Applied Artificial Intelligence

Behavioural Modelling for Complex Systems: AI-Driven Evidence Generation from Heterogeneous Data

Artificial Intelligence (AI) is increasingly used to analyse behavioural phenomena across domains such as healthcare, sustainability, digital systems, smart environments, and societal decision making. However, many real-world behaviours and interactions cannot be adequately understood through isolated datasets or single data modalities. Behavioural modelling in complex systems often requires the integration of fragmented, indirect, partially observed, or heterogeneous data sources to generate meaningful evidence. This Article Collection focuses on emerging approaches to Behavioural Modelling for Complex Systems, with particular emphasis on AI-driven methods that transform heterogeneous data into decision-relevant behavioural evidence. This Article Collection considers behaviour broadly as interactions across humans, systems, environments, and hybrid socio-technical ecosystems. It seeks contributions that move beyond conventional predictive analytics toward approaches capable of uncovering patterns, relationships, and behavioural evidence that are difficult or impossible to capture from any single data source.

Behavioural Modelling for Complex Systems is important because many critical decisions in healthcare, sustainability, public policy, infrastructure, digital governance, and intelligent systems are increasingly made in environments characterised by incomplete, sparse, or indirectly observable data. Traditional AI approaches frequently rely on narrowly defined datasets that may fail to represent the complexity of real-world interactions and behaviours. Advances in multimodal AI, generative AI, large language models (LLMs), knowledge representation, and data integration now create opportunities to generate richer forms of behavioural evidence from existing and heterogeneous data sources. Such approaches have the potential to support more informed, adaptive, and context-aware decision making in complex systems. This Article Collection also reflects growing interest in AI systems that can bridge gaps between structured and unstructured data, support reasoning across modalities, and enable the innovative use of routinely collected or otherwise inaccessible data for real-world applications aligned with societal and sustainable development priorities.

This Article Collection welcomes original research articles, review papers, methodological studies, application-focused contributions, and interdisciplinary perspectives that fit the scope of Applied Artificial Intelligence. This Article Collection adopts a broad and interdisciplinary view of behavioural modelling and encourages submissions from computing and AI as well as disciplines such as psychology, behavioural science, sociology, health sciences, public policy, sustainability, environmental studies, digital humanities, and human-computer interaction.

Topics of interest include, but are not limited to:

• Behavioural Modelling using heterogeneous and multimodal data
• AI-driven Evidence Generation
• Multimodal Reasoning and Rrepresentation Learning
• Generative AI and Large Language Models (LLMs) for Behavioural Analysis
• Graph-based and Relational AI
• Behavioural Modelling in socio-technical and cyber-physical systems
• Hybrid Human-System Interactions
• Explainable and Trustworthy AI
• Knowledge Graphs and Retrieval-Augmented Systems
• Synthetic and Inferred Behavioural Evidence Generation
• AI-Enabled decision-support systems operating in Data-Incomplete environments.

Contributions exploring theoretical advances, interdisciplinary applications, and real-world deployments are particularly encouraged.

Keywords: Behaviour Modelling, Complex Systems and Decision Support, Heterogeneous and Multimodal Data, Generative AI and LLM, AI-Driven Evidence Generation

Manuscript Submissions:

Manuscript submission is open until 31st March 2027.

All manuscripts submitted to this Article Collection will undergo desk assessment and peer-review as part of our standard editorial process. Manuscripts which do not fall within the scope of the journal will be rejected.

This journal applies the Taylor & Francis' Open Data Sharing Policy. All authors will be required to make their data and materials supporting their results or analyses presented in their paper freely available.

To submit your papers to this Article Collection, please:

1. Check "Yes" for the question, "Are you submitting your paper for a specific special issue or article collection?"
2. Select the relevant Article Collection from the drop-down menu under the question, "Behavioural Modelling for Complex Systems: AI-Driven Evidence Generation from Heterogeneous Data"
3. Enter your Discount Code on the Final Page (Services) in the “Apply Discount Code” box on the right-hand side of the screen, otherwise this will not be applied for their submission, and you would be subject to the journal’s Full APC Fee

We are able to offer a 10% Discount to all authors, and have a limited number of 20% Discount codes only available for early submissions. It should be noted that discount codes must be entered in at the point of submission as they cannot be applied retroactively, nor can these be combined as only the higher valued discount would be applicable.

Please contact Christopher Montgomery, Commissioning Editor regarding details on obtaining your discount codes, and with any other queries for this Article Collection.

Article Collection Guest Advisors

Dr. Nonso Nnamoko is a Senior Lecturer in Computer Science in Department of Computer Science at Edge Hill University, UK. His research focuses on multi-modal artificial intelligence, particularly the innovative use of heterogeneous and multimodal data to generate decision-relevant evidence for complex systems. His work spans machine learning, natural language and image processing, generative AI, knowledge representation, and behavioural inference across domains including healthcare, sustainability, digital systems, and public policy. He has led and contributed to interdisciplinary research projects involving AI-driven behavioural analysis, ethical AI, and data-informed decision support. He is particularly interested in approaches that combine AI with behavioural and societal perspectives to address real-world challenges.

Yannis Korkontzelos is a Professor in Computer Science, with a research focus on a variety of subfields of Natural Language Processing and Text Mining, such as compositional semantics, multiword expression and term extraction, document classification and sentiment analysis, applied to a number of domains, such as biomedicine, social sciences, social media, open source software and scientific publications.

Dr. Asfak Ali is a researcher specializing in computer vision, deep learning, and intelligent embedded systems, with a focus on real-time perception under adverse environmental conditions, Medical Imaging and Biomedical Signal Processing. He was associated with Jadavpur University as a Guest Faculty in the Department of Electronics and Telecommunication Engineering. He currently serves as the Director of Deep Duo Foundation. His research interests include object tracking, image restoration, medical image analysis, video analytics, edge AI, and IoT-enabled intelligent systems, with publications in reputed IEEE, Elsevier, Springer, ACM, and other international venues. Dr. Ali has also actively contributed to the research community as an organizer and reviewer for international events and challenges, including ICPR 2024, ICPR 2026 and ICME ECHO 2026. His current work focuses on developing practical and socially impactful AI-driven technologies for real-world applications.