In many real-world applications involving static environments, the spatial layout of objects remains consistent across instances. However, state-of-the-art object detection models often fail to leverage this spatial prior, resulting in inconsistent predictions, missed detections, or misclassifications, particularly in cluttered or occluded scenes. In this work, we propose a graph-based post-processing pipeline that explicitly models the spatial relationships between objects to correct detection anomalies in egocentric frames. Using a graph neural network (GNN) trained on manually annotated data, our model identifies invalid object class labels and predicts corrected class labels based on their neighbourhood context. We evaluate our approach both as a standalone anomaly detection and correction framework and as a post-processing module for standard object detectors such as YOLOv7 and RT-DETR. Experiments demonstrate that incorporating this spatial reasoning significantly improves detection performance, with$\text{mAP} {@} 50$gains of up to 4 %. This method highlights the potential of leveraging the environment's spatial structure to improve reliability in object detection systems.

Accurate evaluation of procedural communication compliance is essential in simulation-based training, particularly in safety-critical domains where adherence to compliance checklists reflects operational competence. This paper explores a lightweight, deployable approach using prompt-based inference with open-source large language models (LLMs) that can run efficiently on consumer-grade GPUs. We present Prompt-and-Check, a method that uses context-rich prompts to evaluate whether each checklist item in a protocol has been fulfilled, solely based on transcribed verbal exchanges. We perform a case study in the maritime domain with participants performing an identical simulation task, and experiment with models such as LLama 2 7B, LLaMA 3 8B and Mistral 7B, running locally on an RTX 4070 GPU. For each checklist item, a prompt incorporating relevant transcript excerpts is fed into the model, which outputs a compliance judgment. We assess model outputs against expert-annotated ground truth using classification accuracy and agreement scores. Our findings demonstrate that prompting enables effective context-aware reasoning without task-specific training. This study highlights the practical utility of LLMs in augmenting debriefing, performance feedback, and automated assessment in training environments.

Seafarer competence in visual attention, communication, and stress management is critical to maritime safety. While assessment methods for these individual areas have evolved with simulators, sensor data, and artificial intelligence, there remains no established approach to systematically integrate these outputs into a practical competence measure to support more efficient and standardised debriefing and to enable reliable comparison between trainees. In this paper, we present a multimodal assessment report that fuses analysed results from eyetracking, audio recordings, and Electroencephalogram (EEG) signals collected during full-mission bridge simulator exercises. The report provides an integrated, instructor-friendly summary of each trainee's performance across key competence pillars, along with an executive summary. This approach offers maritime instructors a more comprehensive and objective tool to identify individual strengths, weaknesses, and development needs.