Artificial Intelligence XXXIX 42nd SGAI International Conference on Artificial Intelligence, AI 2022, Cambridge, UK, December 13–15, 2022, Proceedings

This book constitutes the proceedings of the 42nd SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, AI 2022, which was held in Cambridge, UK, in December 2022.

The 20 full papers and 11 short papers presented in this volume were carefully reviewed and selected from 40 submissions. The volume includes technical papers presenting new and innovative developments in the field as well as application papers presenting innovative applications of AI techniques in a number of subject domains.

The papers are organized in the following topical sections: best technical paper; best application paper; AI for health and medicine; AI for scientific discovery and decision making; AI for industrial applications; feasibility studies of applied AI; and short papers.

Best Technical Paper.- Practical Limits to Transfer Learning of Neural Network Controllers from Earth to Space Environments.- Best Application Paper.- Job Assignment Problem and Traveling Salesman Problem: A Linked Optimisation Problem.- AI for Health and Medicine.- Twitter Flu Trend: A Hybrid Deep Neural Network for Tweet Analysis.- Data Augmentation for Pathology Prioritisation: An Improved LSTM-Based Approach.- Scanned ECG Arrhythmia Classification Using a Pre-trained Convolutional Neural Network as a Feature Extractor.- AI for Scientific Discovery and Decision Making.- Bootstrapping Neural Electronics from Lunar Resources for In-Situ Artificial Intelligence Applications.- Query Resolution of Literature Knowledge Graphs using Hybrid Document Embeddings.- On an Artificial Neural Network Approach for Predicting Photosynthetically Active Radiation in the Water Column.- Morality, Machines and the Interpretation Problem: A Value-based, Wittgensteinian Approach to Building Moral Agents.- CRC: Consolidated Rules Construction for Expressive Ensemble Classification.- Competitive Learning with Spiking Nets and Spike Timing Dependent Plasticity.- An Evolutionary Game Theory Model of the Decision to Confront.- Hidden Markov Models for Surprising Pattern Detection in Discrete Symbol Sequence Data.- AI for Industrial Applications.- The ODeLIndA dataset for Field-of-View Obstruction Detection using Transfer Learning for Real-Time Industrial Applications.- Automated Quality Inspection of High Voltage Equipment Supported by Machine Learning and Computer Vision.- On Predicting the Work Load for Service Contractors.- OAK4XAI: Model towards Out-Of-Box EXplainable AI for Digital Agriculture.- Feasibility Studies of Applied AI.- Deep Learning for Detecting Tilt Angle And Orientation of Photovoltaic Panels on Satellite Imagery.- Recurrent Neural Networks for Music Genre Classification.- Explainable Boosting Machines for Network Intrusion Detection with Features Reduction.- Short Papers.- Accelerating Cyber-Breach Investigations through Novel use of Artificial Immune System Algorithms.- Comparing ML Models for Food Production Forecasting.- Comparing Peircean Algorithm with Various Bio-inspired Techniques for Multi-dimensional Function Optimization.- Medical Recommendation System Based on Daily Clinical Reports: A Proposed NLP Approach for Emergency Departments.- MentaLex: a Mental Processes Lexicon based on the Essay dataset.- Credit Card Fraud Using Adversarial Attacks.- Anomaly Detection and Root Cause Analysis on Log Data.- Developing Testing Frameworks for AI Cameras.- Time is Budget: A Heuristic for Reducing the Risk of Ruin in Multi-Armed Gambler Bandits.- Two Phase Open-Domain Question Answering System.- Have a Break from MakingDecisions, Have a MARS: The Multi-valued Action Reasoning System.