BCS SGAI
The Specialist Group on Artificial Intelligence
AI-2025: The Forty-fifth SGAI International Conference
16th-18th December 2025

Order of Refereed Paper Sessions

Session 1: Peterhouse Lecture Theatre (2 papers)

Deep Learning

A Hybrid Reasoning System for Visual Arithmetic Learning
Wenbo Zhang, Colin G. Johnson and Ender Özcan (University of Nottingham)

This Looks Like That and That and That: Multi-objective Optimization for Diverse Prototype Learning
A.Parise and B.Mac Namee (University College Dublin)

Session 1: Upper Hall (2 papers)

Evolutionary Algorithms

Evolutionary Optimization of Autonomous Agents for Decreasing Resource Intensity on Geographically Located Interdependent Task Sets
M.Fyvie and A.-C. Zavoianu (Robert Gordon University, UK), J.A.W.McCall (Robert Gordon University, UK and PlanSea Solutions, UK)

Explaining Recommender Systems’ Performance via User Behaviour Patterns
GianCarlo A.P.I. Catalano (University of Stirling), Klaudia Dynak (University of Wrocław), Alexander E.I. Brownlee (University of Stirling) and Piotr Lipinski (University of Wrocław)

Session 1: Davidson Room (2 papers)

Medical Computing and Health Informatics

Generation, Use and Effects of Synthetic Data to Train Medical AI`s: Examined Using the Example of Knee Arthroplasty
T. Neiss-Theuerkauff, A. Schierbaum, Y. Korte-Wagner, T. Luhmann, T. Sieberth and Frank Wallhoff (Jade University, Oldenburg, Germany)

Synthetic Patient Simulation and Model Stacking for Early Disease Detection: An EHR-focused AI Framework for Diagnostic Accuracy and Generalization
Sathish Kumar Natarajan (Prabhu International Research Institute, Yamanashi, Japan), Azween Abdullah (HELP University, Kuala Lumpur, Malaysia), Prabhu Natarajan (Prabhu International Research Institute, Yamanashi, Japan)

Session 2: Peterhouse Lecture Theatre (5 papers)

Machine Learning

Multi-Agent Reinforcement Learning Framework for Modeling Astrocyte-Neuron Interactions in Neural Microenvironments
Zhen Chen (University of Science and Technology of China), Shufan Yang (University of Leeds, UK)

A New Longitudinal Classification Method Based on Stacking Predictions for Separate Time Points
S Provost and AA Freitas (University of Kent, UK)

Measuring and Comparison of the Energy Consumption of different Machine Learning Methods
Christoph Tholen (German Research Center for Artificial Intelligence and Saarland University of Applied Sciences), Carolin Leluschko (German Research Center for Artificial Intelligence), Lars Nolle (German Research Center for Artificial Intelligence and Jade University of Applied Sciences), Frederic Stahl (German Research Center for Artificial Intelligence)

Machine Learning-Enhanced Production Frontier Estimation: An EATBoosting Variant
Juan Aparicio (Miguel Hernandez University, Spain and Valencian Graduate School and Research Network of Artificial Intelligence, Spain), Vincent Charles (Queen’s University Belfast, UK), Maria D. Guillen (Miguel Hernandez University, Spain)

A Comparative Study of Feature Selection in Tsetlin Machines
V.Halenka, OC.Granmo, L.Jiao, PA. Anderson (University of Agder, Norway)

Session 2: Upper Hall (5 papers)

Large Language Models

Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking
Aldan Creo (Universitat Politècnica de València, Spain), Raul Castro Fernandez (University of Chicago, USA) and Manuel Cebrian (Spanish National Research Council)

Data and Knowledge-Driven Approach for Energy Profiling in Smart Context-Aware Buildings
Mona Farrag, Gerald Feldman, Haitham Mahmoud, Nouh Elmitwally (Birmingham City University, UK) and, Mohamed M. Gaber(Queensland University of Technology, Brisbane, Australia)

Retry and Refine: A Multi-Agent Framework for LLM Based Reliable Unit Test Generation
Tanmay Ghosh and Noorhan Abbas (University of Leeds, UK)

Enhancing Voice-Controlled Drone Navigation: A Hybrid Approach Using ASR and NLP for UAV Command Interpretation
Yassir Alkasim and Abdulrahman Altahhan (University of Leeds, UK)

TravQuery: A Customer Support Chatbot based on Retrieval Augmented Generation (RAG)
Aneela Farnaz and Chris Huyck (Middlesex University, London, UK)

Session 2: Davidson Room (5 papers)

Applications of Artificial Intelligence

A Fuzzy-logic Based Cognitive Walkthrough to Assess the Degrees of Soft Skills Targeted in an Intelligent Educational Adventure Game
K.Chrysafiadi, S.Papadimitriou and M.Virvou (University of Piraeus, Greece)

Streamlining Municipal Governance: Detecting Redundancy in Regulation Plans using Text Embeddings in Local Government
K. A. Borgersen and M. Goodwin (University of Agder, Norway), A. S. Nossum (Norkart, Norway)

Exam Timetabling Problem Using Cooperative Hyper-heuristics: A Case Study of the ITC2007 Dataset
Kate Han and Evelyn Oginni (University of Salford, Manchester, UK), John A. W. McCall (Robert Gordon University, UK), Paul McMullan (Queen’s University Belfast, UK), Yun Chen ( University of Salford, Manchester, UK)xxxxx

Carbon Crest: A Personal Carbon Credit Model for Sustainable Transport Behaviour in Greater Manchester
Kate Han (University of Salford, Manchester, UK), Meropi Tzanetakis (Vienna University of Economics and Business, Vienna, Austria), Evelyn Oginni (University of Salford, Greater Manchester, UK), Arun Matthew and Bobin Joseph (The Carboncrest Network Ltd., Manchester, UK)

How AI is Changing Medicine: a Simple Matter of Time?
Mercedes Arguello Casteleiro (University of Manchester, UK), Chloe Henson (Gold Coast University Hospital, Australia), Manoj Kulshrestha (Midcheshire Hospital Foundation Trust, UK), Muhammad Waleed Iqbal (University of Buckingham, UK), Nava Maroto (Universidad Politécnica de Madrid, Spain), Maria Jesus Fernandez Prieto (University of Salford, UK), Julio Des Diz (Hospital do Salnés, Spain), Tim Furmston, John Keane and Robert Stevens (University of Manchester, UK) and Chris Wroe (BMJ, UK)

Session 3: Peterhouse Lecture Theatre (4 papers)

Neural Networks

Two-Stage Graph Convolutional Framework for Pipeline Leak Detection and Size Identification
F. Saleem and J.-M. Kim (University of Ulsan, South Korea)

TamilSandhi: A Neuro-Symbolic AI toolkit for correcting Sandhi errors in Tamil
Yazhmozhi V M, Annalu Waller and Jacky Visser (University of Dundee, UK)

Evaluation of Explanations for Object Detection using Transformers with Sonar Data
Christoph Manss and Tarek A. El-Mihoub (German Research Centre for Artificial Intelligence)

Predicting London`s Precipitation: A Spatio-Temporal Neural Network Approach
Huma Zafar and Stelios Kapetanakis (Distributed Analytics Solutions, USA), , Giacomo Nalli (Middlesex University, UK) and , Khuong Nguyen (Royal Holloway University, UK)

Session 3: Upper Hall (4 papers)

Large Language Models

Multimodal Sarcasm Dataset Generation for a Low-Resource Language: Swahili
Eugene Kariba and Noorhan Abbas (University of Leeds, UK)

English K_Quantization of LLMs Does Not Disproportionately Diminish Multilingual Performance
K. A. Borgersen and Morten Goodwin (University of Agder, Norway)

Neuro-Symbolic AI: Combining Neural and Symbolic AI for UK Syndromic Surveillance
Mercedes Arguello Casteleiro (University of Manchester, UK), Nava Maroto (Universidad Politécnica de Madrid, Spain), Maria Jesus Fernandez Prieto (University of Salford, UK), Yuan Wei (Civil Aviation Flight University of China, China), Peter John Noble and Alan David Radford (University of Liverpool, UK) and Goran Nenadic (University of Manchester, UK)

Bi-Resolution: A Logic Reasoning Enhancement Method for Large Language Models Based on Resolution and Bidirectional Reasoning Fusion
Yifei Wang (East China Normal University, China), and Yixiang Chen (East China Normal University and Shanghai Normal University, China)

Session 3: Davidson Room (4 papers)

Machine Learning

MTL-LungNet: A Unified Model for Nodule Segmentation and Malignancy Classification
Mihai Nan, Cătălin-Mihail Chiru and Adina-Magda Florea (National University of Science and Technology , Politehnica, Bucharest)

Soft Actor-Critic Reinforcement Learning for Reactive Current Injection Protocols
M.Fathollahi, A.Camacho and C.Angulo (Universitat Politecnica de Catalunya, Spain) and J.Hampton (Siemens Energy AG)

A Reinforcement Learning Environment for Job Shop Scheduling with Tool Management
R. Maharjan, P.-A. Andersen and L.Jiao (University of Agder, Norway)

HAD-QC: A Hybrid AI Approach for Automated Quality Control of Argo Float Data
S.Aiwale and L.Sun (University of Reading, UK), F.Stahl (German Research Center for Artificial Intelligence,Germany)

Session 4: Peterhouse Lecture Theatre (4 papers)

Machine Learning

6D Grasp Pose Estimation using Machine Learning with Synthetic Data: Explainable Grasping with Point Cloud Networks
Augustinas Steikunas and Giovanna Martínez-Arellano (University of Nottingham, UK)

Transformer-Based and Generative Classifiers for Mining Imbalanced Datasets
Piotr Jedrzejowicz and Iza Wierzbowska (Gdynia Maritime University, Gdynia, Poland)

DeLSTM-AE: A Decomposition-Driven Framework for Univariate Time Series Anomaly Detection
M. Albalushi and S. Alzubi (University of Exeter, UK)

Forecasting Uranium Prices Using LSTM and VMD-Based Ensemble Models
S.Gopalakrishnakone (University of London, UK)

Session 4: Upper Hall (3 papers)

Techniques of AI

Navigating the N-Person Prisoners` Dilemma: From the Tragic Valley to the Collaborative Hill
C. Tcaci and C. Huyck (Middlesex University, UK)

Evolutionary Harnessing of Sneak Currents of 1R Memristive Crossbar
Xinming Shi (Queen’s University Belfast, UK), Xin Yao (Lingnan University, Hong Kong SAR)

Rethinking the Illusion of Thinking
I.Dellibarda, P.Romero-Sorozabal, E.Rocon and M.Cebrian (Center for Automation and Robotics, Spanish National Research Council)

Session 4: Davidson Room (3 papers)

Natural Language Processing and Machine Vision

Data Science Approaches to Evaluating Honours Candidates
F. von Braun-Bates (Ministry of Justice, UK), S. Sen (Arndit Ltd., Cambridge, UK), I. Talukdar (Indian Institute of Technology Delhi, India) and A. Lahiri (Kainos, London, UK)

From the Laboratory to Real-World Application: Evaluating Zero-Shot Scene Interpretation on Edge Devices for Mobile Robotics
Nicolas Schuler (Trier University of Applied Sciences, Germany and University of Luxembourg, Luxembourg), Lea Dewald (Trier University of Applied Sciences, Germany), Nick Baldig (Trier University of Applied Sciences, Germany and University of Luxembourg, Luxembourg) and Jürgen Graf (Trier University of Applied Sciences, Germany)

Unsupervised Learning for Industrial Defect Detection: A Case Study on Shearographic Data
J. Plassmann (Trier University of Applied Science, Germany and RPTU University Kaiserslautern-Landau, Germany) and N. Schuler (Trier University of Applied Science, Germany and University of Luxembourg, Luxembourg), Georg von Freymann (RPTU University Kaiserslautern-Landau, Germany and Fraunhofer Institute for Industrial Mathematics, Germany) and Michael Schuth (Trier University of Applied Science, Germany)


BCS SGAI
The Specialist Group on Artificial Intelligence
AI-2025: The Forty-fifth SGAI International Conference
16th-18th December 2025