检索结果-内蒙古大学图书馆

7th International Conference on Vision, Image and Signal Processing, ICVISP 2023

作者： Yuan, Ge Zhou, Jie Huang, Chucheng Gao, Can Wang, Yangbo Shen, Xinrui National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China College of Mathematics and Statistics Shenzhen University Guangdong Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China

ISBN: (纸本)9781839539848

Prototype-based clustering algorithms have garnered considerable attention in the field of machine learning due to their efficiency and interpretability. Nonetheless, these algorithms often face performance degradation when confronted with high-dimensional or non-ellipsoidal data distributions. To surmount these challenges, this study introduces a novel clustering approach, dubbed Clustering with Adaptive Graph learning and Spectral Rotation (CAGSR). In CAGSR, the imposed spectral rotation operation mitigates the discrepancy between the membership matrix, which adheres to the notion of fuzzy clustering, and the spectral representations derived from an adaptive graph rather than a predefined one. This enables the generation of a comprehensive representation of the data across multiple spaces. Furthermore, the clustering and graph learning tasks are jointly optimized in a projected subspace, which can effectively reduce the adverse impact caused by irrelevant features in the original space. The proposed method seamlessly integrates fuzzy clustering, graph structure learning, and spectral rotation into a unified model, facilitating the detection of intrinsic structures. Experimental evaluations conducted on benchmark data sets substantiate the effectiveness of CAGSR when compared to related clustering approaches. © The Institution of engineering & Technology 2023.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

Noise-Optimized Signal Processing for TENG-Based Touch Sensing Using I2C Integrated Circuits

引用

IEEE Sensors Journal 2025年

作者： Moger, Gourav Kakim, Alibek Mubarak, Assem Bushanov, Yersaiyn Kalimuldina, Gulnur Yeshmukhametov, Azamat Nazarbayev University Department of Robotics Engineering Astana Kazakhstan Nazarbayev University School of Engineering and Digital Sciences Department of Mechanical and Aerospace Engineering Astana Kazakhstan LLP MiraiTech Astana Kazakhstan Nazarbayev University Institute of Smart Systems and Artificial Intelligence Advanced Robotics and Mechatronics System laboratory Astana Kazakhstan

Triboelectric nanogenerator (TENG) sensors efficiently convert mechanical stimuli into electrical signals, making them well-suited for touch sensing due to their high sensitivity, durability, and self-powered operation. However, conventional signal acquisition methods introduce noise, affecting measurement accuracy. This paper presents a compact, Inter-Integrated Circuit (I2C)-based signal processing circuit designed to enhance signal fidelity while minimizing noise interference. The system’s performance was evaluated by analyzing sensor response across varying contact areas (50 mm² to 576 mm²) and drop heights, demonstrating a consistently high signal-to-noise ratio (SNR) across impact conditions. A high-frequency impact experiment further confirmed the PCB’s ability to distinguish sensor output from noise. Comparison with direct analog acquisition showed a significant enhancement in SNR, validating the PCB’s effectiveness in noise reduction. The system exhibited a rise time of 3.27 milliseconds, ensuring rapid detection of mechanical stimuli. Additionally, the measured latency of 88.9 ms between impact and signal detection falls within acceptable limits for realtime applications. These results establish the proposed PCB-based signal processing method as a practical solution for improving TENG sensor performance in touch-sensing applications requiring high accuracy and noise resilience. The compact, low-power design further enhances its suitability for integration into wearable electronics, interactive surfaces, and space-constrained systems where conventional bulky processing units are impractical. © 2001-2012 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Forewarning Crossing Intention of Pedestrians Using Multimodal Deep Learning Approach 7

Forewarning Crossing Intention of Pedestrians Using Multimod...

引用

7th International Conference on Green Technology and Sustainable Development, GTSD 2024

作者： Nguyen, Chi-Tam Duong, Minh-Thien Phan, Thanh-Danh Nguyen, Van-Binh Le, My-Ha Hcmc University of Technology and Education Intelligent System Laboratory Ho Chi Minh City Viet Nam Soongsil University Dept. of Information and Telecommunication Engineering Seoul Korea Republic of Chungbuk National University Dept. of Intelligent Systems and Robotics Cheongju Korea Republic of Institute of Engineering-Technology Thu Dau Mot University Thu Dau Mot City Viet Nam Hcmc University of Technology and Education Faculty of Electrical and Electronics Engineering Ho Chi Minh City Viet Nam

ISBN: (纸本)9798350386073

Nowadays, traffic accidents not only come from public transportation but also from pedestrians. Therefore, designing a solution to protect pedestrian safety is essential. This article proposes a system for forewarning the crossing intentions of pedestrians, comprising the tasks of detection, tracking, and intention prediction. Firstly, our proposed system performs the detection and pose estimation of pedestrians using the YOLOv7-Pose model. Subsequently, the OC-SORT algorithm is employed for the tracking task. Ultimately, an efficient architecture based on the VoVNet backbone and Temporal Shift Module is provided to forewarn whether pedestrians will cross the road or not. The input of the proposed network in multimodality includes RGB image or semantic image map, keypoints, and vehicle speed. In addition, the bag-of-freebies technique is applied to enhance the model's overall performance and address the issue of biased model creation caused by imbalanced data. Comprehensive experiments performed on the JAAD benchmark dataset demonstrate that our proposed method performs better than existing benchmark classification models. © 2024 IEEE.

关键词： Mass transportation

来源：评论

学校读者我要写书评

暂无评论

Theoretical Modeling and Performance Analysis on the Linear Electromagnetic Actuator with High Nonlinear Dynamic Negative Stiffness

SSRN

引用

SSRN 2024年

作者： Wang, Chuchao Lu, Shizhou Liu, Xiaohan Mo, Wenyin Zhang, Bin Li, Kai Sun, Lining Mechanical Electrical & Information Engineering Shandong University Weihai264209 China School of Mechanical Engineering Dalian University of Technology Dalian116081 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

Electromagnetic mechanisms are introduced to adjust the stiffness and improve the performance of mechanical systems, which have been widely researched. In this paper, the transient performance of a novel linear solenoid elastic actuator with higher nonlinear negative stiffness and speed by introducing the negative stiffness mechanism is analyzed and predicted. The actuator can achieve an initial theoretical stiffness of -20.96 N/m at 1 A current and a maximum stroke of 9 mm in 0.5 s. The performance indicators including peak time, overshoot, and steady-state displacement are obtained through electromagnetic-mechanical coupled modeling. The influence of system parameters including natural frequency, equivalent stiffness and damping coefficient on performance indicators is also studied. First, the approximate analytical model of the electromagnetic force is derived by constructing an innovative magnetic field distribution model. Second, the nonlinear vibration equation is solved theoretically to obtain the analytical results of the performance indicators and system parameters. Finally, the transient displacements and performance indicators obtained from the analytical model, the numerical model established in Simulink software and the simulation model obtained in Adams software are compared. The maximum errors of the peak time, overshoot and stable displacement through the analytical model and experiment are 2.56 ms, 9.37% and 0.32 mm, respectively. The theoretical and experimental results show the nonlinear effects of input currents on performance indicators and system parameters. The overshoot has a strong positive following feature on the damping coefficient, but the vibration frequency mainly depends on the equivalent stiffness of the system. This research provides a reference for the transient solution of nonlinear electromagnetic-dynamic coupling models and performance improvement of linear electromagnetic actuators. © 2024, The Authors. All rights reserved.

关键词： Stiffness

来源：评论

学校读者我要写书评

暂无评论

Two-Photon Image-Guided Automated 3D Locating of Micropipette Tip

Two-Photon Image-Guided Automated 3D Locating of Micropipett...

引用

第43届中国控制会议

作者： Zizhen Li Jie Li Qili Zhao Xin Zhao Mingzhu Sun National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases Engineering Research Center of Trusted Behavior Intelligence Ministry of Education Tianjin Key Laboratory of Intelligent Robotics (tikLIR) Institute of Robotics and Automatic Information System (IRAIS) Nankai University Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The 21st century has been universally recognized by the scientific community as the era of neuroscience, with the patch clamp technique serving as a key to unraveling the intricate mysteries of brain science. Due to its advantages such as reduced sample damage and enhanced penetration capability, the application of two-photon microscope in deep imaging of live animals has become prevalent, making it a preferred choice over confocal microscope. At present, there exist a few near complete automation techniques of image-guided patching in vivo, which typically start from the micropipette tip appearing in the imaging field of view. The operational workflow for the step involving the installation of the micropipette until the micropipette tip becomes visible within the field of view has regrettably not been provided. However, it is crucial information that is of utmost importance to experimental personnel. In this paper, we present a comprehensive workflow for 3D locating of micropipette tip in a self-built two-photon microscope tailored for patch clamp experiments. Moreover, by fully incorporating the distinctive features of two-photon imaging, the study applies statistical methods to achieve automated execution of the corresponding workflow. The experimental results indicate that the process of micropipette tip locating takes an average of 58.4 ***, the method is not sensitive to parameter selection, allowing experimenters to obtain suitable parameters for different systems through simple testing. The automated 3D micropipette tip locating method proposed in this paper, with its versatility, holds great potential for seamless integration into commercial two-photon microscope systems. It significantly contributes to reducing the work burden on experimenters and minimizing the time required for experimental preparation.

关键词： 3D micropipette tip locating two-photon microscope automated method

来源：评论

学校读者我要写书评

暂无评论

Tunable Rectification of Diffusion-Wave Fields by Spatiotemporal Metamaterials

引用

Physical Review Letters 2022年第25期129卷 256601-256601页

作者： Jiaxin Li Zhanxiang Zhang Guoqiang Xu Haoran Sun Lizhou Dai Tianlong Li Cheng-Wei Qiu Department of Electrical and Computer Engineering National University of Singapore Singapore 117583 Singapore State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin 150001 China

The diffusion process is the basis of many branches of science and engineering, and generally obeys reciprocity between two ports of a linear time-invariant medium. Recent research on classical wave dynamics has explored the spatiotemporal modulation to exhibit preferred directions in photons and plasmons. Here we report a distinct rectification effect on diffusion-wave fields by modulating the conductivity and observe nonreciprocal transport of charges. We experimentally create a spatiotemporal diffusion metamaterial, in which a mode transition to zero frequency is realized. A direct current component thereby emerges, showcasing a biased effect on the charge diffusion when the incident fundamental frequency is a multiple of the system modulation frequency. These results may find applications spanning a plethora of diffusive fields in general.

关键词： Diffusion Metamaterials Bloch-Floquet theorem

来源：评论

学校读者我要写书评

暂无评论

SSC- l0 : Sparse Subspace Clustering with the l0 Inequality Constraint 7th

SSC- l0 : Sparse Subspace Clustering with the l0 Inequality...

引用

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Wang, Yangbo Zhou, Jie Lin, Qingshui Lu, Jianglin Gao, Can National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Basic Teaching Department Liaoning Technical University Huludao125105 China College of Engineering Northeastern University BostonMA02115 United States

ISBN: (纸本)9783031476648

Self-expression learning methods often obtain a coefficient matrix to measure the similarity between pairs of samples. However, directly using all points to represent a fixed sample in a class under the self-expression framework may not be ideal, as points from other classes participate in the representing process. To alleviate this issue, this study attempts to achieve representation learning between points only coming from the same class. In practice, it is easier for data points from the same class to represent each other than that from different classes. So, when reconstructing a point, if the number of non-zero elements in the coefficient vector is limited, a model is more likely to select data points from the class where the reconstructed point lies to complete the reconstruction work. Based on this idea, we propose Sparse Subspace Clustering with the l0 inequality constraint (SSC- l0 ). In SSC- l0, the l0 inequality constraint determines the maximum number of non-zero elements in the coefficient vector, which helps SSC- l0 to conduct representation learning among the points in the same class. After introducing the simplex constraint to ensure the translation invariance of the model, an optimization method concerning l0 inequality constraint is formed to solve the proposed SSC- l0, and its convergence is theoretically analyzed. Extensive experiments on well-known datasets demonstrate the superiority of SSC- l0 compared to several state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Active Complaint Control for Smooth and Quick Connector Assembly*

Active Complaint Control for Smooth and Quick Connector Asse...

引用

IEEE International Conference on robotics and Biomimetics

作者： Jun Wu Yu He He Wang Qiyu Wang Shaowei Fan School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

This paper presents an active complaint control for smooth and quick connector assembly. The application requirement of an end-effector with simultaneous connecters is firstly defined. Then, the hybrid impedance control provides the foundation for active search and passive assembly. After that, a resolution-variant Lissajous search is proposed for smooth motion and earlier connection. At last, simulations and experiments indicate that the proposed controller can guarantee smooth and quick search for connector assembly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatial Correspondence between Graph Neural Network-Segmented Images

arXiv

引用

arXiv 2023年

作者： Li, Qian Fu, Yunguan Yang, Qianye Du, Zhijiang Yu, Hongjian Hu, Yipeng Department of Medical Physics and Biomedical Engineering University College London London United Kingdom State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

Graph neural networks (GNNs) have been proposed for medical image segmentation, by predicting anatomical structures represented by graphs of vertices and edges. One such type of graph is predefined with fixed size and connectivity to represent a reference of anatomical regions of interest, thus known as templates. This work explores the potentials in these GNNs with common topology for establishing spatial correspondence, implicitly maintained during segmenting two or more images. With an example application of registering local vertebral sub-regions found in CT images, our experimental results showed that the GNN-based segmentation is capable of accurate and reliable localization of the same interventionally interesting structures between images, not limited to the segmentation classes. The reported average target registration errors of 2.2±1.3 mm and 2.7±1.4 mm, for aligning holdout test images with a reference and for aligning two test images, respectively, were by a considerable margin lower than those from the tested non-learning and learning-based registration algorithms. Further ablation studies assess the contributions towards the registration performance, from individual components in the originally segmentation-purposed network and its training algorithm. The results highlight that the proposed segmentation-in-lieu-of-registration approach shares methodological similarities with existing registration methods, such as the use of displacement smoothness constraint and point distance minimization albeit on non-grid graphs, which interestingly yielded benefits for both segmentation and registration. We, therefore, conclude that the template-based GNN segmentation can effectively establish spatial correspondence in our application, without any other dedicated registration algorithms. © 2023, CC BY.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Presentation Attack Detector Using Global-Local Model

arXiv

引用

arXiv 2024年

作者： Liu, Haozhe Zhang, Wentian Liu, Feng Wu, Haoqian Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society The National Engineering Laboratory for Big Data System Computing Technology The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The vulnerability of automated fingerprint recognition systems (AFRSs) to presentation attacks (PAs) promotes the vigorous development of PA detection (PAD) technology. However, PAD methods have been limited by information loss and poor generalization ability, resulting in new PA materials and fingerprint sensors. This paper thus proposes a global-local model-based PAD (RTK-PAD) method to overcome those limitations to some extent. The proposed method consists of three modules, called: 1) the global module;2) the local module;and 3) the rethinking module. By adopting the cut-out-based global module, a global spoofness score predicted from nonlocal features of the entire fingerprint images can be achieved. While by using the texture in-painting-based local module, a local spoofness score predicted from fingerprint patches is obtained. The two modules are not independent but connected through our proposed rethinking module by localizing two discriminative patches for the local module based on the global spoofness score. Finally, the fusion spoofness score by averaging the global and local spoofness scores is used for PAD. Our experimental results evaluated on LivDet 2017 show that the proposed RTK-PAD can achieve an average classification error (ACE) of 2.28% and a true detection rate (TDR) of 91.19% when the false detection rate (FDR) equals 1.0%, which significantly outperformed the state-of-the-art methods by ∼10% in terms of TDR (91.19% versus 80.74%). Copyright © 2024, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：