• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    测试科学与仪器(英文版)

    测试科学与仪器(英文版)

    JournalISSN 1674-8042

    年发文量

    研究主题

    论文(1191)

    排序
    1Remote Sensing Semantic Change Detection Via Hybrid Mamba-Transformer Architecture and Cross-Attention Guidance
    Chen Guojun, Kuang Junyao,Ge Hongwei

    Semantic change detection (SCD) in remote sensing aims to identify change regions and recognize semantic categories between bi-temporal images simultaneously. In practical applications, remote sensing images are often susceptible to irrelevant environmental factors such as illumination fluctuations and seasonal vegetation succession, which frequently lead traditional models to pseudo-change detections or semantic misclassifications. To address these challenges, we propose a novel hybrid Mamba-Transformer dual-branch architecture designed to balance efficiency of global context modeling with precision of fine-grained feature extraction. Specifically, vision Mamba blocks are incorporated into encoder stage to leverage their ability to model long sequences with linear complexity, effectively capturing spatiotemporal dependencies of ground objects across large scales. Furthermore, to mitigate feature drift caused by illumination variations and vegetation growth, a cross-attention-guided fusion module is introduced. By calculating correlation between bi-temporal features, this module dynamically enhances feature responses associated with genuine changes while suppressing environmental noise. Finally, decoder integrates Transformer self-attention mechanism to further refine delineation of object boundaries in complex scenes. Extensive experiments were conducted on SECOND and Landsat-SCD datasets to evaluate proposed method. On SECOND dataset, HMTNet achieved 73.85% mIoU and 23.12% SeK, while on Landsat-SCD dataset, it yielded 96.15% overall accuracy. Results confirmed significant performance advantages over mainstream baselines and validated core contributions of proposed hybrid architecture in enhancing environmental robustness and semantic consistency. Integration of Mamba’s global modeling and Transformer’s local refinement provides a robust solution for large-scale remote sensing monitoring under varying environmental conditions, effectively distilling change-relevant information from noisy backgrounds while maintaining high-fidelity boundary localization.

    2026
    引用
    AI阅读
    加入学术空间
    2Design and Verification of Triaxial MOEMS Accelerometer Based on Grating Talbot Effect
    Guo Shangzhou, Zhao Yinuo,Jin Li, Xie Kunyang, Jia Xinrui,Li Mengwei

    This paper presents a monolithic triaxial micro-opto-electromechanical systems (MOEMS) accelerometer utilizing the Talbot effect of micro-nano gratings, which integrates in-plane and out-of-plane sensing structures on a single chip to enable fully triaxial acceleration detection. Based on optical near-field diffraction, the design achieves high sensitivity, wide linear operating range, and superior acceleration resolution. A theoretical model utilizing the Talbot effect for triaxial acceleration sensing is rigorously established, and active optical power stabilization is integrated to mitigate intensity-induced drift caused by light source fluctuations. Through co-optimization of the mechanical structure and nano-grating parameters, the scale factor of the accelerometer is significantly enhanced. The working principle was validated through both simulation and experiment, with good agreement between theoretical predictions and experimental results. The fabricated MOEMS accelerometer, with a compact footprint of 16 mm×16 mm×0.4 mm, exhibits a sensitivity of 2.9 V·g-1 (non-linearity <0.68%) and a resolution of 345 μg. The out-of-plane and in-plane accelerometers achieve bias instability below 54.2 μg and velocity random walk (VRW) below 38.7 μg·Hz-1/2, respectively. These results demonstrate the potential of the proposed architecture for high-precision triaxial inertial sensing in applications such as autonomous navigation, automotive industry monitoring, and industrial machinery condition assessment.

    2026
    引用
    AI阅读
    加入学术空间
    3A Review of Early Warning Methods Based on Force-Gas-temperature Signals for Thermal Runaway in Lithium-Ion Batteries
    Hongzhang Wu, Zan Han, Yicheng Guo, Denglong Ma, Yuhong Li, Yihong Liu, Lihua Tian

    Lithium-ion batteries (LIBs) offer high performance for energy storage but pose safety risks, especially thermal runaway. To enable early warning, battery condition can be inferred indirectly and incompletely from three parameters: mechanical stress-strain, temperature, and gas composition. These three signals differ fundamentally in their physical origins, resulting in distinct timing, sensitivity, and reliability. Although temperature directly reflects the cellu2019s thermal state and surface temperature monitoring is mature and robust, heat-transfer delays make it suitable only as a final indicator. Expansion force responds quickly, providing minutes of lead time, yet is vulnerable to mechanical noise. Characteristic gases such as H2 and CO originate from very early side reactions, including solid electrolyte interphase (SEI) decomposition and electrolyte evaporation, offering tens of minutes of lead time. However, gas detection suffers from dilution, adsorption, and sensor cross-sensitivity, limiting accuracy and cost-effectiveness. No single signal can simultaneously achieve ultra-early, reliable, and low-cost warning. This paper reviews most existing thermal runaway warning mechanisms based on the force-gas-temperature triplet and presents several new predictive approaches. Moreover, the impact of machine learning on the spatiotemporal accuracy and generalization ability of thermal runaway early warning techniques is highlighted. We further propose that a force-gas-temperature multi-modal strategyu2014leveraging the complementarity of the three signalsu2014is essential for practical deployment. Finally, future perspectives are specified in three directions: sensing technology to improve gas sensor selectivity, reduce drift, and enable low-cost distributed sensing; algorithm fusion to develop adaptive multi-signal frameworks that handle signal timing and noise characteristics; and engineering application to validate the force-gas-temperature chain under real operating conditions and achieve low-cost on-board or on-site implementation.

    2026
    引用
    AI阅读
    加入学术空间
    4Traffic Object Detection for Fixed-Camera Expressway Surveillance under Degraded Imaging Conditions
    Liangliang Wang, Shen Xu, Xuexin Wang, Changfei Sun,Yangwen Nie, Can Li

    Traffic object detection in fixed-camera expressway surveillance is challenging because wide-view monitoring scenes contain mixed object scales, distant small targets, weak visual evidence, and degraded imaging factors such as low resolution, blur, weak contrast, glare, and background interference. This study aims to improve multi-class traffic object detection under these practical surveillance conditions while maintaining deployment-oriented real-time inference efficiency. A surveillance-oriented detector is developed on the basis of YOLOv5s. The method introduces two task-driven mechanisms. First, a fine-scale P2 prediction head is added to provide an additional high-resolution response path for small and distant traffic objects. Second, context-aware reassembly of features (CARAFE)-based feature reassembly is incorporated into the neck to improve cross-scale feature fusion for visually weak objects. A self-built expressway surveillance dataset was constructed from roadside videos collected on the Chengdu-Chongqing Expressway. The dataset contains 53582 images, and low-resolution and blurry samples were intentionally retained to reflect realistic monitoring conditions. Experimental results showed that the proposed detector achieved 66.71% mean average precision (mAP), 60.23 frameu00B7s-1, and 50.32% mAP on the small-object subset under the reported evaluation setting. Compared with baseline YOLOv5s, the proposed detector increased overall mAP from 61.89% to 66.71% while maintaining practical inference speed. Controlled module-level analysis on a representative subset further showed that the P2-only setting increased small AP@0.5 from 12.83% to 17.15%, indicating its direct contribution to fine-scale target sensitivity. These results suggest that the proposed detector improves surveillance-oriented traffic object detection in the constructed fixed-camera expressway setting. The evidence is mainly grounded in the self-built application dataset, but broader cross-road and cross-scene validation remains a direction for future work.

    2026
    引用
    AI阅读
    加入学术空间
    5Lightweight Operation Step Recognition Network Based on Post Enhanced Depthwise Convolution and Spatial-Frequency Attention
    Fan Jia,Wang Peng, Li Yue, Lu Yutai

    In practical operational training, image classification is employed to recognize trainees’ operational results in real time. Based on the recognition results, effective feedback can be provided to trainees, which plays a critical role in improving teaching quality and helping mitigate the shortage of teaching resources. Lightweight convolutional neural networks (CNNs) can satisfy real-time recognition requirements. However, recognition accuracy remains low for classes with highly similar operational steps. To address this issue, we propose a lightweight operation step recognition network based on post enhanced depthwise (PED) convolution and spatial-frequency attention mechanism. A post enhanced depthwise convolution module is introduced to effectively improve the nonlinear representation capability of the network, and a spatial-frequency attention (SFA) mechanism is designed to strengthen feature calibration ability, thereby effectively enhancing and integrating important channel features with spatial dimension information. The initial convolution layer and final convolution layer of the backbone network are jointly optimized, reducing the number of model parameters and improving feature information flow. Experiments were conducted on a self-built dataset with ten standard operational step classes. The results show that the proposed method increases the accuracy of two difficult-to-classify classes to 93.50% and 96.02% respectively, the overall Top-1 accuracy in ten classes reaches 95.69%, the training time is only 198 s, and the single-frame inference latency on edge devices is 4.93 ms. These results demonstrate an optimal balance between performance and model lightweightness, superior to other mainstream lightweight networks. The designed network has lightweight and efficient network architecture, and high sensitivity to subtle differences. Therefore, it is appropriate for the devices with limited computing power, and it also has the potential to generalize other real-time recognition tasks with clear steps and indistinct inter-class differences.

    2026
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 1191 篇论文

    高被引作者

    作者引用发文
    Yinjing Guo508
    HongPing Hu467
    XueZhen Cheng462
    Jang-Myung Lee463
    Min -Cheol Hong465
    Yanping Bai464
    MingQing Xiao462
    Jinjuan Song462
    Boo Gyoun Kim462
    V. F. Kravchenko323

    高产作者

    作者引用发文
    FU Luhua1819
    XiaoPeng Wang1917
    Lichen Gu1314
    Hongwei Ge114
    Haiying Dong913
    GuangWu Chen1112
    Yuhong Zhao310
    Fajie Duan510
    ZhiJie Zhang1710
    Zhiguo Gui610

    相关期刊

    Journal of Nanjing University of Science and Technology
    Journal of China Jiliang University
    Journal of Test and Measurement Technology
    Electronic Science and Technology
    Computing Technology and Automation
    Infrared Technology
    Journal of Beijing Information Science & Technology University
    Journal of Electronic Measurement and Instrumentation
    Foreign Electronic Measurement Technology
    吉林大学学报(信息科学版)