Safety and security are key considerations in the design of critical systems. Requirements analysis methods rely on the expertise and experience of human intervention to make critical judgements. While human judgement is essential to an analysis method, it is also important to ensure a degree of formality so that we reason about safety and security at early stages of analysis and design, rather than detect problems later. In this paper, we present a hierarchical and incremental analysis process that aims to justify the design and flow-down of derived critical requirements arising from safety hazards and security vulnerabilities identified at the system level. The safety and security analysis at each level uses STPA-style action analysis to identify hazards and vulnerabilities. At each level, we verify that the design achieves the safety or security requirements by backing the analysis with formal modelling and proof using Event-B refinement. The formal model helps to identify hazards/vulnerabilities arising from the design and how they relate to the safety accidents/security losses being considered at this level. We then re-apply the same process to each component of the design in a hierarchical manner. Thus, we use hazard and vulnerability analysis, together with refinement-based formal modelling and verification, to drive the design, replacing the system level requirements with component requirements. In doing so, we decompose critical system-level requirements down to component-level requirements, transforming them from abstract system level requirements, towards concrete solutions that we can implement correctly so that the hazards/vulnerabilities are mitigated.

Background/Objectives: In the field of computer vision, prominent solutions often rely on transformers and convolutional neural networks (CNNs). Researchers frequently incorporate CNNs and transformers in developing image classification models. This study aims to introduce an innovative CNN model inspired by the Generative Pretrained Transformer (GPT) architecture and assess its image classification capabilities. Methods: This study utilized three distinct biomedical image datasets to evaluate the efficacy of the proposed GPTNeXt model. The datasets encompassed (i) Alzheimer’s disease (AD) magnetic resonance (MR) images, (ii) blood images, and (iii) lung cancer images. The choice of these datasets aimed to showcase the GPTNeXt model’s versatile classification performance. The GPTNeXt model and a deep feature engineering approach based on it were developed. In this deep feature engineering model, features were extracted from the global average pooling layer of GPTNeXt, and a novel deep feature extraction method was employed. This method extracted features from the entire image and generated nine fixed-size patches. To identify the most informative features, iterative neighborhood component analysis (INCA) was applied. The classification phase involved three shallow classifiers to produce classification results. Results: The GPTNeXt-based feature engineering model was applied to the three aforementioned biomedical image datasets, achieving classification accuracies exceeding 98% for all of them. Conclusions: This study demonstrates the high effectiveness of the proposed approach, as evidenced by the exceptional classification performance on the selected biomedical image datasets. Additionally, a lightweight CNN was introduced, showcasing outstanding classification performance.

Intelligent autonomous driving systems must not only predict the appropriate driving manoeuvre but also provide human-interpretable evidence that justifies the decision. However, existing methods typically address these objectives separately, leading to three practical limitations: multi-stage perception-to-language pipelines can propagate upstream perception errors into downstream explanations; post hoc saliency methods often produce pixel-level highlights that are difficult to interpret semantically; and decoupled decision and explanation modules cannot guarantee that the explanation reflects the same scene evidence used for behaviour prediction. In this paper, we propose a unified framework that jointly performs vehicle behaviour prediction and human-centric interpretation from a shared visual backbone. Specifically, a hierarchical Swin Transformer encodes the driving scene into a sequence of spatial tokens, which are processed by two complementary branches. The first branch, termed the Object Selection Module (OSM), learns a compact scene-level semantic representation through query-guided cross-attention, while the second branch extracts a small set of class-agnostic object-centric tokens without requiring bounding-box or segmentation supervision. These two representations are subsequently integrated by a Semantic–Object Fusion (SOF) module based on scaled dot-product attention, residual connections, and a feed-forward network. The behaviour prediction head operates on the fused representation, whereas the interpretation head leverages the semantic representation through a skip connection to preserve decision-relevant context. For surround-view perception, learnable per-camera embeddings are introduced to maintain viewpoint identity with negligible additional parameter cost. Furthermore, a compact language model fine-tuned via Low-Rank Adaptation (LoRA) generates fluent, label-conditioned natural-language justifications. Extensive experiments on two public benchmarks, BDD-OIA and nu-AD, demonstrate that the proposed framework consistently delivers superior performance and provides effective, human-readable interpretations of driving decisions.

Background/Objective: Autonomous vehicles (AVs) require control algorithms capable of handling complex and dynamic environments while satisfying multiple conflicting objectives such as safety, comfort, energy efficiency, and trajectory accuracy. Model predictive control (MPC) offers a principled framework for multi-constraint optimization, yet its real-time feasibility remains challenging for nonlinear vehicle dynamics. Methods: This paper presents a feedforward neural network (FNN)-based MPC framework for autonomous vehicle trajectory tracking. The FNN approximates the coupled vehicle dynamics and visual preview error model using an algebraic sum of log-sigmoid functions. Three adaptive FNN parameter sets, namely, the scaling factor, convergence parameter, and time-shifting parameter, are jointly optimized using a hybrid algorithm that combines the global search capability of fractional particle swarm optimization (FPSO) with the local refinement of sequential quadratic programming (SQP). Results: Comprehensive scenario-based simulations are performed to evaluate trajectory tracking dynamics under dry conditions with an adhesion coefficient of 0.8 and a vehicle mass of 1723 kg moving at a speed of 80 km/h. The results are quantitatively compared with a traditional PID controller and a structurally comparable MPC framework from the literature under identical simulation conditions; related DRL- and RL-based methods are discussed qualitatively for contextual orientation only. The stability, reliability, and computational complexity of the proposed framework are examined based on the mean square error, fitness value, and computational budget in GFLOPs for 100 independent runs. Conclusions: The proposed FNN-based MPC framework demonstrates improved tracking accuracy and optimizer reliability in simulation. While the present results indicate promising computational behavior, real-time deployment will require further validation on embedded automotive hardware and under closed-loop real-time constraints.