Modelling

Graph learning is well suited to modeling relationships among communicating entities in network intrusion detection. However, the resulting models are frequently difficult to interpret, in contrast to many classical approaches that offer more transparent reasoning. This work integrates SHapley Additive exPlanations with temporal, edge-aware GNN based on GraphSAGE architecture to deliver an explainable, inductive intrusion detection model for NetFlow data named TE-G-SAGE. Using the NF-UNSW-NB15-v3 dataset, flow data are transformed into temporal communication graphs where flows are directed edges and endpoints are nodes. The model learns relational patterns across two-hop neighborhoods and achieves strong recall under chronological evaluation, outperforming a GCN baseline and recovering more attacks than a tuned XGBoost model. SHAP is adapted to graph inputs through a feature attribution on the two-hop computational subgraph, producing global and local explanations that align with analyst reasoning. The resulting attributions identify key discriminative features while revealing shared indicators that explain cross-class confusion. The research shows that temporal validation, inductive graph modeling, and Shapley-based attribution can be combined into a transparent, reproducible intrusion detection framework suited for operational use.

Eye tracking scanpaths encode the temporal sequence and spatial distribution of eye movements, offering insights into visual attention and aesthetic perception. However, analysing scanpaths still requires substantial manual effort and specialised expertise, which limits scalability and constrains objectivity of eye tracking methods. This paper examines whether and how multimodal large language models (MLLMs) can provide objective, expert-level scanpath interpretations. We used GPT-4o as a case study to develop eye tracking scanpath analysis (ETSA) approach which integrates (1) structural information extraction to parse scanpath events, (2) knowledge base of visual-behaviour expertise, and (3) least-to-most and few-shot chain-of-thought prompt engineering to guide reasoning. We conducted two studies to evaluate the reliability and effectiveness of the approach, as well as an ablation analysis to quantify the contribution of the knowledge base and a cross-model evaluation to assess generalisability across different MLLMs. The results of repeated-measures experiment show high semantic similarity of 0.884, moderate feature-level agreement with expert scanpath interpretations (F1 = 0.476) and no significant differences from expert annotations based on the exact McNemar test (p = 0.545). Together with the ablation and cross-model findings, this study contributes a generalisable and reliable pipeline for MLLM-based scanpath interpretation, supporting efficient analysis of complex eye tracking data.

Titanium alloys such as Ti-6Al-4V are widely used in aerospace and biomedical fields, but their poor wear resistance and high friction coefficient limit service performance. In this study, laser cladding with La₂O₃ addition was employed to enhance the surface properties of Ti-6Al-4V, and the underlying mechanisms were systematically investigated by combining experimental characterization with multiphysics simulations. XRD and SEM analyses revealed that La₂O₃ addition refined grains and promoted uniform phase distribution throughout the coating thickness, leading to good metallurgical bonding. The hardness was 2–3 times higher than that of the titanium alloy substrate when the content of 2–3 wt.% was of added La₂O₃, while the wear loss ratio was reduced to 0.021% and the average friction coefficient decreased to 0.421. These improvements were strongly supported by simulations: temperature field calculations demonstrated steep thermal gradients conducive to rapid solidification; velocity field analysis and recoil-pressure-driven flow revealed vigorous melt pool convection, which homogenized solute distribution and enhanced coating densification; phase evolution simulations confirmed the role of La₂O₃ in heterogeneous nucleation and dispersion strengthening. In summary, the combined results establish a mechanistic framework where thermal cycling, melt pool dynamics, and La₂O₃-induced nucleation act synergistically to optimize coating microstructure, hardness, and wear resistance. This integrated experimental–numerical approach provides not only quantitative improvements but also a generalizable strategy for tailoring surface performance in laser-based manufacturing.