Deep learning applications in fault diagnosis face two critical challenges. First, a significant distribution gap between source domain training data and target domain samples with unknown noise patterns. Second, labeled fault data remain scarce in practice. These issues hinder the practical deployment. This paper presents a Cross-View Consistency Network (CVC-Net) to tackle these problems through noise-generalization capabilities. The method learns robust features from limited source domain data. It maintains diagnostic accuracy with unknown noise data, without prior knowledge of target noise characteristics. CVC-Net processes temporal waveforms and Gramian Angular Field representations through specialized encoders, exploiting their asymmetric noise sensitivities. A cross-view consistency mechanism extracts fault patterns across modalities. The method integrates fault-aware prototype learning for enhanced discrimination with limited labels and employs adaptive fusion that weights view contributions based on cross-view prediction. Experimental validation shows that CVC-Net is effective in challenging scenarios. When tested on target domain with unknown noise types, CVC-Net maintains reliable performance, effectively handling noise patterns not present during source domain training. Under limited-label conditions, it outperforms existing methods in diagnostic performance.
Surface plasmon resonance (SPR) biosensoris a new type of high sensitivity, real-time, label-free detection technology, which plays an increasingly important role in the biomedicine field. Considering the urgent requirement of trace detection, especially for diagnosing early-stage diseases, the demand for high detection sensitivity of sensors is increasing. In recent years, various nanostructures have been proposed to design SPR biosensors. By constructing composite nanostructures, the detection sensitivity has been significantly enhanced, which has become a promising solution to expand the application of SPR biosensors. This review systematically summarized the basic principle, fabrication and illustrative application of SPR biosensors based on versatile nanostructures. Firstly, the mechanisms of various nanostructures to enhance the detection sensitivity of SPR biosensors were clarified. Then, the preparation strategies of various nanostructures were comprehensively illustrated. In addition, this review also summarized the latest applications of SPR biosensors with different structures. Finally, this review carefully highlighted the current challenges and possible development directions in future.
Benefiting from the rapid advancements in large language models (LLMs), human-drone interaction has reached unprecedented opportunities. In this paper, we propose a method that integrates a fine-tuned CodeT5 model with the Unreal Engine-based AirSim drone simulator to efficiently execute multi-task operations using natural language commands. This approach enables users to interact with simulated drones through prompts or command descriptions, allowing them to easily access and control the drone's status, significantly lowering the operational threshold. In the AirSim simulator, we can flexibly construct visually realistic dynamic environments to simulate drone applications in complex scenarios. By combining a large dataset of (natural language, program code) command-execution pairs generated by ChatGPT with developer-written drone code as training data, we fine-tune the CodeT5 to achieve automated translation from natural language to executable code for drone tasks. Experimental results demonstrate that the proposed method exhibits superior task execution efficiency and command understanding capabilities in simulated environments. In the future, we plan to extend the model functionality in a modular manner, enhancing its adaptability to complex scenarios and driving the application of drone technologies in real-world environments.
In this work, we present the design, fabrication, and study of the optical properties of multilayered metal–dielectric Au/TiO2 structures. The samples were fabricated using Joule effect evaporation for gold and electron beam evaporation for titanium dioxide. Their structure was designed to have an epsilon-near-zero (ENZ) point at different wavelengths around 800 nm, in order to study their nonlinear response as a function of the resonance conditions around the ENZ point. The characterization of the linear properties of the samples was done using spectrophotometry and spectral ellipsometry. We studied the nonlinear response with the z-scan technique at different incident irradiances using a Ti:sapphire femtosecond laser, enabling us to characterize both the refractive and absorptive contributions to the nonlinear response. Due to the high pulse repetition rate inherent to Ti:sapphire systems and the presence of linear absorption in the samples, cumulative pulse-to-pulse thermal effects may be present. A modified version of the z-scan technique that allowed us to separate the electronic from the thermal contribution was used. A clear enhancement of the nonlinear response was observed for the sample with an ENZ point around the laser wavelength 800 nm with a nonlinear refractive index of n2 = 0.103 ± 0.006 cm2·GW−1, a value that is comparable to other ENZ materials in literature.
The European Space Agency (ESA), driven by its ambitions on planned lunar missions with the Argonaut lander, has a profound interest in reliable crater detection, since craters pose a risk to safe lunar landings. This task is usually addressed with automated crater detection algorithms (CDA) based on deep learning techniques. It is non-trivial due to the vast amount of craters of various sizes and shapes, as well as challenging conditions such as varying illumination and rugged terrain. Therefore, we propose a deep-learning CDA based on the OWLv2 model, which is built on a Vision Transformer, that has proven highly effective in various computer vision tasks. For fine-tuning, we utilize a manually labeled dataset fom the IMPACT project, that provides crater annotations on high-resolution Lunar Reconnaissance Orbiter Camera Calibrated Data Record images. We insert trainable parameters using a parameter-efficient fine-tuning strategy with Low-Rank Adaptation, and optimize a combined loss function consisting of Complete Intersection over Union (CIoU) for localization and a contrastive loss for classification. We achieve satisfactory visual results, along with a maximum recall of 94.0
