检索结果-内蒙古大学图书馆

2023 2nd International Conference on Power system and Power Engineering, PSPE 2023

作者： Huo, Jingchong Meng, Runquan Li, Shengwen Liu, Qiang Shanxi Key Lab of Power System Operation and Control Taiyuan University of Technology Taiyuan030024 China Electric Power Research Institute State Grid Shanxi Electric Power Company Taiyuan030001 China

The research on fault protection technology of AC power grid in AC/DC hybrid microgrid is very mature, while the research on fault protection technology of DC microgrid is still in the development stage. Therefore, the research and development of necessary power electronics and protection devices have become a research hotspot in recent years. In this paper, a microcomputer protection device based on the TMS320F28335 chip is developed. Considering the anti-interference of field use, detailed hardware and software design is carried out. The debugging effect is good, and the low-voltage DC short-circuit fault protection function can be reliably realized. © Published under licence by IOP Publishing Ltd.

关键词： Microcomputers

来源：评论

学校读者我要写书评

暂无评论

Entropy Law: The Story Behind Data Compression and LLM Performance

arXiv

引用

arXiv 2024年

作者： Yin, Mingjia Wu, Chuhan Wang, Yufei Wang, Hao Guo, Wei Wang, Yasheng Liu, Yong Tang, Ruiming Lian, Defu Chen, Enhong State Key Laboratory of Cognitive Intelligence University of Science and Technology of China Noah’s Ark Lab Huawei China

Data is the cornerstone of large language models (LLMs), but not all data is useful for model learning. Carefully selected data can better elicit the capabilities of LLMs with much less computational overhead. Most methods concentrate on evaluating the quality of individual samples in data selection, while the combinatorial effects among samples are neglected. Even if each sample is of perfect quality, their combinations may be suboptimal in teaching LLMs due to their intrinsic homogeneity or contradiction. In this paper, we aim to uncover the underlying relationships between LLM performance and data selection. Inspired by the information compression nature of LLMs, we uncover an "entropy law" that connects LLM performance with data compression ratio and first-epoch training loss, which reflect the information redundancy of a dataset and the mastery of inherent knowledge encoded in this dataset, respectively. Through both theoretical deduction and empirical evaluation, we find that model performance is negatively correlated to the compression ratio of training data, which usually yields a lower training loss. Based on the findings of the entropy law, we propose a quite efficient and universal data selection method named ZIP for training LLMs, which aim to prioritize data subsets exhibiting a low compression ratio. Based on a multi-stage algorithm that selects diverse data in a greedy manner, we can obtain a good data subset with satisfactory diversity. Extensive experiments have been conducted to validate the entropy law and the superiority of ZIP across different LLM backbones and alignment stages. We also present an interesting application of entropy law that can detect potential performance risks at the beginning of model training.2 © 2024, CC BY.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

A Multiple-Scale Vision-Based Object Detection Algorithm for UAVs Based on the Local Feature Matching with Transformer Model 3rd

A Multiple-Scale Vision-Based Object Detection Algorithm for...

引用

3rd International Conference on Autonomous Unmanned systems, ICAUS 2023

作者： Yang, Xiaolong Deng, Hui Duan, Xuting Xia, Haiying School of Transportation Science and Engineering Beihang University Beijing100191 China State Key Lab of Intelligent Transportation System Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control Beijing China China Telecom Digital City Technology Co. Ltd. Hebei China Key Laboratory of Operation Safety Technology on Transport Vehicles Ministry of Transport Beijing100088 China

ISBN: (纸本)9789819711024

With the addition of UAVs, the perception and recognition of ground targets have also advanced significantly. UAV photography has gradually become an integral part of this field. Due to the flexibility and lightness of UAVs, they can freely adjust their height and angle. Moreover, multiple UAVs can perceive and recognize the same target from different directions, which has led to increased attention toward collaborative perception using multiple viewpoints of UAVs. Given the diverse image information captured by UAVs from various angles, heights, and environments, i.e., multi-scale conditions, this paper addresses the challenge of target detection by leveraging the Local Feature Matching with Transformer (LoFTR) approach. The paper also explains the process of coordinating transformations for different images captured by multiple UAVs to ensure data consistency and synergy. Finally, experimental validation using the VisDrone dataset demonstrates that the developed detection method can reliably and efficiently operate on targets at different angles and altitudes. © Beijing HIWING Scientific and Technological Information Institute 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A mosquito mouthpart-like bionic neural probe

引用

Microsystems & Nanoengineering 2023年第4期9卷 77-90页

作者： Yu Zhou Huiran Yang Xueying Wang Heng Yang Ke Sun Zhitao Zhou Liuyang Sun Jianlong Zhao Tiger H.Tao Xiaoling Wei State Key Laboratory of Transducer Technology Shanghai Institute of Microsystem and Information TechnologyChinese Academy of Sciences200050 ShanghaiChina School of Graduate Study University of Chinese Academy of Sciences100049 BeijingChina 2020 X-Lab Shanghai Institute of Microsystem and Information TechnologyChinese Academy of Sciences200050 ShanghaiChina Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of Sciences100049 BeijingChina Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences200031 ShanghaiChina Neuroxess Co. Ltd.(Jiangxi)330029 NanchangJiangxiChina Guangdong Institute of Intelligence Science and Technology Hengqin519031 ZhuhaiGuangdongChina Tianqiao and Chrissy Chen Institute for Translational Research ShanghaiChina

Advancements in microscale electrode technology have revolutionized the field of neuroscience and clinicalapplications by offering high temporal and spatial resolution of recording and stimulation. Flexible neural probes, withtheir mechanical compliance to brain tissue, have been shown to be superior to rigid devices in terms of stability andlongevity in chronic recordings. Shuttle devices are commonly used to assist flexible probe implantation;however, theprotective membrane of the brain still makes penetration difficult. Hidden damage to brain vessels duringimplantation is a significant risk. Inspired by the anatomy of the mosquito mouthparts, we present a biomimeticneuroprobe system that integrates high-sensitivity sensors with a high-fidelity multichannel flexible electrode *** customizable system achieves distributed and minimally invasive implantation across brain regions. Mostimportantly, the system’s nonvisual monitoring capability provides an early warning detection for intracranial softtissues, such as vessels, reducing the potential for injury during implantation. The neural probe system demonstratesexceptional sensitivity and adaptability to environmental stimuli, as well as outstanding performance in postoperativeand chronic recordings. These findings suggest that our biomimetic neural-probe device offers promising potential forfuture applications in neuroscience and brain-machine interfaces.

关键词： neural implantation recording

来源：评论

学校读者我要写书评

暂无评论

A theoretical and experimental study of deformation mechanism dictated by disclination-dislocation coupling in Mg alloys at different temperatures

引用

材料科学技术（英文版） 2025年第5期208卷 176-188页

作者： Chunfeng Du Yipeng Gao Yizhen Li Quan Li Min Zha Cheng Wang Hailong Jia Hui-Yuan Wang Key Laboratory of Automobile Materials of Ministry of Education&School of Materials Science and Engineering Nanling CampusJilin UniversityChangchun 130025China Key Laboratory of Automobile Materials of Ministry of Education&School of Materials Science and Engineering Nanling CampusJilin UniversityChangchun 130025China International Center of Future Science Jilin UniversityChangchun 130012China International Center of Future Science Jilin UniversityChangchun 130012China State Key Lab of Superhard Materials and Key Laboratory of Material Simulation Methods&Software of Ministry of Education College of PhysicsJilin UniversityChangchun 130012China Key Laboratory of Automobile Materials of Ministry of Education&School of Materials Science and Engineering Nanling CampusJilin UniversityChangchun 130025China International Center of Future Science Jilin UniversityChangchun 130012China State Key Laboratory of Reliability and Intelligence of Electrical Equipment School of Material Science and EngineeringHebei University of TechnologyTianjin 300130China

Dislocations and disclinations are fundamental topological defects within crystals,which determine the mechanical properties of metals and *** their important roles in multiple physical mecha-nisms,e.g.,dynamic recovery and grain boundary mediated plasticity,the intrinsic coupling and corre-lation between disclinations and dislocations,and their impacts on the deformation behavior of metallic materials still remain obscure,partially due to the lack of a theoretical tool to capture the rotational na-ture of *** using a Lie-algebra-based theoretical framework,we obtain a general equation to quantify the intrinsic coupling of disclinations and *** quasi in-situ electron backscat-ter diffraction characterizations and disclination/dislocation density analyses in Mg alloys,the generation,coevolution and reactions of disclinations and dislocations during dynamic recovery and superplastic de-formation have been quantitatively *** has been demonstrated that the obtained governing equa-tion can capture multiple physical processes associated with mechanical deformation of metals,e.g.,grain rotation and grain boundary migration,at both room temperature and high *** establishing the disclination-dislocation coupling equation within a Lie algebra description,our work provides new insights for exploring the coevolution and reaction of disclinations/dislocations,with profound implica-tions for elucidating the microstructure-property relationship and underlying deformation mechanisms in metallic materials.

关键词： Magnesium alloys Dislocations Grain boundaries Plastic deformation Grain rotation Disclination-dislocation coupling

来源：评论

学校读者我要写书评

暂无评论

MemoryFormer: minimize transformer computation by removing fully-connected layers 24

MemoryFormer: minimize transformer computation by removing f...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Ning Ding Yehui Tang Haochen Qin Zhenli Zhou Chao Xu Lin Li Kai Han Heng Liao Yunhe Wang State Key Lab of General AI School of Intelligence Science and Technology Peking University Huawei Noah's Ark Lab. Huawei HiSilicon

ISBN: (纸本)9798331314385

In order to reduce the computational complexity of large language models, great efforts have been made to to improve the efficiency of transformer models such as linear attention and flash-attention. However, the model size and corresponding computational complexity are constantly scaled up in pursuit of higher performance. In this work, we present MemoryFormer, a novel transformer architecture which significantly reduces the computational complexity (FLOPs) from a new perspective. We eliminate nearly all the computations of the transformer model except for the necessary computation required by the multi-head attention operation. This is made possible by utilizing an alternative method for feature transformation to replace the linear projection of fully-connected layers. Specifically, we first construct a group of in-memory lookup tables that store a large amount of discrete vectors to replace the weight matrix used in linear projection. We then use a hash algorithm to retrieve a correlated subset of vectors dynamically based on the input embedding. The retrieved vectors combined together will form the output embedding, which provides an estimation of the result of matrix multiplication operation in a fully-connected layer. Compared to conducting matrix multiplication, retrieving data blocks from memory is a much cheaper operation which requires little computations. We train MemoryFormer from scratch and conduct extensive experiments on various benchmarks to demonstrate the effectiveness of the proposed model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accurate Prediction of Knee Joint Angles Using a Hybrid CNN-LSTM-Attention Network from Surface Electromyography

Accurate Prediction of Knee Joint Angles Using a Hybrid CNN-...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Wang, Zhuo Chen, Hui Yang, Fangliang Wang, Xiangyang Wu, Xinyu Chen, Chunjie Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen518055 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781665481090

In various fields such as robotics, rehabilitation, biomechanics, human-machine interfaces, and clinical research, human motion prediction has extensive applications. A hybrid networks model based on Convolutional Neural Network-Long Short-Term Memory-Attention (CNN-LSTM-Attention) was employed in this paper to extract features from the high-dimensional space and time series of surface electromyography (sEMG) data for continuous prediction of knee angles. Five able-bodied subjects participated in the study, walking at a self-selected pace while six surface electromyography (sEMG) signals from muscles involved in knee flexion and extension, along with knee angles, were synchronously recorded. The performance was assessed using the root mean square error (RMSE), Pearson Correlation Coefficient (r), and coefficient of determination (R2) between estimated and measured knee joint angles. Compared to the CNN, LSTM, and CNN-LSTM algorithms, the adopted method estimated knee angles more accurately, achieving an average RMSE, ρ, and R2 of 3.09± 0.90,\ 0.9911 ± 0.0052, and 0.9817± 0.0108, respectively. As the advance time increased, the accuracy of knee joint angle estimation decreased, particularly when the advance time reached 100 ms, at which point the RMSE is 4.83 degress. In addition, the computing time of the prediction model was less than 1 ms, which was shorter than the advance time 100 ms it could predict, thereby facilitating real-time computation in practical environments. Compared to previous studies, the proposed method excelled at extracting features directly from raw signals, avoiding the need for handcrafted feature extraction. Consequently, the model effectively achieved continuous and accurate predictions of joint motion angles and demonstrated potential to reduce latency in the human-machine interface. © 2024 IEEE.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

GNSS/IMU Integrated Navigation Methods with NLOS Mitigation 24

GNSS/IMU Integrated Navigation Methods with NLOS Mitigation

引用

24th COTA International Conference of Transportation Professionals: Resilient, Intelligent, Connected, and Lowcarbon Multimodal Transportation, CICTP 2024

作者： Zuo, Yang Duan, Xuting Xia, Haiying Zhou, Jianshan School of Transportation Science and Engineering Beihang Univ. Beijing China State Key Lab of Intelligent Transportation System Beijing China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control Beijing China Zhongguancun Laboratory Beijing China Key Laboratory of Operation Safety Technology on Transport Vehicles Ministry of Transport Beijing China

ISBN: (数字)9780784485484

ISBN: (纸本)9780784485484

With the development of computer technology, intelligent vehicles have become a popular orientation at present. This paper provides a solution for the traditional GNSS/IMU integrated navigation to mitigate the influence of non-line-of-sight (NLOS) environments and achieve high-precision navigation. The LOS/NLOS switching is treated as a transition in a Markov chain, and the DIMM filtering is applied to obtain GNSS-filtered data free from the influence of NLOS. GNSS/IMU integrated navigation is loose coupling in that the method combines IMU information with processed GNSS measurement using the ESKF (Error-state Kalman Filter) to achieve accurate target tracking and positioning by utilizing the state difference as the state variable. Simulation results demonstrate that the proposed method significantly improves tracking and positioning accuracy by effectively mitigating NLOS effects compared to traditional methods. This research provides an effective solution for real-world autonomous vehicle navigation systems and optimizes the city driving experience. © ASCE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Specificity-preserving RGB-D saliency detection

引用

Computational Visual Media 2023年第2期9卷 297-317页

作者： Tao Zhou Deng-Ping Fan Geng Chen Yi Zhou Huazhu Fu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina Computer Vision Lab ETH Z¨urichZ¨urichSwitzerland School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’anChina School of Computer Science and Engineering Southeast UniversityNanjingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Salient object detection(SOD)in RGB and depth images has attracted increasing research *** RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific *** this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific ***,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction *** effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level ***,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared *** using skip connections between encoder and decoder layers,hierarchical features can be fully *** experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection *** project is publicly available at https://***/taozh2017/SPNet.

关键词： salient object detection(SOD) RGB-D cross-enhanced integration module(CIM) multi-modal feature aggregation(MFA)

来源：评论

学校读者我要写书评

暂无评论

Small-Target Infrastructure Detection with Spatial Tracking and Multi-Level Feature Extraction of Railway Track Scenes

Small-Target Infrastructure Detection with Spatial Tracking ...

引用

2024 International Conference on Intelligent Communication, Sensing and Electromagnetics, ICSE 2024

作者： Du, Heng Cang, Huaiming Bai, Yiwen Wang, Xinyi Beijing Elephant Technology Co. Ltd Beijing China School of Transportation Science and Engineering Beihang University Beijing102206 China State Key Lab of Intelligent Transportation System Beijing100191 China School of Mechanical Engineering Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechanical System Design and Intelligent Control Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin300384 China

ISBN: (纸本)9798350354935

In the field of railway transportation, with the continuous improvement of train running speed and the continuous increase of operating mileage, it becomes particularly important to ensure the safety and integrity of small-Target infrastructure along the railway train. Although many small-Target detection methods have been proposed, the research on small-Target infrastructure detection along rail trains is very rare. To solve this problem, this paper proposes a small-Target infrastructure detection network with spatial tracking and multi-level feature extraction based on Yolov8n. The experimental results show that ST-YOLO has a 3.6% mAP improvement on the OSDaR23 dataset compared to the baseline Yolov8n, and shows significant advantages over other state-of-The-Art methods. © 2024 IEEE.

关键词： Railroads

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：