whether a method can support engineering judgment in a way that is transparent, robust, grounded, and useful under real constraints.
The journal serves researchers, practitioners, and interdisciplinary teams working across civil, mechanical, electrical, manufacturing, aerospace, chemical, energy, environmental, transportation, industrial, and systems engineering.
Aims & Scope
Engineering Informatics and Intelligent Systems (EIIS) publishes original research, reviews, benchmark papers, datasets, methods papers, and industrial case studies at the intersection of engineering informatics, artificial intelligence, and intelligent systems.
The journal focuses on computational methods and information-centric systems that support knowledge-intensive engineering tasks throughout the lifecycle of engineered assets and infrastructures. Areas of interest include, but are not limited to, design support, analysis, modeling, simulation, optimization, planning, compliance checking, diagnosis, inspection, monitoring, maintenance, resilience, safety, and risk-informed decision-making.
EIIS particularly welcomes contributions that move beyond unconstrained black-box prediction toward knowledge-embedded and trustworthy AI. This includes approaches that integrate data-driven intelligence with one or more of the following:
- engineering principles and domain theory
- physical laws and mechanistic understanding
- expert rules and structured decision logic
- ontologies, semantics, and knowledge graphs
- standards, codes, and formal constraints
- simulation, optimization, and digital-twin models
- human oversight, traceability, and verification mechanisms
The journal is also interested in the next generation of engineering intelligence systems, including multimodal foundation models, LLM-enabled engineering assistants, agentic workflows, and human-AI collaborative systems, especially when these are grounded through retrieval, tools, formal knowledge, domain constraints, or validation layers.
EIIS values not only novelty, but also clarity of assumptions, operational realism, reproducibility, interpretability, uncertainty awareness, and evidence of engineering usefulness.
