Traumatic peripheral nerve injuries (PNIs) are high-stakes presentations in the emergency department (ED). Missed deficits and delayed referral can lead to functional loss and chronic neuropathic pain. This review summarizes an ED-centered approach to evaluation, early risk stratification, and management pathways. Contemporary epidemiology suggests PNIs after extremity trauma occur at clinically meaningful rates. High-resolution ultrasound and neuromuscular ultrasound can visualize nerve continuity, focal enlargement, traumatic neuroma, and entrapment, though performance depends on operator skill and nerve depth. Magnetic resonance neurography complements ultrasound for deeper nerves, plexus-level injury, and muscle denervation patterns. Electrodiagnostic testing remains central for localization and prognosis but is usually most informative in the subacute period. ED care should integrate mechanism-based suspicion, nerve-specific examination with repeat post-reduction reassessment, selective imaging when it changes decisions, timely surgical consultation for suspected transection/entrapment/progression, and clear documentation with structured follow-up. We recommend an emergency department approach to traumatic peripheral nerve injury that prioritizes early recognition, identification of time-sensitive lesions, and a closed-loop follow-up plan when observation is appropriate. Every at-risk extremity trauma should receive a nerve-specific motor and sensory exam documented before and after reduction, splinting, or casting, because evolving deficits can reflect entrapment, hematoma expansion, ischemia, or compartment syndrome. When mechanism and exam raise concern for high-grade injury, particularly sharp lacerations with motor loss, open fractures with neurologic deficit, progressive weakness after immobilization, or deficits out of proportion to pain, urgent surgical consultation is warranted. High-resolution ultrasound adds the most value when it answers a focused question that changes acute decisions, specifically whether the nerve is in continuity, whether there is focal compression by hematoma or displaced fragments, and whether post-reduction positioning is producing dynamic impingement. In stable closed injuries with preserved continuity and no red flags, we favor functional splinting, multimodal analgesia, and early specialty follow-up with a planned timeline for electrodiagnostic testing in the subacute period to localize injury and guide prognosis. For suspected deep nerve or plexus involvement, equivocal ultrasound, or complex regional injury patterns, magnetic resonance neurography can complement ultrasound by defining lesion extent and demonstrating denervation patterns that influence urgency. Overall, ED success depends less on assigning a perfect injury grade at presentation and more on reliably detecting injuries unlikely to recover spontaneously, reassessing after interventions, and ensuring timely definitive nerve evaluation.
Developing a qualified eco-driving strategy for plug-in hybrid electric vehicles (PHEVs) remains challenging in urban traffic scenarios, due to the comprehensive influence of random traffic flow and signal lights. To solve it, this study develops a hierarchical eco-driving framework integrating lane-changing decisions through a virtual force-based trigger mechanism and an adaptive energy management strategy that dynamically adjusts the equivalence factor. Firstly, considering the interference of neighbor vehicles, the velocity planning layer generates the economic velocity trajectories using dynamic programming in short discrete intervals, enabling the ego-vehicle to navigate through signal intersections smoothly. In addition, the lane changing is properly conducted according to the state of the ego-vehicle, traffic flow, and signal light. In the energy management layer, an adaptive equivalent fuel consumption minimization strategy accounting for trip distance, initial state of charge, and remaining electric mileage is developed to ensure a reasonable power split based on the reference velocity. Simulation and hardware-in-the-loop experimental results indicate that the developed strategy improves the traffic efficiency by 1.68%, while reducing energy consumption by 9.81% and 31.71%, compared with Pontryagin's minimum principle and nonlinear model predictive control based methods.
Safety specifications in cyber-physical systems (CPS) capture the operational conditions the system must satisfy to operate safely within its intended environment. As operating environments evolve, operational rules must be continuously refined to preserve consistency with observed system behavior during simulation-based verification and validation. Revising inconsistent rules is challenging because the changes must remain syntactically correct under a domain-specific grammar. Language-in-the-loop refinement further raises safety concerns beyond syntactic violations, as it can produce semantically unjustified refinements that overfit to the observed outcomes. We introduce a framework that combines counterfactual reasoning with a grammar-constrained refinement loop to refine operational rules, aligning them with the observed system behavior. Applied to an autonomous driving control system, our approach successfully resolved the inconsistencies in an operational rule inferred by a conventional baseline while remaining grammar compliant. An empirical large language model (LLM) study further revealed model-dependent refinement quality and safety lessons, which motivate rigorous grammar enforcement, stronger semantic validation, and broader evaluation in future work.
Current quantum neural networks suffer from extreme sensitivity to both adversarial perturbations and hardware noise, creating a significant barrier to real-world deployment. Existing robustness techniques typically sacrifice clean accuracy or require prohibitive computational resources. We propose a hybrid quantum-classical Differentiable Quantum Architecture Search (DQAS) framework that addresses these limitations by jointly optimizing circuit structure and robustness through gradient-based methods. Our approach enhances traditional DQAS with a lightweight Classical Noise Layer applied before quantum processing, enabling simultaneous optimization of gate selection and noise parameters. This design preserves the quantum circuit’s integrity while introducing trainable perturbations that enhance robustness without compromising standard performance. Experimental validation on MNIST, FashionMNIST, and CIFAR datasets shows consistent improvements in both clean and adversarial accuracy compared to existing quantum architecture search methods. Under various attack scenarios, including Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Basic Iterative Method (BIM), and Momentum Iterative Method (MIM), and under realistic quantum noise conditions, our hybrid framework maintains superior performance. Testing on actual quantum hardware confirms the practical viability of discovered architectures. These results demonstrate that strategic classical preprocessing combined with differentiable quantum architecture optimization can significantly enhance quantum neural network robustness while maintaining computational efficiency.
The vector database stores data as high-dimensional feature vectors. Some recently proposed attack techniques enable an adversary to launch feature vector inversion (FVI) attacks against vector databases. In FVI attacks, an adversary trains an FVI attack network to reconstruct the original private data from their feature vectors based on the assumption that an auxiliary dataset is available to the adversary. However, such a data-available assumption is too strong, making such FVI attacks unrealistic in many real-world scenarios. In this paper, we make the first systematic study on FVI attacks against vector databases in the data-free setting. To tackle the issue of no training data, we develop an output-to-input data generation technique that helps to generate synthetic fake samples for the FVI attack network training. In addition, to ensure the high quality of generated fake samples, we develop the accelerable complete bipartite graph (CBG) search strategy and the downstream-classifier-aided generator training strategy. Furthermore, we empirically identify multiple factors that influence the attack performance. Intriguingly, as the key insight of this work, we find that the proposed FVI attack technique in the data-free setting can be directly employed to boost the attack performance of FVI attacks in the auxiliary-dataset-available setting. Finally, we propose and study defenses against the proposed attacks.
