With the proliferation of interconnection networks in mission-critical systems ranging from cloud computing infrastructures to large-scale data centers, the escalating structural complexity has intensified network vulnerability to malicious attacks and cyber warfare incidents. This article establishes a theoretical framework for evaluating network self-diagnostic capability through a novelh-extrar-component diagnosability metric, denoted as$\widehat{ec}_{r}^{h}(G)$, which quantifies a network’s resilience under compound fault patterns. The proposed metric requires that after removing specific nodes, the remaining subgraph is required to preserve at leastrconnected components where every component maintains a node count exceedingh. Through rigorous combinatorial analysis, we derive closed-form expressions for star networks$S_{n}$,$\widehat{ec}_{2}^{1}(S_{n}) = 4n - 9$and$\widehat{ec}_{3}^{1}(S_{n}) = 6n - 15$when$n \ge 6$, establishing the tight diagnosability bounds for this fundamental network topology. To enable practical implementation, we design a Trial System-based Fault Diagnosis Algorithm (TSFD) that features adaptive syndrome verification and parallel fault localization mechanisms. Extensive simulations demonstrate the accuracy of 98.99% fault detection with linear-time complexity$O(Nd)$inn-dimensional star networks. This work advances network reliability theory by introducing a multi-feature diagnosability measure for system-level diagnosis and developing an efficient diagnosis algorithm validated through large-scale network emulation.

With the scale of multiprocessor systems constantly increasing, the large number of interconnected processors (or nodes) makes faulty nodes inevitable. The fault diagnosis of multiprocessor systems therefore is a key technique for the system’s robustness. In this paper, we first propose a novel diagnostic metric, the$h$-extra$r$-component diagnosability, denoted$ECD^{h}_{r}(G)$, which characterizes one special pattern of faults. We derive some theoretical results for the ECD of hypercube, denoted$ECD^{h}_{r}(Q_{n})$, under the PMC model. Diagnostic algorithms is proposed and implemented to detect faulty nodes that will disconnect hypercube$Q_{n}$into$r$components each containing at least$h+1$nodes. We also test the ECD-PMC algorithm to the hypercube network with different number of faulty processors satisfying the$h$-extra$r$-component condition. Extensive simulation results show that our proposed method achieves very good performance in terms of ACCR, TPR, FPR, and TNR.

Autonomous driving with reinforcement learning (RL) has significant potential. However, applying RL in real-world settings remains challenging due to the need for safe, efficient, and robust learning. Incorporating human expertise into the learning process can help overcome these challenges by reducing risky exploration and improving sample efficiency. In this work, we propose a reward-free, active human-in-the-loop learning method called Human-Guided Distributional Soft Actor-Critic (H-DSAC). Our method combines Proxy Value Propagation (PVP) and Distributional Soft Actor-Critic (DSAC) to enable efficient and safe training in real-world environments. The key innovation is the construction of a distributed proxy value function within the DSAC framework. This function encodes human intent by assigning higher expected returns to expert demonstrations and penalizing actions that require human intervention. By extrapolating these labels to unlabeled states, the policy is effectively guided toward expert-like be-havior. With a well-designed state space, our method achieves real-world driving policy learning within practical training times. Results from both simulation and real-world experiments demonstrate that our framework enables safe, robust, and sample-efficient learning for autonomous driving. The videos and code are available at: https://github.com/lzqw/H-DSAC.

The Surgical Visual Question Localized-Answering (VQLA) aims to locate the specific instance area while responing the associated question, which has the potential to assist junior resident doctors in understanding the surgical process and offering decision support for surgeons. Yet, this task remains a challenging job for data-driven neural networks, due to the serious reliance on surgical scene information provided by posterior knowledge. Hence, we propose a prior-posterior knowledge prompting-and-Reasoning (PPKPR) method to imitate the operational mode of a surgeon. Surgeons systematically inspect each instance within the surgical scene and its associated question, subsequently relying on their accumulated work experience to understand and answer the questions. The PPKPR comprises three modules: prior-posterior multi-domain knowledge prompter (PPMP), prior-posterior instance knowledge prompter (PPIP), and posterior knowledge Reasoner (PKR). Specifically, PPMP aligns prior-posterior multi-domain knowledge, thus prompting model to alleviate the misinterpretations of the textual question. PPIP provides the prior instance knowledge, ensuring model to focus on correct areas in the visual scene. The prompted knowledge is refined by the PKR to reasoning the final answer. Experimental results demonstrate that our method performs favorably against the state-of-the-art methods on the EndoVis-18 and EndoVis-17 datasets.

The potential benefits of automatic radiology report generation, such as reducing misdiagnosis rates and enhancing clinical diagnosis efficiency, are significant. However, existing data-driven methods lack essential medical prior knowledge, which hampers their performance. Moreover, establishing global correspondences between radiology images and related reports, while achieving local alignments between images correlated with prior knowledge and text, remains a challenging task. To address these shortcomings, we introduce a novel Eye Gaze Guided Cross-modal Alignment Network (EGGCA-Net) for generating accurate medical reports. Our approach incorporates prior knowledge from radiologists' Eye Gaze Region (EGR) to refine the fidelity and comprehensibility of report generation. Specifically, we design a Dual Fine-Grained Branch (DFGB) and a Multi-Task Branch (MTB) to collaboratively ensure the alignment of visual and textual semantics across multiple levels. To establish fine-grained alignment between EGR-related images and sentences, we introduce the Sentence Fine-grained Prototype Module (SFPM) within DFGB to capture cross-modal information at different levels. Additionally, to learn the alignment of EGR-related image topics, we introduce the Multi-task Feature Fusion Module (MFFM) within MTB to refine the encoder output information. Finally, a specifically designed label matching mechanism is designed to generate reports that are consistent with the anticipated disease states. The experimental outcomes indicate that the introduced methodology surpasses previous advanced techniques, yielding enhanced performance on two extensively used benchmark datasets: Open-i and MIMIC-CXR.

Localization is a fundamental problem in autonomous mobile robot navigation. This paper introduces a new artificial landmark-based localization system for mobile robots navigating in indoor environments. Laser-activated RFID tag is designed and used as the artificial landmark in the proposed localization system. The robot localization is realized via the combination of the stereo vision and laser-activated RFID based on the principle of triangulation. The localization system functions like an indoor GPS. Preliminary research shows that the proposed system is promising to provide a robust and accurate indoor localization method for mobile robots.

This paper introduces a novel self-localization algorithm for mobile robots, which recovers the robot position and orientation from a single image of identified landmarks taken by an onboard camera. The visual angle between two landmarks can be derived from their projections in the same image. The distances between the optical center and the landmarks can be calculated from the visual angles and the known landmark positions based on the law of cosine. The robot position can be determined using the principle of trilateration. The robot orientation is then computed from the robot position, landmark positions and their projections. Extensive simulation has been carried out. A comprehensive error analysis provides the insight on how to improve the localization accuracy.