检索结果-内蒙古大学图书馆

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Jingcheng Yang Frank Kulwa Xuanwei Liu Yiqing Lu Yufa Fu Guanglin Li Yaping Huai Xin Zhang Yongcheng Li CAS Key Laboratory of Human-Machine Intelligence Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences (CAS) Shenzhen China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen China Shenzhen Dapeng New District Nanao People’s Hospital Shenzhen China Department of Rehabilitation Medicine Shenzhen Longhua District Central Hospital Shenzhen China Brain Cognition and Brain-Computer Intelligence Integration Group Kunming University of Science and Technology Kunming China Shandong Zhongke Advanced Technology Co. Ltd. Jinan China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

The emerging neurorehabilitation technology, Brain-computer Interface (BCI), provides a novel prospect for stroke recovery. However, decoding brain activity during the movement present substantial challenges, and feature extraction is crutial to build a better decoder. In this study the CEBRA method were employed to extract features first based on electroencephalogram(EEG) data during Motor Execution(ME) and Motor lmagery (Ml) tasks for 20 participants (including 10 stroke patients). The results revealed that, in MI tasks, CEBRA-RF (Random Forests) achieved an average classification accuracy of 91.33%, with an average F1-score of 91.19%, and CEBRA-SVM (Support Vector Machine) achieved an average classification accuracy of 91.32%, with an average F1-score of 90.83%. Compared to other conventional feature extraction methods, CEBRA shows significantly higher accuracy (t-test, p<0.01). However, in ME tasks, CEBRA-RF achieved an average classification accuracy of 75.67%, with an average F1-score of 75.39%, and CEBRA-SVM achieved an average classification accuracy of 76.13%, with an average F1-score of 75.80%. Nevertheless, no significant differences were observed compared to other feature extraction methods. These findings demonstrate the potential of CEBRA in decoding patients’ brain activity. The results of this study hold promise in addressing the current challenges of low decoding accuracy in BCI systems, offering a new approach for designing BCI-assisted rehabilitation systems for stroke patients.

关键词： Support vector machines Brain Accuracy Stroke (medical condition) Feature extraction Motors Brain-computer interfaces Neurorehabilitation Decoding Paralysis

来源：评论

学校读者我要写书评

暂无评论

Towards Long Video Understanding via Fine-detailed Video Story Generation

arXiv

引用

arXiv 2024年

作者： You, Zeng Wen, Zhiquan Chen, Yaofo Li, Xin Zeng, Runhao Wang, Yaowei Tan, Mingkui The School of Future Technology South China University of Technology Guangzhou China Peng Cheng Laboratory Shenzhen China The School of Software Engineering South China University of Technology Guangzhou China The Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China The School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

Long video understanding has become a critical task in computer vision, driving advancements across numerous applications from surveillance to content retrieval. Existing video understanding methods suffer from two challenges when dealing with long video understanding: intricate long-context relationship modeling and interference from redundancy. To tackle these challenges, we introduce Fine-Detailed Video Story generation (FDVS), which interprets long videos into detailed textual representations. Specifically, to achieve fine-grained modeling of long-temporal content, we propose a Bottom-up Video Interpretation Mechanism that progressively interprets video content from clips to video. To avoid interference from redundant information in videos, we introduce a Semantic Redundancy Reduction mechanism that removes redundancy at both the visual and textual levels. Our method transforms long videos into hierarchical textual representations that contain multi-granularity information of the video. With these representations, FDVS is applicable to various tasks without any fine-tuning. We evaluate the proposed method across eight datasets spanning three tasks. The performance demonstrates the effectiveness and versatility of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Inorganic nanoparticles for photothermal treatment of cancer

引用

Journal of Materials Chemistry B 2024年第15期12卷 3569-3593页

作者： Thirumurugan, Senthilkumar Ramanathan, Susaritha Muthiah, Kayalvizhi Samuvel Lin, Yu-Chien Hsiao, Michael Dhawan, Udesh Wang, An-Ni Liu, Wai-Ching Liu, Xinke Liao, Mei-Yi Chung, Ren-Jei No. 1 Sec. 3 Zhongxiao E. Rd Taipei10608 Taiwan School of Materials Science and Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Genomics Research Center Academia Sinica Taipei115 Taiwan Department and Graduate Institute of Veterinary Medicine School of Veterinary Medicine National Taiwan University Taipei10617 Taiwan Centre for the Cellular Microenvironment Division of Biomedical Engineering James Watt School of Engineering Mazumdar-Shaw Advanced Research Centre University of Glasgow GlasgowG116EW United Kingdom Scrona AG Grubenstrasse 9 Zürich8045 Switzerland Faculty of Science and Technology Technological and Higher Education Institute of Hong Kong New Territories Hong Kong999077 Hong Kong College of Materials Science and Engineering Chinese Engineering and Research Institute of Microelectronics Shenzhen University Shenzhen518060 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Department of Applied Chemistry National Pingtung University Pingtung90003 Taiwan Taipei106 Taiwan

In recent years, inorganic nanoparticles (NPs) have attracted increasing attention as potential theranostic agents in the field of oncology. Photothermal therapy (PTT) is a minimally invasive technique that uses nanoparticles to produce heat from light to kill cancer cells. PTT requires two essential elements: a photothermal agent (PTA) and near-infrared (NIR) radiation. The role of PTAs is to absorb NIR, which subsequently triggers hyperthermia within cancer cells. By raising the temperature in the tumor microenvironment (TME), PTT causes damage to the cancer cells. Nanoparticles (NPs) are instrumental in PTT given that they facilitate the passive and active targeting of the PTA to the TME, making them crucial for the effectiveness of the treatment. In addition, specific targeting can be achieved through their enhanced permeation and retention effect. Thus, owing to their significant advantages, such as altering the morphology and surface characteristics of nanocarriers comprised of PTA, NPs have been exploited to facilitate tumor regression significantly. This review highlights the properties of PTAs, the mechanism of PTT, and the results obtained from the improved curative efficacy of PTT by utilizing NPs platforms. © 2024 The Royal Society of Chemistry

关键词： Cancer cells

来源：评论

学校读者我要写书评

暂无评论

Clustering Strategy for Megaconstellation with Synergistic Energy and Size Considerations

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Zhang, Chengxi Yin, Tianle Wang, Wenshuo Wu, Jin Wang, Jihe Qi, Yuhua He, Wei Jiangnan University Key Laboratory of Advanced Control for Light Industry Processes Ministry of Education Wuxi214122 China Beijing Institute of Technology Mechanical Engineering China Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong SAR Hong Kong University of Science and Technology Beijing School of Intelligent Science and Technology Beijing China School of Aeronautics and Astronautics Shenzhen518107 China Sun Yat-sen University No. 135 Xingang West Road Guangzhou China

This paper proposes an energy- and size-aware clustering (ESC) strategy for megaconstellation systems. The methodology constructs a hierarchical architecture with designated cluster heads and member satellites through role differentiation. Cluster heads serve as relay nodes, reducing the communication load on ground infrastructure by interacting with ground stations and other entities. This hierarchical approach enables efficient constellation control through interactions primarily with cluster heads. The ESC strategy begins with a cluster head election process, incorporating orphan handling management to select cluster heads, ensuring full coverage of the entire constellation. Then, a two-stage multi-objective optimization framework is used to deal with division of members to clusters and intra-cluster multi-hop connectivity configurations. This dual-phase approach optimizes energy consumption while maintaining balanced cluster sizes. Simulations on the OneWeb system validate the ESC strategy as a viable solution in that it achieves 55.9% energy consumption reduction compared to traditional discrete gradient optimization methods while maintaining more balanced cluster sizes. © 2025 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Defect Detection Algorithm for Solar Panels 5

Deep Learning based Defect Detection Algorithm for Solar Pan...

引用

5th World Robot Conference Symposium on advanced Robotics and Automation, WRC SARA 2023

作者： Li, Jiaqi Li, Hongxu Wu, Yifan Zhou, Hailiang Manfredi, Luigi Li, Peng Zhang, Hong Hebei Province Yanshan University Department of Key Lab of Industrial Computer Control Engineering Qinhuangdao066004 China University of Alberta Department of Computing Science EdmontonABT6G 2R3 Canada Hebei Baoding Jiasheng Photovoltaic Technology Co. Ltd. China United Kingdom Southern University of Science and Technology Department of Electronic and Electrical Engineering Shenzhen China

ISBN: (纸本)9798350307320

Defect detection of solar panels plays an essential role in guaranteeing product quality within automated production lines. However, traditional manual inspection of solar panel defects suffers from low efficiency. This paper proposes an enhanced YOLOv5 algorithm (EL-YOLOv5) fused with the CBAM hybrid attention module to ensure product quality. The algorithm focuses on detecting five common types of defects that frequently appear on photovoltaic production lines, namely hidden cracks, scratches, broken grids, black spots, and short circuits. This study utilizes publicly available solar panel datasets, as well as datasets collected from actual photovoltaic production lines. These datasets are annotated accordingly and used to train the proposed algorithm. The experimental results demonstrate that the proposed algorithm achieves good performance on both the public and actual solar panel defect datasets. Particularly in actual datasets, where defect features are often less apparent and defects are smaller in size, the proposed algorithm can still detect even minor black spots. © 2023 IEEE.

关键词： Solar panels

来源：评论

学校读者我要写书评

暂无评论

Kernel-based Class-specific Broad Learning System for software defect prediction

Kernel-based Class-specific Broad Learning System for softwa...

引用

2021 International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2021

作者： Chen, Wuxing Yang, Kaixiang Shi, Yifan Feng, Qiying Zhang, Chengxi Yu, Zhiwen Guangdong University of Technology School of Computer Science and Technology Guangzhou China Zhejiang University College of Control Science and Engineering Hangzhou China Huaqiao University School of Engineering Institute Quanzhou China South China University of Technology Computer Science and Engineering Guangzhou China Harbin Institute of Technology Shenzhen Electronic Information Engineering Shenzhen China

ISBN: (纸本)9781665402453

With the continuous expansion of the software industry, the problem of software defects is receiving more and more attention. There has been a series of machine learning methods applied to the field of software defect prediction (SDP) as a way to ensure the stability of software. However, SDP suffers from the imbalance problem. To solve this problem, we first propose a class-specific broad learning system (CSBLS), which assigns a specific penalty factor to each class in accordance with the data distribution. Then we design a class-specific kernel-based broad learning system (CSKBLS), which adopts kernel mapping instead of random projection. This additive kernel scheme takes into account both outliers and noise in the data set. Extensive experiments on the real-world NASA datasets show that CSKBLS outperforms the comparison methods on the tasks of software defect prediction. © 2021 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Consistent and Asymptotically Statistically-Efficient Solution to Camera Motion Estimation

arXiv

引用

arXiv 2024年

作者： Zeng, Guangyang Zeng, Qingcheng Li, Xinghan Mu, Biqiang Chen, Jiming Shi, Ling Wu, Junfeng The School of Data Science Chinese University of Hong Kong Shenzhen Shenzhen518172 China The College of Control Science and Engineering The State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix, which is not optimal in the maximum likelihood (ML) sense. In this paper, we dive into the original measurement model with respect to the rotation matrix and normalized translation vector and formulate the ML problem. We then propose a two-step algorithm to solve it: In the first step, we estimate the variance of measurement noises and devise a consistent estimator based on bias elimination;In the second step, we execute a one-step Gauss-Newton iteration on manifold to refine the consistent estimate. We prove that the proposed estimate owns the same asymptotic statistical properties as the ML estimate: The first is consistency, i.e., the estimate converges to the ground truth as the point number increases;The second is asymptotic efficiency, i.e., the mean squared error of the estimate converges to the theoretical lower bound - Cramer-Rao bound. In addition, we show that our algorithm has linear time complexity. These appealing characteristics endow our estimator with a great advantage in the case of dense point correspondences. Experiments on both synthetic data and real images demonstrate that when the point number reaches the order of hundreds, our estimator outperforms the state-of-the-art ones in terms of estimation accuracy and CPU time. Copyright © 2024, The Authors. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

ArmorCLIP: A hybrid defense strategy for boosting adversarial robustness in vision-language models

ArmorCLIP: A hybrid defense strategy for boosting adversaria...

引用

2024 International Conference on computer Application and Information Security, ICCAIS 2024

作者： Li, Yijun Liang, Yuhan Niu, Yumeng Shen, Qianhe Liu, Hangyu Computer Science and Technology Harbin Institute of Technology Guangdong Shenzhen518055 China Faculty of Engineering University of Bristol BristolBS8 1TH United Kingdom Beijing University of Civil Engineering and Architecture Beijing102612 China University of Toronto Mississauga MississaugaL5L 1C6 Canada Xi’an Tieyi ICC Shaanxi Xi’an710054 China

ISBN: (纸本)9781510689312

The robustness of Vision-Language Models (VLMs) such as Contrastive Language-Image Pretraining (CLIP) is critical for their deployment in safety-critical applications like autonomous driving, healthcare diagnostics, and security systems, where accurate interpretation of visual and textual data is essential. However, these models are highly susceptible to adversarial attacks, which can severely compromise their performance and reliability in real-world scenarios. Previous methods have primarily focused on improving robustness through adversarial training and generating adversarial examples using models like FGSM, AutoAttack, and DeepFool. However, these approaches often rely on strong assumptions, such as fixed perturbation norms or predefined attack patterns, and involve high computational complexity, making them challenging to implement in practical settings. In this paper, we propose a novel adversarial training framework that integrates multiple attack strategies and advanced machine learning techniques to significantly enhance the robustness of VLMs against a broad range of adversarial attacks. Experiments conducted on real-world datasets, including CIFAR-10 and CIFAR-100, demonstrate that the proposed method significantly enhances model robustness. The fine-tuned CLIP model achieved an accuracy of 43.5% on adversarially perturbed images, compared to only 4% for the baseline model. The neural network model achieved a high accuracy of 98% in these challenging classification tasks, while the XGBoost model reached a success rate of 85.26% in prediction tasks. © The Authors.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Edge Accelerated Robot Navigation With Collaborative Motion Planning

arXiv

引用

arXiv 2023年

作者： Li, Guoliang Han, Ruihua Wang, Shuai Gao, Fei Eldar, Yonina C. Xu, Chengzhong Department of Computer and Information Science University of Macau 999078 China The Department of Computer Science The University of Hong Kong Hong Kong The Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China The State Key Laboratory of Industrial Control Technology The Huzhou Institute Zhejiang University Zhejiang 310027 China The Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot7610001 Israel

Low-cost distributed robots suffer from limited onboard computing power, resulting in excessive computation time when navigating in cluttered environments. This paper presents Edge Accelerated Robot Navigation (EARN), to achieve real-time collision avoidance by adopting collaborative motion planning (CMP). As such, each robot can dynamically switch between a conservative motion planner executed locally to guarantee safety (e.g., path-following) and an aggressive motion planner executed non-locally to guarantee efficiency (e.g., overtaking). In contrast to existing motion planning approaches that ignore the interdependency between low-level motion planning and high-level resource allocation, EARN adopts model predictive switching (MPS) that maximizes the expected switching gain with respect to robot states and actions under computation and communication resource constraints. The MPS problem is solved by a tightly-coupled decision making and motion planning framework based on bilevel mixed-integer nonlinear programming and penalty dual decomposition. We validate the performance of EARN in indoor simulation, outdoor simulation, and real-world environments. Experiments show that EARN achieves significantly smaller navigation time and higher success rates than state-of-the-art navigation approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Dual-Band Printed Antenna Design for Bluetooth and WLAN Applications

Dual-Band Printed Antenna Design for Bluetooth and WLAN Appl...

引用

IEEE International Conference on Electronic Information and Communication technology (ICEICT)

作者： Naveed Hamid Nawaz Khan Botao Feng Xiao Ding Wenzhe Gu Li Deng Kwok L. Chung College of Electronics and Information Engineering Shenzhen University Shenzhen China Faculty of Humanities and Arts Macau University of Science and Technology Macau China School of Computer Science and Engineering Huizhou University Huizhou China College of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China School of Computer Science and Engineering Huizhou University Huizhou P. R. China

ISBN: (数字)9798350384437

ISBN: (纸本)9798350384444

This study presents the fabrication process of a printed antenna on a FR-4 substrate with accurate measurements of 25×37×1 mm 3 . The antenna design, known for its simplicity, has four semicircles with four small square patches at each end. In addition, it includes two rectangular patches that are fitted with pin diode switches in order to enable the ability to operate in two different frequency bands. The antenna's ground has a carefully placed opening. The antenna being examined demonstrates resonance at both the frequencies of 2.4 GHz and 5 GHz, with reflection coefficients of -19.6 dB and -16.5 dB correspondingly. The VSWR for both working frequencies is below 2, satisfying the requirements of Bluetooth and WLAN applications. The tiny size and creative design elements of this antenna allow for versatility and adaptation in many wireless communication systems.

关键词： Wireless communication Antenna measurements Wireless LAN Bluetooth PIN photodiodes Resonant frequency Dual band

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：