Graph-based Retrieval-Augmented Generation (GraphRAG) is a prominent technique for mitigating hallucinations in Large Language Models (LLMs), yet it faces critical limitations in high-stakes anesthesiology question answering. At the retrieval stage, pervasive synonymy and knowledge fragmentation cause clinical queries to resolve to incorrect synonym clusters, while the highly specialized and domain-specific nature of clinical language widens the semantic gap, making an effective balance between recall and precision difficult to achieve. At the reasoning stage, the high structural heterogeneity of anesthesiology knowledge graphs, combined with the strong context-dependence of clinical semantics, renders existing multi-hop reasoning susceptible to clinical logic drift along weak associations, thereby introducing unreliable reasoning paths. Finally, at the fusion stage, conflicts between retrieved evidence and the model's parametric knowledge can easily lead to highly confident yet clinically unsafe hallucinations. To address these challenges, we propose the Description-augmented, Uncertainty-aware, and Adaptive Layered Knowledge Framework (DUAL-Know). For retrieval, query augmentation and description-augmented semantic recall bridge terminology gaps and comprehensively retrieve relevant knowledge. For reasoning, a Dynamically Gated Heterogeneous Multi-Head Attention (DGHMA) mechanism accommodates graph heterogeneity and dynamically injects query intent into each reasoning layer, followed by an uncertainty-aware path ranking module that filters noisy chains. For fusion, a multi-metric scoring strategy jointly evaluates model confidence, retrieval consistency, and semantic coherence to safely arbitrate knowledge conflicts. Experiments demonstrate that DUAL-Know consistently outperforms strong baselines, generating more accurate, reliable, and verifiable answers for complex clinical question-answering tasks.

Mirror segmentation is an emerging computer vision task that is extensively applied in various fields. However, it presents significant challenges to existing segmentation methods when irregular shapes are involved. Most methods are designed for deployment on heavy-duty host machines that demand substantial computational resources and storage capacity, which limits their feasibility for deployment on mobile devices, where efficient and resource-friendly solutions are required. Therefore, we propose a morphology-guided network (MGNet) with knowledge distillation, called MGNet-S*, to achieve the efficiency required for deployment in mobile devices. In this network, we introduce an erosion dilation fusion module that leverages morphological knowledge to extract texture details from intrinsic features. This module incorporates different optimization strategies for multimodal features. Furthermore, it provides a knowledge-distillation framework specifically tailored to the proposed MGNet-S*. The MGNet-S* includes three effective distillation modules: a semi-soft label, misaligned features, and adaptive aggregation types. These modules facilitate the efficient transfer of knowledge from the MGNet teacher to MGNet student, allowing the lightweight network, MGNet-S*, to achieve remarkable performance. Numerous experiments proved that our proposed MGNet-S* outperformed state-of-the-art methods, achieving an 88.6% reduction in parameter count and 82.5% reduction in floating-point operations compared to those of the MGNet teacher network.

Mirror segmentation, an emerging discipline in the field of computer vision, involves the identification and marking of mirrors in an image. Current mirror segmentation methods rely on fixed mirror elements as features for object segmentation. However, these methods do not account for the varied quality of feature images obtained under complex real-world conditions, leading to inaccurate segmentation results. To address these limitations, we propose a novel uncertainty-aware transformer localization network (UTLNet) for RGB-D mirror segmentation. Our approach draws inspiration from biomimicry, specifically the behavior pattern of human observation. We aim to explore features from different angles and focus on complex features that are challenging to determine during the coding stage. Additionally, we employ graph convolution to construct complementary dual-modal fusion features. Furthermore, we design a multiscale interaction transformer module using the shifted-window self-attention mechanism to acquire precise position information. In our experiments, the proposed UTLNet surpasses the current state-of-the-art mirror segmentation method as well as alternative task-specific methods. It achieves superior performance across various evaluation scenarios.

Considering the objective of production task accomplishment, the health state of manufacturing systems is contingent on three key operational factors: 1) task requirements, 2) equipment performance, and 3) product quality. Throughout the system lifecycle, these factors are subject to varying degrees of uncertainty resulting from the 5M1E (i.e., men, machine, material, method, measurement, and environment) fluctuations. Such operational uncertainties pose considerable challenges for decision-makers to obtain instructive results from conventional health prognosis methods. Consequently, based on a conceptual investigation of operational uncertainty and its implications on system health, this study proposes a novel health prognosis approach for multistate manufacturing systems from a mission reliability perspective. In this approach, the operational uncertainties are 1) categorized according to objective and subjective perspectives, 2) represented in fuzzy and probabilistic metrics, and subsequently 3) ensembled in a customized uncertain production risk process-based prognosis model for health prediction. To further eliminate the influence of subjective perturbations on the results, we adaptively assessed the boundaries of fuzzy parameters within this model by a deep reinforcement learning algorithm in lieu of expert elicitations. Finally, to validate the results, the proposed approach is applied to an industrial case study involving a ferrite phase shifter manufacturing system.